Paper Digest: NeurIPS 2023 Highlights
1, Toolformer: Language Models Can Teach Themselves to Use Tools
Timo Schick; Jane Dwivedi-Yu; Roberto Dessi; Roberta Raileanu; Maria Lomeli; Eric Hambro; Luke Zettlemoyer; Nicola Cancedda; Thomas Scialom;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we show that LMs can teach themselves to *use external tools* via simple APIs and achieve the best of both worlds.
2, Self-Refine: Iterative Refinement with Self-Feedback
Aman Madaan; Niket Tandon; Prakhar Gupta; Skyler Hallinan; Luyu Gao; Sarah Wiegreffe; Uri Alon; Nouha Dziri; Shrimai Prabhumoye; Yiming Yang; Shashank Gupta; Bodhisattwa Prasad Majumder; Katherine Hermann; Sean Welleck; Amir Yazdanbakhsh; Peter Clark;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through iterative feedback and refinement.
3, Vicuna Evaluation: Exploring LLM-as-a-Judge and Chatbot Arena
Lianmin Zheng; Wei-Lin Chiang; Ying Sheng; Siyuan Zhuang; Zhanghao Wu; Yonghao Zhuang; Zi Lin; Zhuohan Li; Dacheng Li; Eric Xing; Hao Zhang; Joseph Gonzalez; Ion Stoica;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them.
4, Mathematical Capabilities of ChatGPT
Simon Frieder; Luca Pinchetti; Chevalier; Ryan-Rhys Griffiths; Tommaso Salvatori; Thomas Lukasiewicz; Philipp Petersen; Julius Berner;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We investigate the mathematical capabilities of two iterations of ChatGPT (released 9-January-2023 and 30-January-2023) and of GPT-4 by testing them on publicly available datasets, as well as hand-crafted ones, using a novel methodology.
5, The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only
Guilherme Penedo; Quentin Malartic; Daniel Hesslow; Ruxandra Cojocaru; Hamza Alobeidli; Alessandro Cappelli; Baptiste Pannier; Ebtesam Almazrouei; Julien Launay;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, as larger models requiring pretraining on trillions of tokens are considered, it is unclear how scalable is curation, and whether we will run out of unique high-quality data soon. At variance with previous beliefs, we show that properly filtered and deduplicated web data alone can lead to powerful models; even significantly outperforming models trained on The Pile.
6, InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
Wenliang Dai; Junnan Li; DONGXU LI; Anthony Meng Huat Tiong; Junqi Zhao; Weisheng Wang; Boyang Li; Pascale N Fung; Steven Hoi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pretrained BLIP-2 models.
7, QLoRA: Efficient Finetuning of Quantized LLMs
Tim Dettmers; Artidoro Pagnoni; Ari Holtzman; Luke Zettlemoyer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present QLoRA, an efficient finetuning approach that reduces memory usage enough to finetune a 65B parameter model on a single 48GB GPU while preserving full 16-bit finetuning task performance.
8, Language Is Not All You Need: Aligning Perception with Language Models
Shaohan Huang; Li Dong; Wenhui Wang; Yaru Hao; Saksham Singhal; Shuming Ma; Tengchao Lv; Lei Cui; Owais Khan Mohammed; Barun Patra; Qiang Liu; Kriti Aggarwal; Zewen Chi; Nils Bjorck; Vishrav Chaudhary; Subhojit Som; XIA SONG; Furu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce KOSMOS-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot).
9, Reflexion: Language Agents with Verbal Reinforcement Learning
Noah Shinn; Federico Cassano; Ashwin Gopinath; Karthik Narasimhan; Shunyu Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose Reflexion, a novel framework to reinforce language agents not by updating weights, but instead through linguistic feedback.
10, Scaling Data-Constrained Language Models
Niklas Muennighoff; Alexander Rush; Boaz Barak; Teven Le Scao; Nouamane Tazi; Aleksandra Piktus; Thomas Wolf; Colin Raffel; Sampo Pyysalo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose and empirically validate a scaling law for compute optimality that accounts for the decreasing value of repeated tokens and excess parameters.
11, LIMA: Less Is More for Alignment
Chunting Zhou; Pengfei Liu; Puxin Xu; Srinivasan Iyer; Jiao Sun; Yuning Mao; Xuezhe Ma; Avia Efrat; Ping Yu; LILI YU; Susan Zhang; Gargi Ghosh; Mike Lewis; Luke Zettlemoyer; Omer Levy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Large language models are trained in two stages: (1) unsupervised pretraining from raw text, to learn general-purpose representations, and (2) large scale instruction tuning and reinforcement learning, to better align to end tasks and user preferences. We measure the relative importance of these two stages by training LIMA, a 65B parameter LLaMa language model fine-tuned with the standard supervised loss on only 1,000 carefully curated prompts and responses, without any reinforcement learning or human preference modeling
12, Segment Everything Everywhere All at Once
Xueyan Zou; Jianwei Yang; Hao Zhang; Feng Li; Linjie Li; Jianfeng Wang; Lijuan Wang; Jianfeng Gao; Yong Jae Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present SEEM, a promotable and interactive model for segmenting everything everywhere all at once in an image.
13, Language Models Can Solve Computer Tasks
Geunwoo Kim; Pierre Baldi; Stephen McAleer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent recursively criticizes and improves its output (RCI).
14, Stable Bias: Evaluating Societal Representations in Diffusion Models
Sasha Alexandra Luccioni; Christopher Akiki; Margaret Mitchell; Yacine Jernite;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This evaluation, however, is made more difficult by the synthetic nature of these systems’ outputs: common definitions of diversity are grounded in social categories of people living in the world, whereas the artificial depictions of fictive humans created by these systems have no inherent gender or ethnicity. To address this need, we propose a new method for exploring the social biases in TTI systems.
15, HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends in Hugging Face
Yongliang Shen; Kaitao Song; Xu Tan; Dongsheng Li; Weiming Lu; Yueting Zhuang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Considering large language models (LLMs) have exhibited exceptional ability in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks and language could be a generic interface to empower this. Based on this philosophy, we present HuggingGPT, a framework that leverages LLMs (e.g., ChatGPT) to connect various AI models in machine learning communities (e.g., Hugging Face) to solve AI tasks.
16, Direct Preference Optimization: Your Language Model Is Secretly A Reward Model
Rafael Rafailov; Archit Sharma; Eric Mitchell; Christopher D Manning; Stefano Ermon; Chelsea Finn;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, RLHF is a complex and often unstable procedure, first fitting a reward model that reflects the human preferences, and then fine-tuning the large unsupervised LM using reinforcement learning to maximize this estimated reward without drifting too far from the original model. In this paper, we leverage a mapping between reward functions and optimal policies to show that this constrained reward maximization problem can be optimized exactly with a single stage of policy training, essentially solving a classification problem on the human preference data.
17, StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
Yonglong Tian; Lijie Fan; Phillip Isola; Huiwen Chang; Dilip Krishnan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We show that (1) when the generative model is properly configured, training self-supervised methods on synthetic images can match or beat the real image counterpart;(2) by treating the multiple images generated from the same text prompt as positives for each other, we develop a multi-positive contrastive learning method, which we call StableRep.
18, Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting
Miles Turpin; Julian Michael; Ethan Perez; Samuel Bowman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs�e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always (A)�which models systematically fail to mention in their explanations.
19, ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Jiazheng Xu; Xiao Liu; Yuchen Wu; Yuxuan Tong; Qinkai Li; Ming Ding; Jie Tang; Yuxiao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a comprehensive solution to learn and improve text-to-image models from human preference feedback.
20, Self-Supervised Learning with Lie Symmetries for Partial Differential Equations
Grégoire Mialon; Quentin Garrido; Hannah Lawrence; Danyal Rehman; Bobak Kiani; Yann LeCun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we learn general-purpose representations of PDEs from heterogeneous data by implementing joint embedding methods for self-supervised learning (SSL), a framework for unsupervised representation learning that has had notable success in computer vision.
21, Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
Yuval Kirstain; Adam Polyak; Uriel Singer; Shahbuland Matiana; Joe Penna; Omer Levy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences.
22, Distributed Inference and Fine-tuning of Large Language Models Over The Internet
Alexander Borzunov; Dmitry Baranchuk; Tim Dettmers; Max Ryabinin; Younes Belkada; Artem Chumachenko; Pavel Samygin; Colin Raffel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate methods for cost-efficient inference and fine-tuning of LLMs, comparing local and distributed strategies.
23, Visual Instruction Tuning
Haotian Liu; Chunyuan Li; Qingyang Wu; Yong Jae Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present the first attempt to use language-only GPT-4 to generate multimodal language-image instruction-following data. By instruction tuning on such generated data, we introduce LLaVA: Large Language and Vision Assistant, an end-to-end trained large multimodal model that connects a vision encoder and an LLM for general-purpose visual and language understanding.
24, Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from The Data Perspective
Huayang Li; Tian Lan; Zihao Fu; Deng Cai; Lemao Liu; Nigel Collier; Taro Watanabe; Yixuan Su;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we aim to advance our understanding by presenting a straightforward and unified explanation from the data perspective.
25, AlpacaFarm: A Simulation Framework for Methods That Learn from Human Feedback
Yann Dubois; Xuechen Li; Rohan Taori; Tianyi Zhang; Ishaan Gulrajani; Jimmy Ba; Carlos Guestrin; Percy Liang; Tatsunori Hashimoto;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Replicating and understanding this instruction-following process faces three major challenges: the high cost of data collection, the lack of trustworthy evaluation, and the absence of reference method implementations. We address these bottlenecks with AlpacaFarm, a simulator that enables research and development for learning from feedback at a low cost.
26, Dissecting Knowledge Distillation: An Exploration of Its Inner Workings and Applications
Utkarsh Ojha; Yuheng Li; Anirudh Sundara Rajan; Yingyu Liang; Yong Jae Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Does its data invariance properties become similar? Our work presents a comprehensive study to try to answer these questions.
27, OpenProteinSet: Training Data for Structural Biology at Scale
Gustaf Ahdritz; Nazim Bouatta; Sachin Kadyan; Lukas Jarosch; Dan Berenberg; Ian Fisk; Andrew Watkins; Stephen Ra; Richard Bonneau; Mohammed AlQuraishi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Generation of MSAs is highly computationally intensive, however, and no datasets comparable to those used to train AlphaFold2 have been made available to the research community, hindering progress in machine learning for proteins. To remedy this problem, we introduce OpenProteinSet, an open-source corpus of more than 16 million MSAs, associated structural homologs from the Protein Data Bank, and AlphaFold2 protein structure predictions.
28, Does Localization Inform Editing? Surprising Differences in Causality-Based Localization Vs. Knowledge Editing in Language Models
Peter Hase; Mohit Bansal; Been Kim; Asma Ghandeharioun;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we find that we can change how a fact is stored in a model by editing weights that are in a different location than where existing methods suggest that the fact is stored.
29, Towards Automated Circuit Discovery for Mechanistic Interpretability
Arthur Conmy; Augustine Mavor-Parker; Aengus Lynch; Stefan Heimersheim; Adrià Garriga-Alonso;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work proposes a novel algorithm, Automatic Circuit DisCovery (ACDC), to automate the identification of the important units in the network.
30, Visual Instruction Inversion: Image Editing Via Image Prompting
Thao Nguyen; Yuheng Li; Utkarsh Ojha; Yong Jae Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a method for image editing via visual prompting.
31, Paraphrasing Evades Detectors of AI-generated Text, But Retrieval Is An Effective Defense
Kalpesh Krishna; Yixiao Song; Marzena Karpinska; John Wieting; Mohit Iyyer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To increase the robustness of AI-generated text detection to paraphrase attacks, we introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
32, SceneScape: Text-Driven Consistent Scene Generation
Rafail Fridman; Amit Abecasis; Yoni Kasten; Tali Dekel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a method for text-driven perpetual view generation -- synthesizing long-term videos of various scenes solely, given an input text prompt describing the scene and camera poses.
33, Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation
Binhui Xie; Shuang Li; Qingju Guo; Chi Liu; Xinjing Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents Annotator, a general and efficient active learning baseline, in which a plain voxel-centric online selection strategy is tailored to probe and annotate the salient and exemplar voxel girds within each LiDAR scan, broadening the potential of segmentation performance even under distribution shift.
34, Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
Oleg Platonov; Denis Kuznedelev; Artem Babenko; Liudmila Prokhorenkova;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that commonly used homophily measures have critical drawbacks preventing the comparison of homophily levels across different datasets.
35, Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Shunyu Yao; Dian Yu; Jeffrey Zhao; Izhak Shafran; Tom Griffiths; Yuan Cao; Karthik Narasimhan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This means they can fall short in tasks that require exploration, strategic lookahead, or where initial decisions play a pivotal role. To surmount these challenges, we introduce a new framework for language model inference, Tree of Thoughts (ToT), which generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.
36, Guide Your Agent with Adaptive Multimodal Rewards
Changyeon Kim; Younggyo Seo; Hao Liu; Lisa Lee; Jinwoo Shin; Honglak Lee; Kimin Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we instead propose to utilize the knowledge captured within large vision-language models for improving the generalization capability of control agents.
37, C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
Yuzhen Huang; Yuzhuo Bai; Zhihao Zhu; Junlei Zhang; Jinghan Zhang; Tangjun Su; Junteng Liu; Chuancheng Lv; Yikai Zhang; jiayi lei; Yao Fu; Maosong Sun; Junxian He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context.
38, Grounded Decoding: Guiding Text Generation with Grounded Models for Robot Control
Wenlong Huang; Fei Xia; Dhruv Shah; Danny Driess; Andy Zeng; Yao Lu; Pete Florence; Igor Mordatch; Sergey Levine; Karol Hausman; brian ichter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, if we want to make use of the semantic knowledge in a language model while still situating it in an embodied setting, we must construct an action sequence that is both likely according to the language model and also realizable according to grounded models of the environment. We frame this as a problem similar to probabilistic filtering: decode a sequence that both has high probability under the language model and high probability under a set of grounded model objectives.
39, BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
Xuan Chen; Wenbo Guo; Guanhong Tao; Xiangyu Zhang; Dawn Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite initial defenses proposed in recent studies, these methods have very limited generalizability and scalability. To address this issue, we propose BIRD, a technique to detect and remove backdoors from a pretrained DRL policy in a clean environment without requiring any knowledge about the attack specifications and accessing its training process.
40, Battle of The Backbones: A Large-Scale Comparison of Pretrained Models Across Computer Vision Tasks
Micah Goldblum; Hossein Souri; Renkun Ni; Manli Shu; Viraj Prabhu; Gowthami Somepalli; Prithvijit Chattopadhyay; Adrien Bardes; Mark Ibrahim; Judy Hoffman; Rama Chellappa; Andrew Wilson; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Battle of the Backbones (BoB) makes this choice easier by benchmarking a diverse suite of pretrained models, including vision-language models, those trained via self-supervised learning, and the Stable Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more.
41, A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning
Valeriia Cherepanova; Gowthami Somepalli; Jonas Geiping; C. Bayan Bruss; Andrew Wilson; Tom Goldstein; Micah Goldblum;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We construct a challenging feature selection benchmark evaluated on downstream neural networks including transformers, using real datasets and multiple methods for generating extraneous features.
42, Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition
Samuel Dooley; Rhea Sukthanker; John Dickerson; Colin White; Frank Hutter; Micah Goldblum;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Motivated by the belief that the inductive bias of a model architecture is more important than the bias mitigation strategy, we take a different approach to bias mitigation.
43, Are Aligned Neural Networks Adversarially Aligned?
Nicholas Carlini; Florian Tramer; Daphne Ippolito; Ludwig Schmidt; Milad Nasr; Matthew Jagielski; Pang Wei Koh; Irena Gao; Christopher A. Choquette-Choo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: They respond helpfully to user questions, but when asked to perform some behavior that would cause harm, will politely refuse. We study to what extent these models are aligned even when interacting with an adversarial user who constructs worst-case adversarial example inputs.
44, Patch N’ Pack: NaViT, A Vision Transformer for Any Aspect Ratio and Resolution
Mostafa Dehghani; Basil Mustafa; Josip Djolonga; Jonathan Heek; Matthias Minderer; Mathilde Caron; Andreas Steiner; Joan Puigcerver; Robert Geirhos; Ibrahim Alabdulmohsin; Avital Oliver; Piotr Padlewski; Alexey Gritsenko; Mario Lucic; Neil Houlsby;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, models such as the Vision Transformer (ViT) offer flexible sequence-based modeling, and hence varying input sequence lengths. We take advantage of this with NaViT (Native Resolution ViT) which uses sequence packing during training to process inputs of arbitrary resolutions and aspect ratios.
45, Likelihood-Based Diffusion Language Models
Ishaan Gulrajani; Tatsunori Hashimoto;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we take the first steps towards closing the perplexity gap between autoregressive and diffusion-based language models, with the goal of building and releasing a diffusion model which outperforms the smallest widely-adopted autoregressive model (GPT-2 124M).
46, Structural Pruning for Diffusion Models
Gongfan Fang; Xinyin Ma; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The impressive capability of these models, however, often entails significant computational overhead during both training and inference. To tackle this challenge, we present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones, without the need for extensive re-training.
47, Data Selection for Language Models Via Importance Resampling
Sang Michael Xie; Shibani Santurkar; Tengyu Ma; Percy Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Instead, we extend the classic importance resampling approach used in low-dimensions for LM data selection. We propose Data Selection with Importance Resampling (DSIR), an efficient and scalable framework that estimates importance weights in a reduced feature space for tractability and selects data with importance resampling according to these weights.
48, Learning Universal Policies Via Text-Guided Video Generation
Yilun Du; Mengjiao (Sherry) Yang; Bo Dai; Hanjun Dai; Ofir Nachum; Josh Tenenbaum; Dale Schuurmans; Pieter Abbeel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent progress in text-guided image synthesis has yielded models with an impressive ability to generate complex novel images, exhibiting combinatorial generalization across domains. Motivated by this success, we investigate whether such tools can be used to construct more general-purpose agents.
49, Counterfactual Memorization in Neural Language Models
Chiyuan Zhang; Daphne Ippolito; Katherine Lee; Matthew Jagielski; Florian Tramer; Nicholas Carlini;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We formulate a notion of counterfactual memorization which characterizes how a model's predictions change if a particular document is omitted during training.
50, Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Zhiqing Sun; Yikang Shen; Qinhong Zhou; Hongxin Zhang; Zhenfang Chen; David Cox; Yiming Yang; Chuang Gan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, this dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision and the related issues on quality, reliability, diversity, self-consistency, and undesirable biases. To address these challenges, we propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision.
51, Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Zeqiu Wu; Yushi Hu; Weijia Shi; Nouha Dziri; Alane Suhr; Prithviraj (Raj) Ammanabrolu; Noah Smith; Mari Ostendorf; Hannaneh Hajishirzi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we use fine-grained human feedback (e.g., which sentence is false, which sub-sentence is irrelevant) as an explicit training signal.
52, VisoGender: A Dataset for Benchmarking Gender Bias in Image-text Pronoun Resolution
Siobhan Mackenzie Hall; Fernanda Gonçalves Abrantes; Hanwen Zhu; Grace Sodunke; Aleksandar Shtedritski; Hannah Rose Kirk;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce VisoGender, a novel dataset for benchmarking gender bias in vision-language models.
53, TextDiffuser: Diffusion Models As Text Painters
Jingye Chen; Yupan Huang; Tengchao Lv; Lei Cui; Qifeng Chen; Furu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Diffusion models have gained increasing attention for their impressive generation abilities but currently struggle with rendering accurate and coherent text. To address this issue, we introduce TextDiffuser, focusing on generating images with visually appealing text that is coherent with backgrounds.
54, Isotropic Loss Design for Non-contrastive SSL
Manu Srinath Halvagal; Axel Laborieux; Friedemann Zenke;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we analytically study learning dynamics under cosine similarity in the eigenspace of the predictor network and show that collapse is avoided through implicit variance regularization similar to Euclidean loss but with fundamentally different dynamics.
55, ToolkenGPT: Augmenting Frozen Language Models with Massive Tools Via Tool Embeddings
Shibo Hao; Tianyang Liu; Zhen Wang; Zhiting Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Although the latter method offers adaptability to new tools, it struggles with the inherent context length constraint of LLMs when many new tools are presented, and mastering a new set of tools with few-shot examples remains challenging, resulting in suboptimal performance. To address these limitations, we propose a novel solution, named **ToolkenGPT**, wherein LLMs effectively learn to master tools as predicting tokens through **tool embeddings** for solving complex tasks.
56, Generating Images with Multimodal Language Models
Jing Yu Koh; Daniel Fried; Russ Salakhutdinov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a method to fuse frozen text-only large language models (LLMs) with pre-trained image encoder and decoder models, by mapping between their embedding spaces.
57, Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models
Ying Fan; Olivia Watkins; Yuqing Du; Hao Liu; Moonkyung Ryu; Craig Boutilier; Pieter Abbeel; Mohammad Ghavamzadeh; Kangwook Lee; Kimin Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose using reinforcement learning (RL) to fine-tune text-to-image models.
58, Solving Inverse Problems Provably Via Posterior Sampling with Latent Diffusion Models
Litu Rout; Negin Raoof; Giannis Daras; Constantine Caramanis; Alex Dimakis; Sanjay Shakkottai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the first framework to solve general inverse problems leveraging pre-trained *latent* diffusion models.
59, Ordering-based Conditions for Global Convergence of Policy Gradient Methods
Jincheng Mei; Bo Dai; Alekh Agarwal; Mohammad Ghavamzadeh; Csaba Szepesvari; Dale Schuurmans;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We prove that, for finite-arm bandits with linear function approximation, the global convergence of policy gradient (PG) methods depends on inter-related properties between the policy update and the representation.
60, Optimizing Prompts for Text-to-Image Generation
Yaru Hao; Zewen Chi; Li Dong; Furu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Instead of laborious human engineering, we propose prompt adaptation, a general framework that automatically adapts original user input to model-preferred prompts.
61, Language Models Augmented with Decoupled Memory
Weizhi Wang; Li Dong; Hao Cheng; Xiaodong Liu; Xifeng Yan; Jianfeng Gao; Furu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Decoupled-Memory-Augmented LLMs (DeMA), which enables LLMs to memorize long history.
62, Extensible Prompts for Language Models on Zero-shot Language Style Customization
Tao Ge; Hu Jing; Li Dong; Shaoguang Mao; Yan Xia; Xun Wang; Si-Qing Chen; Furu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose eXtensible Prompt (X-Prompt) for prompting a large language model (LLM) beyond natural language (NL).
63, LLaVA-Med: Training A Large Language-and-Vision Assistant for Biomedicine in One Day
Chunyuan Li; Cliff Wong; Sheng Zhang; Naoto Usuyama; Haotian Liu; Jianwei Yang; Tristan Naumann; Hoifung Poon; Jianfeng Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a cost-efficient approach for training a vision-language conversational assistant that can answer open-ended research questions of biomedical images.
64, Tracr: Compiled Transformers As A Laboratory for Interpretability
David Lindner; Janos Kramar; Sebastian Farquhar; Matthew Rahtz; Tom McGrath; Vladimir Mikulik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We show how to compile human-readable programs into standard decoder-only transformer models.
65, Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off
Zichen Zhang; Johannes Kirschner; Junxi Zhang; Francesco Zanini; Alex Ayoub; Masood Dehghan; Dale Schuurmans;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The impact of time discretization on RL methods has not been fully characterized in existing theory, but a more detailed analysis of its effect could reveal opportunities for improving data-efficiency. We address this gap by analyzing Monte-Carlo policy evaluation for LQR systems and uncover a fundamental trade-off between approximation and statistical error in value estimation.
66, Multi-Objective Agency Requires Non-Markovian Rewards
Silviu Pitis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a practical non-Markovian aggregation scheme that overcomes the impossibility with only one additional parameter for each objective.
67, Bypass Exponential Time Preprocessing: Fast Neural Network Training Via Weight-Data Correlation Preprocessing
Josh Alman; 杰昊 梁; Zhao Song; Ruizhe Zhang; Danyang Zhuo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a new preprocessing method that simply stores the weight-data correlation in a tree data structure in order to quickly, dynamically detect which neurons fire at each iteration.
68, LLM-Pruner: On The Structural Pruning of Large Language Models
Xinyin Ma; Gongfan Fang; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: With LLM being a general-purpose task solver, we explore its compression in a task-agnostic manner, which aims to preserve the multi-task solving and language generation ability of the original LLM.
69, Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells
Rylan Schaeffer; Mikail Khona; Tzuhsuan Ma; Cristobal Eyzaguirre; Sanmi Koyejo; Ila Fiete;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We define a novel self-supervised learning (SSL) framework for properly arranging representations in an abstract coding space, and show that it can produce grid codes when constrained to perform high-efficiency representation of space with recurrent neural networks.
70, Are Emergent Abilities of Large Language Models A Mirage?
Rylan Schaeffer; Brando Miranda; Sanmi Koyejo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present our alternative explanation in a simple mathematical model, then test it in three complementary ways: we (1) make, test and confirm three predictions on the effect of metric choice using the InstructGPT/GPT-3 family on tasks with claimed emergent abilities, (2) make, test and confirm two predictions about metric choices in a meta-analysis of emergent abilities on BIG-Bench; and (3) show how to choose metrics to produce never-before-seen seemingly emergent abilities in multiple vision tasks across diverse deep networks.
71, Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
Wanrong Zhu; Jack Hessel; Anas Awadalla; Samir Yitzhak Gadre; Jesse Dodge; Alex Fang; Youngjae Yu; Ludwig Schmidt; William Yang Wang; Yejin Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We use a linear assignment algorithm to place images into longer bodies of text using CLIP features, a process that we show outperforms alternatives.
72, DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization
Zhiqing Sun; Yiming Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper broadens the current scope of neural solvers for NPC problems by introducing a new graph-based diffusion framework, namely DIFUSCO.
73, Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models
Pan Lu; Baolin Peng; Hao Cheng; Michel Galley; Kai-Wei Chang; Ying Nian Wu; Song-Chun Zhu; Jianfeng Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, LLMs have inherent limitations as they are incapable of accessing up-to-date information (stored on the Web or in task-specific knowledge bases), using external tools, and performing precise mathematical and logical reasoning. In this paper, we present Chameleon, an AI system that mitigates these limitations by augmenting LLMs with plug-and-play modules for compositional reasoning.
74, Unlimiformer: Long-Range Transformers with Unlimited Length Input
Amanda Bertsch; Uri Alon; Graham Neubig; Matthew Gormley;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose Unlimiformer: a general approach that wraps any existing pretrained encoder-decoder transformer, and offloads the cross-attention computation to a single $k$-nearest-neighbor ($k$NN) index, while the returned $k$NN distances are the attention dot-product scores.
75, Simple and Controllable Music Generation
Jade Copet; Felix Kreuk; Itai Gat; Tal Remez; Gabriel Synnaeve; Yossi Adi; Alexandre Defossez;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens.
76, Setting The Trap: Capturing and Defeating Backdoor Threats in PLMs Through Honeypots
Ruixiang Tang; Jiayi Yuan; Yiming Li; Zirui Liu; Rui Chen; Xia Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, our objective is to develop a backdoor-resistant tuning procedure that yields a backdoor-free model, no matter whether the fine-tuning dataset contains poisoned samples.
77, Faith and Fate: Limits of Transformers on Compositionality
Nouha Dziri; Ximing Lu; Melanie Sclar; Xiang (Lorraine) Li; Liwei Jiang; Bill Yuchen Lin; Sean Welleck; Peter West; Chandra Bhagavatula; Ronan Le Bras; Jena Hwang; Soumya Sanyal; Xiang Ren; Allyson Ettinger; Zaid Harchaoui; Yejin Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a measure of compositional complexity, we introduce computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.
78, What Makes Good Examples for Visual In-Context Learning?
Yuanhan Zhang; Kaiyang Zhou; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To demystify in-context learning in computer vision, we conduct an extensive research and identify a critical problem: downstream performance is highly sensitivie to the choice of visual in-context examples. To address this problem, we propose a prompt retrieval framework specifically for large vision models, allowing the selection of in-context examples to be fully automated.
79, Fast Attention Requires Bounded Entries
Josh Alman; Zhao Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate whether faster algorithms are possible by \emph{implicitly} making use of the matrix $A$.
80, Simplifying and Empowering Transformers for Large-Graph Representations
Qitian Wu; Wentao Zhao; Chenxiao Yang; Hengrui Zhang; Fan Nie; Haitian Jiang; Yatao Bian; Junchi Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we critically demonstrate that even using a one-layer attention can bring up surprisingly competitive performance across node property prediction benchmarks where node numbers range from thousand-level to billion-level.
81, RealTime QA: What's The Answer Right Now?
Jungo Kasai; Keisuke Sakaguchi; yoichi takahashi; Ronan Le Bras; Akari Asai; Xinyan Yu; Dragomir Radev; Noah Smith; Yejin Choi; Kentaro Inui;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce RealTime QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version).
82, Segment Anything in 3D with NeRFs
Jiazhong Cen; Zanwei Zhou; Jiemin Fang; chen yang; Wei Shen; Lingxi Xie; Dongsheng Jiang; XIAOPENG ZHANG; Qi Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper aims to generalize SAM to segment 3D objects.
83, LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion
Jiaqi Guan; Xingang Peng; PeiQi Jiang; Yunan Luo; Jian Peng; Jianzhu Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address a more general problem where the poses of the fragments are *unknown* in 3D space.
84, ClusterFomer: Clustering As A Universal Visual Learner
James Liang; Yiming Cui; Qifan Wang; Tong Geng; Wenguan Wang; Dongfang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents ClusterFormer, a universal vision model that is based on the Clustering paradigm with TransFormer.
85, Perfect Linear Concept Erasure in Closed Form
Nora Belrose; David Schneider-Joseph; Shauli Ravfogel; Ryan Cotterell; Edward Raff; Stella Biderman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We prove that a rank $k - 1$ orthogonal projection is sufficient to perfectly guard a $k$-class concept from all linear adversaries with convex loss functions, and provide the formula in closed form.
86, Language Models Meet World Models: Embodied Experiences Enhance Language Models
Jiannan Xiang; Tianhua Tao; Yi Gu; Tianmin Shu; Zirui Wang; Zichao Yang; Zhiting Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The limitation arises from the fact that LMs are trained only on written text and miss essential embodied knowledge and skills. In this paper, we propose a new paradigm of enhancing LMs by finetuning them with world models, to gain diverse embodied knowledge while retaining their general language capabilities.
87, Provably Bounding Neural Network Preimages
Christopher Brix; Suhas Kotha; Huan Zhang; J. Zico Kolter; Krishnamurthy Dvijotham;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present the INVPROP algorithm for verifying properties over the preimage of a linearly constrained output set of a neural network, which can be combined with branch-and-bound to increase precision.
88, Does Progress on ImageNet Transfer to Real-world Datasets?
Alex Fang; Simon Kornblith; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In particular, we study datasets collected with the goal of solving real-world tasks (e.g., classifying images from camera traps or satellites), as opposed to web-scraped benchmarks collected for comparing models.
89, What Is The Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models
Khashayar Gatmiry; Zhiyuan Li; Tengyu Ma; Sashank Reddi; Stefanie Jegelka; Ching-Yao Chuang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that with the standard Restricted Isometry Property (RIP) on the measurements, minimizing the trace of Hessian is approximately equivalent to minimizing the Schatten 1-norm of the corresponding end-to-end matrix parameters (i.e., the product of all layer matrices), which in turn leads to better generalization.
90, VisionLLM: Large Language Model Is Also An Open-Ended Decoder for Vision-Centric Tasks
Wenhai Wang; Zhe Chen; Xiaokang Chen; Jiannan Wu; Xizhou Zhu; Gang Zeng; Ping Luo; Tong Lu; Jie Zhou; Yu Qiao; Jifeng Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present an LLM-based framework for vision-centric tasks, termed VisionLLM.
91, Fine-Tuning Language Models with Just Forward Passes
Sadhika Malladi; Tianyu Gao; Eshaan Nichani; Alex Damian; Jason Lee; Danqi Chen; Sanjeev Arora;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a memory-efficient zeroth-order optimizer (MeZO), adapting the classical ZO-SGD method to operate in-place, thereby fine-tuning LMs with the same memory footprint as inference.
92, Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization
Aniket Murhekar; Zhuowen Yuan; Bhaskar Ray Chaudhury; Bo Li; Ruta Mehta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we model a collaborative FL framework, where every agent attempts to achieve an optimal trade-off between her learning payoff and data sharing cost.
93, Scaling Riemannian Diffusion Models
Aaron Lou; Minkai Xu; Adam Farris; Stefano Ermon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, the additional geometric complexity renders the diffusion transition term inexpressible in closed form, so prior methods resort to imprecise approximations of the score matching training objective that degrade performance and preclude applications in high dimensions. In this work, we reexamine these approximations and propose several practical improvements.
94, (Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More
Jan Schuchardt; Yan Scholten; Stephan Günnemann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For the first time, we propose a sound notion of adversarial robustness that accounts for task equivariance.
95, PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning About Change
Karthik Valmeekam; Matthew Marquez; Alberto Olmo; Sarath Sreedharan; Subbarao Kambhampati;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: There is a strong need for systematic and extensible planning benchmarks with sufficient diversity to evaluate whether LLMs have innate planning capabilities. Motivated by this, we propose PlanBench, an extensible benchmark suite based on the kinds of domains used in the automated planning community, especially in the International Planning Competition, to test the capabilities of LLMs in planning or reasoning about actions and change.
96, On The Planning Abilities of Large Language Models - A Critical Investigation
Karthik Valmeekam; Matthew Marquez; Sarath Sreedharan; Subbarao Kambhampati;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities.
97, InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback
John Yang; Akshara Prabhakar; Karthik Narasimhan; Shunyu Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While LLMs have recently exhibited promising coding capabilities, current coding benchmarks mostly consider a static instruction-to-code sequence transduction process, which has the potential for error propagation and a disconnect between the generated code and its final execution environment. To address this gap, we introduce InterCode, a lightweight, flexible, and easy-to-use framework for constructing interactive code environments with multiple types of feedback signals.
98, Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Mitsuhiko Nakamoto; Yuexiang Zhai; Anikait Singh; Max Sobol Mark; Yi Ma; Chelsea Finn; Aviral Kumar; Sergey Levine;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we devise an approach for learning an effective initialization from offline data that also enables fast online fine-tuning capabilities.
99, Diffusion Self-Guidance for Controllable Image Generation
Dave Epstein; Allan Jabri; Ben Poole; Alexei Efros; Aleksander Holynski;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce self-guidance, a method that provides precise control over properties of the generated image by guiding the internal representations of diffusion models.
100, Stable and Low-precision Training for Large-scale Vision-language Models
Mitchell Wortsman; Tim Dettmers; Luke Zettlemoyer; Ari Morcos; Ali Farhadi; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce new methods for 1) accelerating and 2) stabilizing training for large language-vision models.
101, Collaborative Development of NLP Models
Fereshte Khani; Marco Tulio Ribeiro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, the exhaustive delineation of a concept is challenging, and an improper approach can create shortcuts or interfere with original data or other concepts. To address these challenges, we introduce CoDev, a framework that enables multi-user interaction with the model, thereby mitigating individual limitations.
102, The Clock and The Pizza: Two Stories in Mechanistic Explanation of Neural Networks
Ziqian Zhong; Ziming Liu; Max Tegmark; Jacob Andreas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Using modular addition as a prototypical problem, we show that algorithm discovery in neural networks is sometimes more complex: small changes to model hyperparameters and initializations can induce discovery of qualitatively different algorithms from a fixed training set, and even learning of multiple different solutions in parallel.
103, Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Arpit Bansal; Eitan Borgnia; Hong-Min Chu; Jie Li; Hamid Kazemi; Furong Huang; Micah Goldblum; Jonas Geiping; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact, an entire family of generative models can be constructed by varying this choice.
104, Where Are We in The Search for An Artificial Visual Cortex for Embodied Intelligence?
Arjun Majumdar; Karmesh Yadav; Sergio Arnaud; Jason Yecheng Ma; Claire Chen; Sneha Silwal; Aryan Jain; Vincent-Pierre Berges; Tingfan Wu; Jay Vakil; Pieter Abbeel; Jitendra Malik; Dhruv Batra; Yixin Lin; Oleksandr Maksymets; Aravind Rajeswaran; Franziska Meier;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual ‘foundation models’ for Embodied AI.
105, In-Context Impersonation Reveals Large Language Models' Strengths and Biases
Leonard Salewski; Isabel Rio-Torto; Stephan Alaniz; Eric Schulz; Zeynep Akata;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In everyday conversations, humans can take on different roles and adapt their vocabulary to their chosen roles. We explore whether LLMs can take on, that is impersonate, different roles when they generate text in-context.
106, Synthetic Pretraining for Few-shot Black-Box Optimization
Tung Nguyen; Sudhanshu Agrawal; Aditya Grover;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address the more challenging yet realistic setting of few-shot black-box optimization, where only a few labeled data points are available.
107, ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling
Tung Nguyen; Jason Jewik; Hritik Bansal; Prakhar Sharma; Aditya Grover;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce ClimateLearn, an open-source PyTorch library that vastly simplifies the training and evaluation of machine learning models for data-driven climate science.
108, SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
Cheng-Yu Hsieh; Jieyu Zhang; Zixian Ma; Aniruddha Kembhavi; Ranjay Krishna;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This hackability is so dire that blind models with no access to the image outperform state-of-the-art vision-language models. To remedy this rampant vulnerability, we introduce $\textit{SugarCrepe}$, a new benchmark for vision-language compositionality evaluation.
109, Scalable 3D Captioning with Pretrained Models
Tiange Luo; Chris Rockwell; Honglak Lee; Justin Johnson;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects.
110, Timewarp: Transferable Acceleration of Molecular Dynamics By Learning Time-Coarsened Dynamics
Leon Klein; Andrew Foong; Tor Fjelde; Bruno Mlodozeniec; Marc Brockschmidt; Sebastian Nowozin; Frank Noe; Ryota Tomioka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present *Timewarp*, an enhanced sampling method which uses a normalising flow as a proposal distribution in a Markov chain Monte Carlo method targeting the Boltzmann distribution.
111, Inference-Time Intervention: Eliciting Truthful Answers from A Language Model
Kenneth Li; Oam Patel; Fernanda Viégas; Hanspeter Pfister; Martin Wattenberg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Inference-Time Intervention (ITI), a technique designed to enhance the truthfulness of large language models (LLMs).
112, DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
Sang Michael Xie; Hieu Pham; Xuanyi Dong; Nan Du; Hanxiao Liu; Yifeng Lu; Percy Liang; Quoc V Le; Tengyu Ma; Adams Wei Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a small proxy model using group distributionally robust optimization (Group DRO) over domains to produce domain weights (mixture proportions) without knowledge of downstream tasks. We then resample a dataset with these domain weights and train a larger, full-sized model.
113, Neural Functional Transformers
Allan Zhou; Kaien Yang; Yiding Jiang; Kaylee Burns; Winnie Xu; Samuel Sokota; J. Zico Kolter; Chelsea Finn;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Nevertheless, constructing expressive and efficient neural functional architectures that can handle high-dimensional weight-space objects remains challenging. This paper uses the attention mechanism to define a novel set of permutation equivariant weight-space layers and composes them into deep equivariant models called neural functional Transformers (NFTs).
114, Permutation Equivariant Neural Functionals
Allan Zhou; Kaien Yang; Kaylee Burns; Adriano Cardace; Yiding Jiang; Samuel Sokota; J. Zico Kolter; Chelsea Finn;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We approach the design of neural functionals through the lens of symmetry, in particular by focusing on the permutation symmetries that arise in the weights of deep feedforward networks because hidden layer neurons have no inherent order. We introduce a framework for building *permutation equivariant* neural functionals, whose architectures encode these symmetries as an inductive bias.
115, Bridging Discrete and Backpropagation: Straight-Through and Beyond
Liyuan Liu; Chengyu Dong; Xiaodong Liu; Bin Yu; Jianfeng Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables.
116, Symbolic Discovery of Optimization Algorithms
Xiangning Chen; Chen Liang; Da Huang; Esteban Real; Kaiyuan Wang; Hieu Pham; Xuanyi Dong; Thang Luong; Cho-Jui Hsieh; Yifeng Lu; Quoc V Le;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training.
117, Is Your Code Generated By ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
Jiawei Liu; Chunqiu Steven Xia; Yuyao Wang; LINGMING ZHANG;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Such limitation in the existing benchmarks begs the following question: In the era of LLMs, is the code generated really correct? To answer this, we propose EvalPlus – a code synthesis benchmarking framework to rigorously evaluate the functional correctness of LLM-synthesized code.
118, Reward Imputation with Sketching for Contextual Batched Bandits
Xiao Zhang; Ninglu Shao; Zihua Si; Jun Xu; Wenhan Wang; Hanjing Su; Ji-Rong Wen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an efficient approach called Sketched Policy Updating with Imputed Rewards (SPUIR) that completes the unobserved rewards using sketching, which approximates the full-information feedbacks.
119, REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths
Xu Chen; Jingsen Zhang; Lei Wang; Quanyu Dai; Zhenhua Dong; Ruiming Tang; Rui Zhang; Li Chen; Xin Zhao; Ji-Rong Wen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the past few years, while a lot of promising explainable recommender models have been proposed, the datasets used to evaluate them still suffer from several limitations, for example, the explanation ground truths are not labeled by the real users, the explanations are mostly single-modal and around only one aspect. To bridge these gaps, in this paper, we build a new explainable recommendation dataset, which, to our knowledge, is the first contribution that provides a large amount of real user labeled multi-modal and multi-aspect explaination ground truths.
120, Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
Beichen Zhang; Kun Zhou; Xilin Wei; Xin Zhao; Jing Sha; Shijin Wang; Ji-Rong Wen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In CARP, we test four LLMs with CoT prompting, and find that they are all prone to make mistakes at the early steps of the solution, leading to incorrect answers. Based on this finding, we propose a new approach that can deliberate the reasoning steps with tool interfaces, namely \textbf{DELI}.
121, OpenAGI: When LLM Meets Domain Experts
Yingqiang Ge; Wenyue Hua; Kai Mei; jianchao ji; Juntao Tan; Shuyuan Xu; Zelong Li; Yongfeng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce \textbf{OpenAGI}, an open-source AGI research platform designed for multi-step, real-world tasks.
122, Scaling in Depth: Unlocking Robustness Certification on ImageNet
Kai Hu; Andy Zou; Zifan Wang; Klas Leino; Matt Fredrikson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper investigates strategies for expanding certifiably robust training to larger, deeper models.
123, Why Diffusion Models Memorize and How to Mitigate Copying
Gowthami Somepalli; Vasu Singla; Micah Goldblum; Jonas Geiping; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Images generated by diffusion models like Stable Diffusion are increasingly widespread. Recent works and even lawsuits have shown that these models are prone to replicating their training data, unbeknownst to the user. In this paper, we first analyze this memorization problem in text-to-image diffusion models.
124, Big Little Transformer Decoder
Sehoon Kim; Karttikeya Mangalam; Suhong Moon; Jitendra Malik; Michael Mahoney; Amir Gholami; Kurt Keutzer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The inference latency is further exacerbated by autoregressive generative tasks, as models need to run iteratively to generate tokens sequentially without leveraging token-level parallelization. To address this, we propose Big Little Decoder (BiLD), a framework that can improve inference efficiency and latency for a wide range of text generation applications.
125, Alexa Arena: A User-Centric Interactive Platform for Embodied AI
Qiaozi Gao; Govindarajan Thattai; Suhaila Shakiah; Xiaofeng Gao; Shreyas Pansare; Vasu Sharma; Gaurav Sukhatme; Hangjie Shi; Bofei Yang; Desheng Zhang; Lucy Hu; Karthika Arumugam; Shui Hu; Matthew Wen; Dinakar Guthy; Shunan Chung; Rohan Khanna; Osman Ipek; Leslie Ball; Kate Bland; Heather Rocker; Michael Johnston; Reza Ghanadan; Dilek Hakkani-Tur; Prem Natarajan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Alexa Arena, a user-centric simulation platform for Embodied AI (EAI) research.
126, Grounding Neural Inference with Satisfiability Modulo Theories
Matt Fredrikson; Kaiji Lu; Somesh Jha; Saranya Vijayakumar; Vijay Ganesh; Zifan Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we present a set of techniques for integrating Satisfiability Modulo Theories (SMT) solvers into the forward and backward passes of a deep network layer, called SMTLayer.
127, 3D-LLM: Injecting The 3D World Into Large Language Models
Yining Hong; Haoyu Zhen; Peihao Chen; Shuhong Zheng; Yilun Du; Zhenfang Chen; Chuang Gan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose to inject the 3D world into large language models, and introduce a whole new family of 3D-LLMs.
128, $k$-Means Clustering with Distance-Based Privacy
Alessandro Epasto; Vahab Mirrokni; Shyam Narayanan; Peilin Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we initiate the study of Euclidean clustering with Distance-based privacy.
129, Multi-scale Diffusion Denoised Smoothing
Jongheon Jeong; Jinwoo Shin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we investigate the trade-off between accuracy and certified robustness of denoised smoothing: for example, we question on which representation of diffusion model would maximize the certified robustness of denoised smoothing.
130, Backprop-Free Dataset Distillation
Songhua Liu; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, different from the time-consuming forward-backward passes, we introduce a backprop-free fashion for dataset distillation with significantly improved efficiency.
131, VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models
Yonatan Bitton; Hritik Bansal; Jack Hessel; Rulin Shao; Wanrong Zhu; Anas Awadalla; Josh Gardner; Rohan Taori; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce VisIT-Bench, a robust benchmark for diverse real-life vision-language instructions across 70 tasks, from recognition to reasoning.
132, Dissecting Chain-of-Thought: A Study on Compositional In-Context Learning of MLPs
Yingcong Li; Kartik Sreenivasan; Angeliki Giannou; Dimitris Papailiopoulos; Samet Oymak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Chain-of-thought (CoT) is a method that enables language models to handle complex reasoning tasks by decomposing them into simpler steps. Despite its success, the underlying mechanics of CoT are not yet fully understood. In an attempt to shed light on this, our study investigates the impact of CoT on the ability of transformers to in-context learn a simple to study, yet general family of compositional functions: multi-layer perceptrons (MLPs).
133, Jailbroken: How Does LLM Safety Training Fail?
Alexander Wei; Nika Haghtalab; Jacob Steinhardt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Large language models trained for safety and harmlessness remain susceptible to adversarial misuse, as evidenced by the prevalence of �jailbreak� attacks on early releases of ChatGPT that elicit undesired behavior. Going beyond recognition of the issue, we investigate why such attacks succeed and how they can be created.
134, Fair Graph Distillation
Qizhang Feng; Zhimeng Jiang; Ruiquan Li; Yicheng Wang; Na Zou; Jiang Bian; Xia Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on the proposed coherence metric, we introduce a framework for fair graph distillation using a bi-level optimization algorithm.
135, Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
Neel Guha; Mayee Chen; Kush Bhatia; Azalia Mirhoseini; Frederic Sala; Christopher Ré;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Embroid, a method which computes multiple representations of a dataset under different embedding functions, and uses the consistency between the LM predictions for neighboring samples to identify mispredictions.
136, On Evaluating Adversarial Robustness of Large Vision-Language Models
Yunqing Zhao; Tianyu Pang; Chao Du; Xiao Yang; Chongxuan LI; Ngai-Man (Man) Cheung; Min Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we propose evaluating the robustness of open-source large VLMs in the most realistic and high-risk setting, where adversaries have only black-box system access and seek to deceive the model into returning the targeted responses.
137, The Learnability of In-Context Learning
Noam Wies; Yoav Levine; Amnon Shashua;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a first-of-its-kind PAC based framework for in-context learnability, and use it to provide the first finite sample complexity results for the in-context learning setup.
138, NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations
Varun Jampani; Kevis-kokitsi Maninis; Andreas Engelhardt; Arjun Karpur; Karen Truong; Kyle Sargent; Stefan Popov; Andre Araujo; Ricardo Martin Brualla; Kaushal Patel; Daniel Vlasic; Vittorio Ferrari; Ameesh Makadia; Ce Liu; Yuanzhen Li; Howard Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To enable systematic research progress on 3D reconstruction from casual image captures, we propose `NAVI': a new dataset of category-agnostic image collections of objects with high-quality 3D scans along with per-image 2D-3D alignments providing near-perfect GT camera parameters.
139, Text Alignment Is An Efficient Unified Model for Massive NLP Tasks
Yuheng Zha; Yichi Yang; Ruichen Li; Zhiting Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose text alignment as an efficient unified model for a wide range of crucial tasks involving text entailment, similarity, question answering (and answerability), factual consistency, and so forth.
140, Meta-in-context Learning in Large Language Models
Julian Coda-Forno; Marcel Binz; Zeynep Akata; Matt Botvinick; Jane Wang; Eric Schulz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the present paper, we demonstrate that the in-context learning abilities of large language models can be recursively improved via in-context learning itself.
141, Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs
Deepak Narayanan; Keshav Santhanam; Peter Henderson; Rishi Bommasani; Tony Lee; Percy Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, access to LLMs today is largely restricted to black-box text generation APIs; raw runtimes measured through this interface do not satisfy these desiderata: model providers can implement software and hardware optimizations orthogonal to the model, and shared infrastructure introduces performance contention. We propose a new metric for inference efficiency that puts models on equal footing as though they were served on uniform hardware and software and without performance contention.
142, Lexinvariant Language Models
Qian Huang; Eric Zelikman; Sarah Chen; Yuhuai Wu; Gregory Valiant; Percy Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: First, we prove that we can construct a lexinvariant LM to converge to the true language model at a uniform rate that is polynomial in terms of the context length, with a constant factor that is sublinear in the vocabulary size. Second, to build a lexinvariant LM, we simply encode tokens using random Gaussian vectors, such that each token maps to the same representation within each sequence but different representations across sequences.
143, Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes
Connor Toups; Rishi Bommasani; Kathleen Creel; Sarah Bana; Dan Jurafsky; Percy Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In practice, the societal impact of machine learning is determined by the surrounding context of machine learning deployments. To capture this, we introduce *ecosystem-level analysis*: rather than analyzing a single model, we consider the collection of models that are deployed in a given context.
144, Holistic Evaluation of Text-to-Image Models
Tony Lee; Michihiro Yasunaga; Chenlin Meng; Yifan Mai; Joon Sung Park; Agrim Gupta; Yunzhi Zhang; Deepak Narayanan; Hannah Teufel; Marco Bellagente; Minguk Kang; Taesung Park; Jure Leskovec; Jun-Yan Zhu; Fei-Fei Li; Jiajun Wu; Stefano Ermon; Percy Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing evaluations primarily focus on image-text alignment and quality. To address this limitation, we introduce a new benchmark, Holistic Evaluation of Text-to-Image Models (HEIM).
145, INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms
Shih-Cheng Huang; Zepeng Huo; Ethan Steinberg; Chia-Chun Chiang; Curtis Langlotz; Matthew Lungren; Serena Yeung; Nigam Shah; Jason Fries;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of pulmonary embolism (PE) patients, along with ground truth labels for multiple outcomes.
146, Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping
Chunming He; Kai Li; Yachao Zhang; Guoxia Xu; Longxiang Tang; Yulun Zhang; Zhenhua Guo; Xiu Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: It remains a challenging task since (1) it is hard to distinguish concealed objects from the background due to the intrinsic similarity and (2) the sparsely-annotated training data only provide weak supervision for model learning. In this paper, we propose a new WSCOS method to address these two challenges.
147, Data Portraits: Recording Foundation Model Training Data
Marc Marone; Benjamin Van Durme;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Even while these models are now key in AI system building, it can be difficult to answer the straightforward question: has the model already encountered a given example during training? We therefore propose a widespread adoption of Data Portraits: artifacts that record training data and allow for downstream inspection.
148, MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning
Zeyuan Ma; Hongshu Guo; Jiacheng Chen; Zhenrui Li; Guojun Peng; Yue-Jiao Gong; Yining Ma; Zhiguang Cao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, this field is hindered by the lack of a unified benchmark. To fill this gap, we introduce MetaBox, the first benchmark platform expressly tailored for developing and evaluating MetaBBO-RL methods.
149, Mirror Diffusion Models for Constrained and Watermarked Generation
Guan-Horng Liu; Tianrong Chen; Evangelos Theodorou; Molei Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Mirror Diffusion Models (MDM), a new class of diffusion models that generate data on convex constrained sets without losing any tractability.
150, Towards Label-free Scene Understanding By Vision Foundation Models
Runnan Chen; Youquan Liu; Lingdong Kong; Nenglun Chen; Xinge ZHU; Yuexin Ma; Tongliang Liu; Wenping Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we investigate the potential of vision foundation models in enabling networks to comprehend 2D and 3D worlds without labelled data.
151, Annotating 8,000 Abdominal CT Volumes for Multi-Organ Segmentation in Three Weeks
Chongyu Qu; Tiezheng Zhang; Hualin Qiao; jie liu; Yucheng Tang; Alan Yuille; Zongwei Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a systematic and efficient method to expedite the annotation process for organ segmentation.
152, Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
Ibrahim Alabdulmohsin; Lucas Beyer; Alexander Kolesnikov; Xiaohua Zhai;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration. We advance and refine such methods to infer compute-optimal model shapes, such as width and depth, and successfully implement this in vision transformers.
153, The Impact of Positional Encoding on Length Generalization in Transformers
Amirhossein Kazemnejad; Inkit Padhi; Karthikeyan Natesan Ramamurthy; Payel Das; Siva Reddy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we conduct a systematic empirical study comparing the length generalization performance of decoder-only Transformers with five different position encoding approaches including Absolute Position Embedding (APE), T5's Relative PE, ALiBi, and Rotary, in addition to Transformers without positional encoding (NoPE).
154, Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
Zebin You; Yong Zhong; Fan Bao; Jiacheng Sun; Chongxuan LI; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In an effort to further advance semi-supervised generative and classification tasks, we propose a simple yet effective training strategy called *dual pseudo training* (DPT), built upon strong semi-supervised learners and diffusion models.
155, VPP: Efficient Universal 3D Generation Via Voxel-Point Progressive Representation
Zekun Qi; Muzhou Yu; Runpei Dong; Kaisheng Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by the characteristics of different representations, we propose VPP, a voxel-point progressive representation for both efficient and universal 3D generation.
156, Large Language Models Implicitly Learn to Straighten Neural Sentence Trajectories to Construct A Predictive Representation of Natural Language
Eghbal Hosseini; Evelina Fedorenko;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We quantify straightness using a1-dimensional curvature metric, and provide support for the trajectory straighteninghypothesis across four results: i) In trained models, the curvature progressivelydecreases from the first to the middle layers of the network.
157, (Un)interpretability of Transformers: A Case Study with Dyck Grammars
Kaiyue Wen; Yuchen Li; Bingbin Liu; Andrej Risteski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, through a combination of theoretical results and carefully controlled experiments on synthetic data, we take a critical viewof methods that exclusively focus on individual parts of the model, rather than consider the network as a whole.
158, Learning in The Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
Jimmy Ba; Murat Erdogdu; Taiji Suzuki; Zhichao Wang; Denny Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Abstract: We consider the learning of a single-index target function $f_*: \mathbb{R}^d\to\mathbb{R}$ under spiked covariance data: $f_*(\boldsymbol{x}) = ...
159, Meet in The Middle: A New Pre-training Paradigm
Anh Nguyen; Nikos Karampatziakis; Weizhu Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce ``Meet in the Middle'' (MIM) a new pre-training paradigm that improves data efficiency by training in two directions, left-to-right and right-to-left, and encouraging the respective modelsto agree on their token distribution for each position.
160, Swap Agnostic Learning, or Characterizing Omniprediction Via Multicalibration
Parikshit Gopalan; Michael Kim; Omer Reingold;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce and study the notion of Swap Agnostic Learning.
161, DataComp: In Search of The Next Generation of Multimodal Datasets
Samir Yitzhak Gadre; Gabriel Ilharco; Alex Fang; Jonathan Hayase; Georgios Smyrnis; Thao Nguyen; Ryan Marten; Mitchell Wortsman; Dhruba Ghosh; Jieyu Zhang; Eyal Orgad; Rahim Entezari; Giannis Daras; Sarah Pratt; Vivek Ramanujan; Yonatan Bitton; Kalyani Marathe; Stephen Mussmann; Richard Vencu; Mehdi Cherti; Ranjay Krishna; Pang Wei Koh; Olga Saukh; Alexander Ratner; Shuran Song; Hannaneh Hajishirzi; Ali Farhadi; Romain Beaumont; Sewoong Oh; Alex Dimakis; Jenia Jitsev; Yair Carmon; Vaishaal Shankar; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Multimodal datasets are a critical component in recent breakthroughs such as CLIP, Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model architectures or training algorithms. To address this shortcoming in the machine learning ecosystem, we introduce DataComp, a testbed for dataset experiments centered around a new candidate pool of 12.8 billion image-text pairs from Common Crawl.
162, Benchmarking Distribution Shift in Tabular Data with TableShift
Josh Gardner; Zoran Popovic; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a consequence, the robustness of tabular models to distribution shift is poorly understood. To address this issue, we introduce TableShift, a distribution shift benchmark for tabular data.
163, GenEval: An Object-focused Framework for Evaluating Text-to-image Alignment
Dhruba Ghosh; Hannaneh Hajishirzi; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce GenEval, an object-focused framework to evaluate compositional image properties such as object co-occurrence, position, count, and color.
164, AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
Tong Wu; Zhihao Fan; Xiao Liu; Yeyun Gong; yelong shen; Jian Jiao; Hai-Tao Zheng; Juntao Li; zhongyu wei; Jian Guo; Nan Duan; Weizhu Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To account for the inherent sequential characteristic of natural language, we introduce Auto-Regressive Diffusion (AR-Diffusion).
165, On The Connection Between Pre-training Data Diversity and Fine-tuning Robustness
Vivek Ramanujan; Thao Nguyen; Sewoong Oh; Ali Farhadi; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Pre-training has been widely adopted in deep learning to improve model performance, especially when the training data for a target task is limited. In our work, we seek to understand the implications of this training strategy on the generalization properties of downstream models.
166, Improving Multimodal Datasets with Image Captioning
Thao Nguyen; Samir Yitzhak Gadre; Gabriel Ilharco; Sewoong Oh; Ludwig Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our work focuses on caption quality as one major source of noise, and studies the effectiveness of generated captions in increasing the utility of web-scraped datapoints with nondescript text.
167, Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective
Chenyu You; Weicheng Dai; Yifei Min; Fenglin Liu; David Clifton; S. Kevin Zhou; Lawrence Staib; James Duncan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose $\texttt{ARCO}$, a semi-supervised contrastive learning (CL) framework with stratified group theory for medical image segmentation.
168, Focused Transformer: Contrastive Training for Context Scaling
Szymon Tworkowski; Konrad Staniszewski; Mikołaj Pacek; Yuhuai Wu; Henryk Michalewski; Piotr Miłoś;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We pinpoint a key challenge, referred to as the distraction issue, where keys associated with distinct semantic values may overlap, making them challenging to differentiate. To address this issue, we propose the Focused Transformer (FoT), a method that utilizes a training process inspired by contrastive learning.
169, EmbodiedGPT: Vision-Language Pre-Training Via Embodied Chain of Thought
Yao Mu; Qinglong Zhang; Mengkang Hu; Wenhai Wang; Mingyu Ding; Jun Jin; Bin Wang; Jifeng Dai; Yu Qiao; Ping Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce EmbodiedGPT, an end-to-end multi-modal foundation model for embodied AI, empowering embodied agents with multi-modal understanding and execution capabilities.
170, Any-to-Any Generation Via Composable Diffusion
Zineng Tang; Ziyi Yang; Chenguang Zhu; Michael Zeng; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present Composable Diffusion (CoDi), a novel generative model capable of generating any combination of output modalities, such as language, image, video, or audio, from any combination of input modalities.
171, Generator Born from Classifier
Runpeng Yu; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we make a bold attempt toward an ambitious task: given a pre-trained classifier, we aim to reconstruct an image generator, without relying on any data samples.
172, How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception
Dingkang Yang; Kun Yang; Yuzheng Wang; Jing Liu; Zhi Xu; Peng Zhai; Lihua Zhang; Rongbin Yin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the advancements in previous efforts, challenges remain due to various noises in the perception procedure, including communication redundancy, transmission delay, and collaboration heterogeneity. To tackle these issues, we propose How2comm, a collaborative perception framework that seeks a trade-off between perception performance and communication bandwidth.
173, Improving CLIP Training with Language Rewrites
Lijie Fan; Dilip Krishnan; Phillip Isola; Dina Katabi; Yonglong Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce Language augmented CLIP (LaCLIP), a simple yet highly effective approach to enhance CLIP training through language rewrites.
174, From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader
Weiwen Xu; Xin Li; Wenxuan Zhang; Meng Zhou; Wai Lam; Luo Si; Lidong Bing;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data.
175, PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation
Zhaoxi Chen; Fangzhou Hong; Haiyi Mei; Guangcong Wang; Lei Yang; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present PrimDiffusion, the first diffusion-based framework for 3D human generation.
176, FELM: Benchmarking Factuality Evaluation of Large Language Models
shiqi chen; Yiran Zhao; Jinghan Zhang; I-Chun Chern; Siyang Gao; Pengfei Liu; Junxian He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This direction remains under-explored, resulting in substantial impediments to the progress of factuality evaluators. To mitigate this issue, we introduce a benchmark for Factuality Evaluation of large Language Models, referred to as FELM.
177, Training-Free Composition of Parameter-Efficient Modules with Arithmetic Operation
Jinghan Zhang; shiqi chen; Junteng Liu; Junxian He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In PEFT, a lightweight module is learned on each dataset while the underlying pretrained language model remains unchanged, resulting in multiple compact modules representing diverse skills when applied to various domains and tasks. In this paper, we propose to compose these parameter-efficient modules through linear arithmetic operations in the weight space, thereby integrating different module capabilities.
178, DeWave: Discrete Encoding of EEG Waves for EEG to Text Translation
Yiqun Duan; Charles Chau; Zhen Wang; Yu-Kai Wang; Chin-teng Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These event markers may not be readily available or could be challenging to acquire during real-time inference, and the sequence of eye fixations may not align with the order of spoken words. To tackle these issues, we introduce a novel framework, DeWave, that integrates discrete encoding sequences into open-vocabulary EEG-to-text translation tasks.
179, Textually Pretrained Speech Language Models
Michael Hassid; Tal Remez; Tu Anh Nguyen; Itai Gat; Alexis CONNEAU; Felix Kreuk; Jade Copet; Alexandre Defossez; Gabriel Synnaeve; Emmanuel Dupoux; Roy Schwartz; Yossi Adi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose TWIST, a method for training SpeechLMs using a warm-start from a pretrained textual language models.
180, EvoPrompting: Language Models for Code-Level Neural Architecture Search
Angelica Chen; David Dohan; David So;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Given the recent impressive accomplishments of language models (LMs) for code generation, we explore the use of LMs as general adaptive mutation and crossover operators for an evolutionary neural architecture search (NAS) algorithm.
181, Mitigating Test-Time Bias for Fair Image Retrieval
Fanjie Kong; Shuai Yuan; Weituo Hao; Ricardo Henao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: So motivated, we introduce a straightforward technique, Post-hoc Bias Mitigation (PBM), that post-processes the outputs from the pre-trained vision-language model.
182, Red Teaming Deep Neural Networks with Feature Synthesis Tools
Stephen Casper; Tong Bu; Yuxiao Li; Jiawei Li; Kevin Zhang; Kaivalya Hariharan; Dylan Hadfield-Menell;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our key insight is that we can train models that respond to specific triggers (e.g., a specific patch inserted into an image) with specific outputs (i.e. a label) and then evaluate interpretability tools based on whether they help humans identify these triggers.
183, UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models
Wenliang Zhao; Lujia Bai; Yongming Rao; Jie Zhou; Jiwen Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we develop a unified corrector (UniC) that can be applied after any existing DPM sampler to increase the order of accuracy without extra model evaluations, and derive a unified predictor (UniP) that supports arbitrary order as a byproduct.
184, (S)GD Over Diagonal Linear Networks: Implicit Bias, Large Stepsizes and Edge of Stability
Mathieu Even; Scott Pesme; Suriya Gunasekar; Nicolas Flammarion;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over $2$-layer diagonal linear networks.
185, RAPHAEL: Text-to-Image Generation Via Large Mixture of Diffusion Paths
Zeyue Xue; Guanglu Song; Qiushan Guo; Boxiao Liu; Zhuofan Zong; Yu Liu; Ping Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs.
186, Controlling Text-to-Image Diffusion By Orthogonal Finetuning
Zeju Qiu; Weiyang Liu; Haiwen Feng; Yuxuan Xue; Yao Feng; Zhen Liu; Dan Zhang; Adrian Weller; Bernhard Schölkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: How to effectively guide or control these powerful models to perform different downstream tasks becomes an important open problem. To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.
187, ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
Chun-Han Yao; Amit Raj; Wei-Chih Hung; Michael Rubinstein; Yuanzhen Li; Ming-Hsuan Yang; Varun Jampani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose ARTIC3D, a self-supervised framework to reconstruct per-instance 3D shapes from a sparse image collection in-the-wild.
188, Continuous-Time Functional Diffusion Processes
Giulio Franzese; Giulio Corallo; Simone Rossi; Markus Heinonen; Maurizio Filippone; Pietro Michiardi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces.
189, Window-Based Distribution Shift Detection for Deep Neural Networks
Guy Bar Shalom; Yonatan Geifman; Ran El-Yaniv;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we study the case of monitoring the healthy operation of a deep neural network (DNN) receiving a stream of data, with the aim of detecting input distributional deviations over which the quality of the network's predictions is potentially damaged.
190, SEGA: Instructing Text-to-Image Models Using Semantic Guidance
Manuel Brack; Felix Friedrich; Dominik Hintersdorf; Lukas Struppek; Patrick Schramowski; Kristian Kersting;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions.
191, Recommender Systems with Generative Retrieval
Shashank Rajput; Nikhil Mehta; Anima Singh; Raghunandan Hulikal Keshavan; Trung Vu; Lukasz Heldt; Lichan Hong; Yi Tay; Vinh Tran; Jonah Samost; Maciej Kula; Ed Chi; Mahesh Sathiamoorthy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates directly.
192, Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training By Diminishing Bias
Zhongwei Wan; Che Liu; Mi Zhang; Jie Fu; Benyou Wang; Sibo Cheng; Lei Ma; César Quilodrán-Casas; Rossella Arcucci;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents a novel framework named Unifying Cross-Lingual Medical Vision-Language Pre-Training (\textbf{Med-UniC}), designed to integrate multi-modal medical data from the two most prevalent languages, English and Spanish.
193, VidChapters-7M: Video Chapters at Scale
Antoine Yang; Arsha Nagrani; Ivan Laptev; Josef Sivic; Cordelia Schmid;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This important topic has been understudied due to the lack of publicly released datasets. To address this issue, we present VidChapters-7M, a dataset of 817K user-chaptered videos including 7M chapters in total.
194, Provable Convergence Guarantees for Black-box Variational Inference
Justin Domke; Robert Gower; Guillaume Garrigos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While black-box variational inference is widely used, there is no proof that its stochastic optimization succeeds. We suggest this is due to a theoretical gap in existing stochastic optimization proofs—namely the challenge of gradient estimators with unusual noise bounds,and a composite non-smooth objective.
195, PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance
Qianqian Xie; Weiguang Han; Xiao Zhang; Yanzhao Lai; Min Peng; Alejandro Lopez-Lira; Jimin Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 128K data samples to support the fine-tuning, and an evaluation benchmark with 8 tasks and 15 datasets.
196, Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents
Zihao Wang; Shaofei Cai; Guanzhou Chen; Anji Liu; Xiaojian (Shawn) Ma; Yitao Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the problem of planning in Minecraft, a popular, democratized yet challenging open-ended environment for developing multi-task embodied agents.
197, Learning Generalizable Agents Via Saliency-guided Features Decorrelation
Sili Huang; Yanchao Sun; Jifeng Hu; Siyuan Guo; Bo Yang; Hechang Chen; Yi Chang; Lichao Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose Saliency-Guided Features Decorrelation (SGFD) to eliminate these correlations through sample reweighting.
198, Decision Stacks: Flexible Reinforcement Learning Via Modular Generative Models
Siyan Zhao; Aditya Grover;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Decision Stacks, a generative framework that decomposes goal-conditioned policy agents into 3 generative modules.
199, Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach
Zhimeng Jiang; Xiaotian Han; Hongye Jin; Guanchu Wang; Rui Chen; Na Zou; Xia Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Subsequently, we analyze the sufficient conditions to guarantee fairness (i.e., low demographic parity) for the target dataset, including fairness for the source dataset, and low prediction difference between the source and target dataset for each sensitive attribute group. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group.
200, Are Diffusion Models Vision-And-Language Reasoners?
Benno Krojer; Elinor Poole-Dayan; Vikram Voleti; Chris Pal; Siva Reddy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis.
201, Fast Optimal Locally Private Mean Estimation Via Random Projections
Hilal Asi; Vitaly Feldman; Jelani Nelson; Huy Nguyen; Kunal Talwar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a new algorithmic framework, namely ProjUnit, for private mean estimation that yields algorithms that are computationally efficient, have low communication complexity, and incur optimal error up to a $1+o(1)$-factor.
202, A Metadata-Driven Approach to Understand Graph Neural Networks
Ting Wei Li; Qiaozhu Mei; Jiaqi Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a \emph{metadata-driven} approach to analyze the sensitivity of GNNs to graph data properties, motivated by the increasing availability of graph learning benchmarks.
203, An Information Theory Perspective on Variance-Invariance-Covariance Regularization
Ravid Shwartz-Ziv; Randall Balestriero; Kenji Kawaguchi; Tim G. J. Rudner; Yann LeCun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present an information-theoretic perspective on the VICReg objective.
204, A Generative Model of The Hippocampal Formation Trained with Theta Driven Local Learning Rules
Tom M George; Kimberly Stachenfeld; Caswell Barry; Claudia Clopath; Tomoki Fukai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we introduce a biologically plausible model of the hippocampal formation tantamount to a Helmholtz machine that we apply to a temporal stream of inputs.
205, Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion
Shengqiong Wu; Hao Fei; Hanwang Zhang; Tat-Seng Chua;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate the task of text-to-image (T2I) synthesis under the abstract-to-intricate setting, i.e., generating intricate visual content from simple abstract text prompts.
206, DiffComplete: Diffusion-based Generative 3D Shape Completion
Ruihang Chu; Enze Xie; Shentong Mo; Zhenguo Li; Matthias Niessner; Chi-Wing Fu; Jiaya Jia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new diffusion-based approach for shape completion on 3D range scans.
207, Real-World Image Variation By Aligning Diffusion Inversion Chain
Yuechen Zhang; Jinbo Xing; Eric Lo; Jiaya Jia;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our investigation uncovers that this domain gap originates from a latents' distribution gap in different diffusion processes. To address this issue, we propose a novel inference pipeline called Real-world Image Variation by ALignment (RIVAL) that utilizes diffusion models to generate image variations from a single image exemplar.
208, Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
Alvin Heng; Harold Soh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by continual learning to selectively forget concepts in pretrained deep generative models.
209, Object-Centric Slot Diffusion
Jindong Jiang; Fei Deng; Gautam Singh; Sungjin Ahn;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore the feasibility and potential of integrating diffusion models into object-centric learning and investigate the pros and cons of this approach.
210, Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints
Jiaxin Bai; Xin Liu; Weiqi Wang; Chen Luo; Yangqiu Song;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Thus, in this paper, we propose a new framework to leverage neural methods to answer complex logical queries based on an EVKG, which can satisfy not only traditional first-order logic constraints but also implicit logical constraints over eventualities concerning their occurrences and orders.
211, 4D Panoptic Scene Graph Generation
Jingkang Yang; Jun CEN; WENXUAN PENG; Shuai Liu; Fangzhou Hong; Xiangtai Li; Kaiyang Zhou; Qifeng Chen; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To solve PSG-4D, we propose PSG4DFormer, a Transformer-based model that can predict panoptic segmentation masks, track masks along the time axis, and generate the corresponding scene graphs via a relation component.
212, How Far Can Camels Go? Exploring The State of Instruction Tuning on Open Resources
Yizhong Wang; Hamish Ivison; Pradeep Dasigi; Jack Hessel; Tushar Khot; Khyathi Chandu; David Wadden; Kelsey MacMillan; Noah Smith; Iz Beltagy; Hannaneh Hajishirzi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets.
213, Learning Mask-aware CLIP Representations for Zero-Shot Segmentation
Siyu Jiao; Yunchao Wei; Yaowei Wang; Yao Zhao; Humphrey Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This issue mainly relates to the fact that CLIP is trained with image-level supervision. To alleviate this issue, we propose a simple yet effective method, named Mask-aware Fine-tuning (MAFT).
214, Quantizable Transformers: Removing Outliers By Helping Attention Heads Do Nothing
Yelysei Bondarenko; Markus Nagel; Tijmen Blankevoort;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To achieve the exact zeros needed in the attention matrix for a no-update, the input to the softmax is pushed to be larger and larger during training, causing outliers in other parts of the network. Based on these observations, we propose two simple (independent) modifications to the attention mechanism - _clipped softmax_ and _gated attention_.
215, Sharpness-Aware Minimization Leads to Low-Rank Features
Maksym Andriushchenko; Dara Bahri; Hossein Mobahi; Nicolas Flammarion;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While its generalization improvement is well-known and is the primary motivation, we uncover an additional intriguing effect of SAM: reduction of the feature rank which happens at different layers of a neural network. We show that this low-rank effect occurs very broadly: for different architectures such as fully-connected networks, convolutional networks, vision transformers and for different objectives such as regression, classification, language-image contrastive training.
216, Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
Shaolei Zhang; Yang Feng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a unified segment-tosegment framework (Seg2Seg) for simultaneous sequence generation, which learns the mapping in an adaptive and unified manner.
217, A Hierarchical Spatial Transformer for Large Numbers of Point Samples in Continuous Space
Wenchong He; Zhe Jiang; Tingsong Xiao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: There are also works related to operator learning on numerical simulations in the continous space, but these methods often do not address the hierarchical spatial representation on irregular points. To fill this gap, this paper proposes a new hierarchical spatial transformer model for a large number of irregular point samples in continuous space.
218, What Indeed Can GPT Models Do in Chemistry? A Comprehensive Benchmark on Eight Tasks
Taicheng Guo; kehan Guo; Bozhao Nan; Zhenwen Liang; Zhichun Guo; Nitesh Chawla; Olaf Wiest; Xiangliang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, rather than pursuing state-of-the-art performance, we aim to evaluate capabilities of LLMs in a wide range of tasks across the chemistry domain.
219, WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding
Yanchao Tan; Zihao Zhou; Hang Lv; Weiming Liu; Carl Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we take a fundamentally different approach than GNNs, to simultaneously achieve deep joint modeling of complex attributes and flexible structures of real-world graphs and obtain unsupervised generic graph representations that are not limited to specific downstream predictions.
220, Emergent Correspondence from Image Diffusion
Luming Tang; Menglin Jia; Qianqian Wang; Cheng Perng Phoo; Bharath Hariharan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we find that correspondence emerges in diffusion models without any explicit supervision.
221, MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
Marco Bellagente; Hannah Teufel; Manuel Brack; Björn Deiseroth; Felix Friedrich; Constantin Eichenberg; Andrew Dai; Robert Baldock; Souradeep Nanda; Koen Oostermeijer; Andres Felipe Cruz-Salinas; Patrick Schramowski; Kristian Kersting; Samuel Weinbach;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To ease image generation, we propose MultiFusion that allows one to express complex and nuanced concepts with arbitrarily interleaved inputs of multiple modalities and languages.
222, Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
Shuhuai Ren; Aston Zhang; Yi Zhu; Shuai Zhang; Shuai Zheng; Mu Li; Alexander Smola; Xu Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work proposes POMP, a prompt pre-training method for vision-language models.
223, Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
Shengpu Tang; Jenna Wiens;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a semi-offline evaluation framework as an intermediate step between offline and online evaluation, where human users provide annotations of unobserved counterfactual trajectories.
224, PyNeRF: Pyramidal Neural Radiance Fields
Haithem Turki; Michael Zollhöfer; Christian Richardt; Deva Ramanan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a simple modification to grid-based models by training model heads at different spatial grid resolutions.
225, Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation
Yuyang Deng; Ilja Kuzborskij; Mehrdad Mahdavi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a problem of learning a model from multiple sources with the goal to performwell on a new target distribution.
226, H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
Zhenyu Zhang; Ying Sheng; Tianyi Zhou; Tianlong Chen; Lianmin Zheng; Ruisi Cai; Zhao Song; Yuandong Tian; Christopher Ré; Clark Barrett; Zhangyang Atlas Wang; Beidi Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Often, a large amount of transient state information, referred to as the $\mathsf{KV}$ $\mathsf{cache}$, is stored in GPU memory in addition to model parameters, scaling linearly with the sequence length and batch size. In this paper, we introduce a novel approach for implementing the $\mathsf{KV}$ $\mathsf{cache}$ which significantly reduces its memory footprint.
227, Distributed Personalized Empirical Risk Minimization
Yuyang Deng; Mohammad Mahdi Kamani; Pouria Mahdavinia; Mehrdad Mahdavi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To learn personalized models at scale, we propose a distributed algorithm that replaces the standard model averaging with model shuffling to simultaneously optimize PERM objectives for all devices.
228, RoboDepth: Robust Out-of-Distribution Depth Estimation Under Corruptions
Lingdong Kong; Shaoyuan Xie; Hanjiang Hu; Lai Xing Ng; Benoit Cottereau; Wei Tsang Ooi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Common corruptions, however, tend to occur in practical scenarios, especially for safety-critical applications like autonomous driving. To fill in this gap, we present a comprehensive robustness test suite dubbed RoboDepth consisting of 18 corruptions from three categories: i) weather and lighting conditions; ii) sensor failure and movement; and iii) data processing issues.
229, Real-World 3D Object Inverse Rendering Benchmark
Zhengfei Kuang; Yunzhi Zhang; Hong-Xing Yu; Samir Agarwala; Shangzhe Wu; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new real-world 3D Object inverse Rendering Benchmark, dubbed 3D-ORB.
230, What You See Is What You Read? Improving Text-Image Alignment Evaluation
Michal Yarom; Yonatan Bitton; Soravit Changpinyo; Roee Aharoni; Jonathan Herzig; Oran Lang; Eran Ofek; Idan Szpektor;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we study methods for automatic text-image alignment evaluation.
231, High-Fidelity Audio Compression with Improved RVQGAN
Rithesh Kumar; Prem Seetharaman; Alejandro Luebs; Ishaan Kumar; Kundan Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To that end, we introduce a high-fidelity universal neural audio compression algorithm that achieves ~90x compression of 44.1 KHz audio into tokens at just 8kbps bandwidth.
232, AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset
Jiakang Yuan; Bo Zhang; Xiangchao Yan; Botian Shi; Tao Chen; Yikang LI; Yu Qiao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Previous works mainly focus on the self-supervised pre-training pipeline, meaning that they perform the pre-training and fine-tuning on the same benchmark, which is difficult to attain the performance scalability and cross-dataset application for the pre-training checkpoint. In this paper, for the first time, we are committed to building a large-scale pre-training point-cloud dataset with diverse data distribution, and meanwhile learning generalizable representations from such a diverse pre-training dataset.
233, Benchmarking Large Language Models on CMExam - A Comprehensive Chinese Medical Exam Dataset
Junling Liu; Peilin Zhou; Yining Hua; Dading Chong; Zhongyu Tian; Andrew Liu; Helin Wang; Chenyu You; Zhenhua Guo; LEI ZHU; Michael Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address this gap, we introduce CMExam, sourced from the Chinese National Medical Licensing Examination.
234, LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
Bo Liu; Yifeng Zhu; Chongkai Gao; Yihao Feng; Qiang Liu; Yuke Zhu; Peter Stone;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To advance research in LLDM, we introduce LIBERO, a novel benchmark of lifelong learning for robot manipulation.
235, ELDEN: Exploration Via Local Dependencies
Zizhao Wang; Jiaheng Hu; Roberto Martín-Martín; Peter Stone;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a new way of defining interesting states for environments with factored state spaces and complex chained dependencies, where an agent's actions may change the state of one factor that, in order, may affect the state of another factor.
236, Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations
Lifan Yuan; Yangyi Chen; Ganqu Cui; Hongcheng Gao; FangYuan Zou; Xingyi Cheng; Heng Ji; Zhiyuan Liu; Maosong Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We identify that the distribution shift settings in previous studies commonly lack adequate challenges, hindering the accurate evaluation of OOD robustness. To address these issues, we propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts.
237, Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
Zirui Liu; Guanchu Wang; Shaochen (Henry) Zhong; Zhaozhuo Xu; Daochen Zha; Ruixiang Tang; Zhimeng Jiang; Kaixiong Zhou; Vipin Chaudhary; Shuai Xu; Xia Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We argue that in stochastic optimization, models can handle noisy gradients as long as the gradient estimator is unbiased with reasonable variance. Following this motivation, we propose a new family of unbiased estimators called \sas, for matrix production with reduced variance, which only requires storing the sub-sampled activations for calculating the gradient.
238, TART: A Plug-and-play Transformer Module for Task-agnostic Reasoning
Kush Bhatia; Avanika Narayan; Christopher De Sa; Christopher Ré;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This raises an intriguing question: Are LLMs actually capable of learning how to reason in a task-agnostic manner? We answer this in the affirmative and, as a proof of concept, propose TART which generically improves an LLM's reasoning abilities using a synthetically trained reasoning module.
239, Skill-it! A Data-driven Skills Framework for Understanding and Training Language Models
Mayee Chen; Nicholas Roberts; Kush Bhatia; Jue WANG; Ce Zhang; Frederic Sala; Christopher Ré;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Using our proposed framework, we introduce an online data sampling algorithm, Skill-It, over mixtures of skills for learning skills more quickly for both continual pre-training and fine-tuning regimes, where we aim to learn multiple skills in the former and an individual skill in the latter.
240, A Case for Reframing Automated Medical Image Classification As Segmentation
Sarah Hooper; Mayee Chen; Khaled Saab; Kush Bhatia; Curtis Langlotz; Christopher Ré;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, recent work has drastically reduced the cost of training segmentation networks. In light of this recent work, we reexamine the choice of training classification vs. segmentation models.
241, Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
Dan Fu; Jessica Grogan; Isys Johnson; Simran Arora; Evan Sabri Eyuboglu; Armin Thomas; Benjamin Spector; Michael Poli; Atri Rudra; Christopher Ré;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we explore Monarch Mixer (M2), a new architecture that uses the same sub-quadratic primitive along both sequence length and model dimension.
242, Have It Your Way: Individualized Privacy Assignment for DP-SGD
Franziska Boenisch; Christopher Mühl; Adam Dziedzic; Roy Rinberg; Nicolas Papernot;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, setting a uniform privacy budget across all points may be overly conservative for some users or, conversely, not sufficiently protective for others. In this paper, we capture these preferences through individualized privacy budgets.
243, On Efficient Training Algorithms For Transformer Language Models
Jean Kaddour; Oscar Key; Piotr Nawrot; Pasquale Minervini; Matt Kusner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we revisit three algorithms: layer stacking, layer dropping, and selective backpropagation.
244, Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks
Aoxiang Zhang; Yu Ran; Weixuan Tang; Yuan-Gen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we make the first attempt to evaluate the robustness of NR-VQA models against adversarial attacks, and propose a patch-based random search method for black-box attack.
245, Deep Language Networks: Joint Prompt Training of Stacked LLMs Using Variational Inference
Alessandro Sordoni; Eric Yuan; Marc-Alexandre Côté; Matheus Pereira; Adam Trischler; Ziang Xiao; Arian Hosseini; Friederike Niedtner; Nicolas Le Roux;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: By viewing large language models (LLMs) as stochastic layers in a deep network, where the tunable parameters are the prompts at each layer, we chain multiple LLMs, feeding the output of the one at layer $l$ to the one at layer $l+1$, jointly training them using variational inference.
246, Benchmarking Robustness to Adversarial Image Obfuscations
Florian Stimberg; Ayan Chakrabarti; Chun-Ta Lu; Hussein Hazimeh; Otilia Stretcu; Wei Qiao; Yintao Liu; Merve Kaya; Cyrus Rashtchian; Ariel Fuxman; Mehmet Tek; Sven Gowal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To reach this goal, these malicious actors may obfuscate policy violating images (e.g., overlay harmful images by carefully selected benign images or visual patterns) to prevent machine learning models from reaching the correct decision. In this paper, we invite researchers to tackle this specific issue and present a new image benchmark.
247, M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models
Wenxuan Zhang; Mahani Aljunied; Chang Gao; Yew Ken Chia; Lidong Bing;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we introduce M3Exam, a novel benchmark sourced from real and official human exam questions for evaluating LLMs in a multilingual, multimodal, and multilevel context.
248, Fine-grained Expressivity of Graph Neural Networks
Jan Böker; Ron Levie; Ningyuan Huang; Soledad Villar; Christopher Morris;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Consequently, we provide a theoretical framework for graph and graphon similarity combining various topological variants of classical characterizations of the $1$-WL.
249, Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder
Huiwon Jang; Jihoon Tack; Daewon Choi; Jongheon Jeong; Jinwoo Shin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop MAE as a unified, modality-agnostic SSL framework.
250, Auditing Fairness By Betting
Ben Chugg; Santiago Cortes-Gomez; Bryan Wilder; Aaditya Ramdas;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We provide practical, efficient, and nonparametric methods for auditing the fairness of deployed classification and regression models.
251, Molecule Joint Auto-Encoding: Self-Supervised Learning of 2D and 3D Trajectories
weitao Du; Jiujiu Chen; Xuecang Zhang; Zhi-Ming Ma; Shengchao Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a pretraining method for molecule joint auto-encoding (MoleculeJAE).
252, Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models
Gen Luo; Yiyi Zhou; Tianhe Ren; Shengxin Chen; Xiaoshuai Sun; Rongrong Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel and affordable solution for the effective VL adaption of LLMs, called Mixture-of-Modality Adaptation (MMA).
253, LayoutGPT: Compositional Visual Planning and Generation with Large Language Models
Weixi Feng; Wanrong Zhu; Tsu-Jui Fu; Varun Jampani; Arjun Akula; Xuehai He; S Basu; Xin Eric Wang; William Yang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose LayoutGPT, a method to compose in-context visual demonstrations in style sheet language to enhance visual planning skills of LLMs.
254, Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence
Grace Luo; Lisa Dunlap; Dong Huk Park; Aleksander Holynski; Trevor Darrell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Diffusion Hyperfeatures, a framework for consolidating multi-scale and multi-timestep feature maps into per-pixel feature descriptors that can be used for downstream tasks.
255, Reverse Engineering Self-Supervised Learning
Ido Ben-Shaul; Ravid Shwartz-Ziv; Tomer Galanti; Shai Dekel; Yann LeCun;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Understanding the learned representation and underlying mechanisms of Self-Supervised Learning (SSL) often poses a challenge. In this paper, we ‘reverse engineer’ SSL, conducting an in-depth empirical analysis of its learned internal representations, encompassing diverse models, architectures, and hyperparameters.
256, Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams
Shiyan Chen; Jiyuan Zhang; Yajing Zheng; Zhaofei Yu; Tiejun Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel approach that integrates the two modalities from two branches, leveraging spike streams as auxiliary visual cues for guiding deblurring in high-speed motion scenes.
257, Adaptive Online Replanning with Diffusion Models
Siyuan Zhou; Yilun Du; Shun Zhang; Mengdi Xu; Yikang Shen; Wei Xiao; Dit-Yan Yeung; Chuang Gan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore how we may effectively replan with diffusion models.
258, DiffVL: Scaling Up Soft Body Manipulation Using Vision-Language Driven Differentiable Physics
Zhiao Huang; Feng Chen; Yewen Pu; Chunru Lin; Hao Su; Chuang Gan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce DiffVL, a method that enables non-expert users to communicate soft-body manipulation tasks -- a combination of vision and natural language, given in multiple stages -- that can be readily leveraged by a differential physics solver.
259, In-Context Learning Unlocked for Diffusion Models
Zhendong Wang; Yifan Jiang; Yadong Lu; yelong shen; Pengcheng He; Weizhu Chen; Zhangyang Atlas Wang; Mingyuan Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models.
260, Beta Diffusion
Mingyuan Zhou; Tianqi Chen; Huangjie Zheng; Zhendong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce beta diffusion with multiplicative transitions over time as a novel method for generative modeling of range-bounded data supported over disjoint regions.
261, Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models
Zhendong Wang; Yifan Jiang; Huangjie Zheng; Peihao Wang; Pengcheng He; Zhangyang Atlas Wang; Weizhu Chen; Mingyuan Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which thus helps democratize diffusion model training to broader users.
262, When Do Neural Nets Outperform Boosted Trees on Tabular Data?
Duncan McElfresh; Sujay Khandagale; Jonathan Valverde; Vishak Prasad C; Ganesh Ramakrishnan; Micah Goldblum; Colin White;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite recent advances in neural nets (NNs) for tabular data, there is still an active discussion on whether or not NNs generally outperform gradient-boosted decision trees (GBDTs) on tabular data, with several recent works arguing either that GBDTs consistently outperform NNs on tabular data, or vice versa. In this work, we take a step back and question the importance of this debate.
263, Ambient Diffusion: Learning Clean Distributions from Corrupted Data
Giannis Daras; Kulin Shah; Yuval Dagan; Aravind Gollakota; Alex Dimakis; Adam Klivans;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples.
264, Neural Oscillators Are Universal
Samuel Lanthaler; T. Konstantin Rusch; Siddhartha Mishra;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Coupled oscillators are being increasingly used as the basis of machine learning (ML) architectures, for instance in sequence modeling, graph representation learning and in physical neural networks that are used in analog ML devices. We introduce an abstract class of *neural oscillators* that encompasses these architectures and prove that neural oscillators are universal, i.e, they can approximate any continuous and casual operator mapping between time-varying functions, to desired accuracy.
265, Martingale Diffusion Models: Mitigating Sampling Drift By Learning to Be Consistent
Giannis Daras; Yuval Dagan; Alex Dimakis; Constantinos Daskalakis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, the standard training objective via Denoising Score Matching (DSM) is only designed to optimize over non-drifted data. To train on drifted data, we propose to enforce a \emph{Martingale} property (MP) which states that predictions of the model on its own generated data follow a Martingale, thus being consistent with the outputs that it generates.
266, ForecastPFN: Synthetically-Trained Zero-Shot Forecasting
Samuel Dooley; Gurnoor Singh Khurana; Chirag Mohapatra; Siddartha V Naidu; Colin White;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we take a different approach and devise ForecastPFN, a zero-shot forecasting model that is trained purely on a novel synthetic data distribution.
267, Res-Tuning: A Flexible and Efficient Tuning Paradigm Via Unbinding Tuner from Backbone
Zeyinzi Jiang; Chaojie Mao; Ziyuan Huang; Ao Ma; Yiliang Lv; Yujun Shen; Deli Zhao; Jingren Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work offers a new tuning paradigm, dubbed Res-Tuning, which intentionally \textit{unbinds} tuners from the backbone.
268, Recurrent Hypernetworks Are Surprisingly SOTA in Meta-RL
Jacob Beck; Risto Vuorio; Zheng Xiong; Shimon Whiteson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we conduct an extensive empirical investigation and suggest a method that works without the need for additional tuning.
269, Data Quality in Imitation Learning
Suneel Belkhale; Yuchen Cui; Dorsa Sadigh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we take the first step toward formalizing data quality for imitation learning through the lens of distribution shift: a high quality dataset encourages the policy to stay in distribution at test time.
270, Inverse Preference Learning: Preference-based RL Without A Reward Function
Joey Hejna; Dorsa Sadigh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Instead of using highly complex architectures, we develop a new and parameter-efficient algorithm, Inverse Preference Learning (IPL), specifically designed for learning from offline preference data. Our key insight is that for a fixed policy, the $Q$-function encodes all information about the reward function, effectively making them interchangeable.
271, Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching
Junsheng Zhou; Baorui Ma; Wenyuan Zhang; Yi Fang; Yu-Shen Liu; Zhizhong Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these methods struggle to map points and pixels to a shared latent space robustly since points and pixels have very different characteristics with patterns learned in different manners (MLP and CNN), and they also fail to construct supervision directly on the transformation since the PnP is non-differentiable, which leads to unstable registration results. To address these problems, we propose to learn a structured cross-modality latent space to represent pixel features and 3D features via a differentiable probabilistic PnP solver.
272, Understanding The Latent Space of Diffusion Models Through The Lens of Riemannian Geometry
Yong-Hyun Park; Mingi Kwon; Jaewoong Choi; Junghyo Jo; Youngjung Uh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Through analysis, we show that 1) the model focuses on low-frequency components early in the generative process and attunes to high-frequency details later.;2) At early timesteps, different samples share similar tangent spaces.; and 3) Simpler datasets that DMs trained on, the more consistent the tangent space for each timestep.
273, Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images
Yuxin Wen; John Kirchenbauer; Jonas Geiping; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs.
274, Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
Yuxin Wen; Neel Jain; John Kirchenbauer; Micah Goldblum; Jonas Geiping; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We describe an easy-to-use approach to automatically optimize hard text prompts through efficient gradient-based optimization.
275, Penalising The Biases in Norm Regularisation Enforces Sparsity
Etienne Boursier; Nicolas Flammarion;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Beyond simple intuitions, the relation between regularising parameters' norm and obtained estimators remains theoretically misunderstood. For one hidden ReLU layer networks with unidimensional data, this work shows the parameters' norm required to represent a function is given by the total variation of its second derivative, weighted by a $\sqrt{1+x^2}$ factor.
276, Towards Revealing The Mystery Behind Chain of Thought: A Theoretical Perspective
Guhao Feng; Yuntian Gu; Haotian Ye; Bohang Zhang; Di He; Liwei Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite the enormous empirical success, the underlying mechanisms behind CoT and how it unlocks the potential of LLMs remain elusive. In this paper, we take a first step towards theoretically answering these questions.
277, Efficient Diffusion Policies For Offline Reinforcement Learning
Bingyi Kang; Xiao Ma; Chao Du; Tianyu Pang; Shuicheng Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, Diffusion-QL suffers from two critical limitations. 1) It is computationally inefficient to forward and backward through the whole Markov chain during training. 2) It is incompatible with maximum likelihood-based RL algorithms (e.g., policy gradient methods) as the likelihood of diffusion models is intractable. Therefore, we propose efficient diffusion policy (EDP) to overcome these two challenges.
278, Paxion: Patching Action Knowledge in Video-Language Foundation Models
Zhenhailong Wang; Ansel Blume; Sha Li; Genglin Liu; Jaemin Cho; Zineng Tang; Mohit Bansal; Heng Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite recent video-language models’ (VidLM) impressive performance on various benchmark tasks, our diagnostic tasks reveal their surprising deficiency (near-random performance) in action knowledge, suggesting that current models rely on object recognition abilities as a shortcut for action understanding. To remedy this, we propose a novel framework, **Paxion**, along with a new **Discriminative Video Dynamics Modeling (DVDM)** objective.
279, Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
Sivan Doveh; Assaf Arbelle; Sivan Harary; Roei Herzig; Donghyun Kim; Paola Cascante-Bonilla; Amit Alfassy; Rameswar Panda; Raja Giryes; Rogerio Feris; Shimon Ullman; Leonid Karlinsky;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we uncover two factors limiting the VL models' compositional reasoning performance.
280, Bounce: A Reliable Bayesian Optimization Algorithm for Combinatorial and Mixed Spaces
Leonard Papenmeier; Luigi Nardi; Matthias Poloczek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To fill the need for a reliable algorithm for combinatorial and mixed spaces, this paper proposes Bounce that relies on a novel map of various variable types into nested embeddings of increasing dimensionality.
281, On The Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis
Arghya Datta; Sayak Chakrabarty;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The main obstruction is posed by the inherent identifiability nature of the PPCA model resulting from the rotational symmetry of the parameterization. To resolve this ambiguity, we propose a novel approach using quotient topological spaces and in particular, we show that the maximum likelihood solution is consistent in an appropriate quotient Euclidean space.
282, Efficient Neural Music Generation
Max W. Y. Lam; Qiao Tian; Tang Li; Zongyu Yin; Siyuan Feng; Ming Tu; Yuliang Ji; Rui Xia; Mingbo Ma; Xuchen Song; Jitong Chen; Wang Yuping; Yuxuan Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present **M**e**L**o**D**y (**M** for music; **L** for LM; **D** for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7\% or 99.6\% forward passes in MusicLM, respectively, for sampling 10s or 30s music.
283, Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns
Xin Liu; Zheng Li; Yifan Gao; Jingfeng Yang; Tianyu Cao; Zhengyang Wang; Bing Yin; Yangqiu Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose the Frequent Attribute Pattern Augmented Transformer (FAPAT) that characterizes user intents by building attribute transition graphs and matching attribute patterns.
284, Distribution-Free Statistical Dispersion Control for Societal Applications
Zhun Deng; Thomas Zollo; Jake Snell; Toniann Pitassi; Richard Zemel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We initiate the study of distribution-free control of statistical dispersion measures with societal implications and propose a simple yet flexible framework that allows us to handle a much richer class of statistical functionals beyond previous work.
285, Synthetic Experience Replay
Cong Lu; Philip Ball; Yee Whye Teh; Jack Parker-Holder;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we leverage the tremendous recent progress in generative modeling and propose Synthetic Experience Replay (SynthER), a diffusion-based approach to flexibly upsample an agent's collected experience.
286, Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis
Geonu Kim; Byunggook Na; Gunhee Kim; Hyuntae Cho; Seungjin Kang; Hee Sun Lee; Saerom Choi; Heejae Kim; Seungwon Lee; Yongdeok Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present comprehensive benchmark suite which consists of two semiconductor material datasets and 10 MLFF models with 6 evaluation metrics.
287, Provable Benefits of Annealing for Estimating Normalizing Constants
Omar Chehab; Aapo Hyvarinen; Andrej Risteski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: First, we show that using NCE is more efficient than the importance sampling estimator, but in the limit of infinitesimal path steps, the difference vanishes. Second, we find that using the geometric path brings down the estimation error from an exponential to a polynomial function of the parameter distance between the target and proposal distributions.
288, MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
Shitao Tang; Fuyang Zhang; Jiacheng Chen; Peng Wang; Yasutaka Furukawa;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces MVDiffusion, a simple yet effective multi-view image generation method for scenarios where pixel-to-pixel correspondences are available, such as perspective crops from panorama or multi-view images given depth/pose.
289, Provable Benefits of Score Matching
Chirag Pabbaraju; Dhruv Rohatgi; Anish Prasad Sevekari; Holden Lee; Ankur Moitra; Andrej Risteski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While score matching and variants thereof are popular in practice, precise theoretical understanding of the benefits and tradeoffs with maximum likelihood---both computational and statistical---are not well understood. In this work, we give the first example of a natural exponential family of distributions such that the score matching loss is computationally efficient to optimize, and has a comparable statistical efficiency to ML, while the ML loss is intractable to optimize using a gradient-based method.
290, DreamHuman: Animatable 3D Avatars from Text
Nikos Kolotouros; Thiemo Alldieck; Andrei Zanfir; Eduard Bazavan; Mihai Fieraru; Cristian Sminchisescu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present \emph{DreamHuman}, a method to generate realistic animatable 3D human avatar models entirely from textual descriptions.
291, Deep Equilibrium Based Neural Operators for Steady-State PDEs
Tanya Marwah; Ashwini Pokle; J. Zico Kolter; Zachary Lipton; Jianfeng Lu; Andrej Risteski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To achieve this, we first demonstrate that the solution of most steady-state PDEs can be expressed as a fixed point of a non-linear operator. Motivated by this observation, we propose FNO-DEQ, a deep equilibrium variant of the FNO architecture that directly solves for the solution of a steady-state PDE as the infinite-depth fixed point of an implicit operator layer using a black-box root solver and differentiates analytically through this fixed point resulting in $\mathcal{O}(1)$ training memory.
292, Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection
Haibao Yu; Yingjuan Tang; Enze Xie; Jilei Mao; Ping Luo; Zaiqing Nie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the uncertain temporal asynchrony and limited communication conditions that are present in traffic environments can lead to fusion misalignment and constrain the exploitation of infrastructure data. To address these issues in vehicle-infrastructure cooperative 3D (VIC3D) object detection, we propose the Feature Flow Net (FFNet), a novel cooperative detection framework.
293, ProteinBench: Benchmarking Protein Design on Diverse Tasks, Models, and Metrics
Zhangyang Gao; Cheng Tan; Yijie Zhang; Xingran Chen; Lirong Wu; Stan Z. Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose ProteinBench, a new benchmark for protein design, which comprises extended protein design tasks, integrated models, and diverse evaluation metrics.
294, Localized Symbolic Knowledge Distillation for Visual Commonsense Models
Jae Sung Park; Jack Hessel; Khyathi Chandu; Paul Pu Liang; Ximing Lu; Qiuyuan Huang; Peter West; Jianfeng Gao; Ali Farhadi; Yejin Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We build LocalizedVisual Commonsense model which allows users to specify (multiple) regions-as-input.
295, H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training
Yuzhong Wang; Xu Han; Weilin Zhao; Guoyang Zeng; Zhiyuan Liu; Maosong Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a framework to automatically find an efficient integration of memory optimization and parallelism for High-Throughput Transformer Training (named H3T), which is rarely considered by existing efforts for training big Transformer-based models.
296, One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning
Shaochen (Henry) Zhong; Zaichuan You; Jiamu Zhang; Sebastian Zhao; Zachary LeClaire; Zirui Liu; Vipin Chaudhary; Shuai Xu; Xia Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we answer the questions by fairly and comprehensively investigating the adversarial performance of 10+ popular structured pruning methods.
297, Assumption Violations in Causal Discovery and The Robustness of Score Matching
Francesco Montagna; Atalanti Mastakouri; Elias Eulig; Nicoletta Noceti; Lorenzo Rosasco; Dominik Janzing; Bryon Aragam; Francesco Locatello;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Because causal discovery without further assumptions is an ill-posed problem, each algorithm comes with its own set of usually untestable assumptions, some of which are hard to meet in real datasets. Motivated by these considerations, this paper extensively benchmarks the empirical performance of recent causal discovery methods on observational _iid_ data generated under different background conditions, allowing for violations of the critical assumptions required by each selected approach.
298, LLMScore: Unveiling The Power of Large Language Models in Text-to-Image Synthesis Evaluation
Yujie Lu; Xianjun Yang; Xiujun Li; Xin Eric Wang; William Yang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose LLMScore, a new framework that offers evaluation scores with multi-granularity compositionality.
299, SpokenWOZ: A Large-Scale Speech-Text Dataset for Spoken Task-Oriented Dialogue in Multiple Domains
Shuzheng Si; Wentao Ma; Haoyu Gao; Yuchuan Wu; Ting-En Lin; Yinpei Dai; Hangyu Li; Rui Yan; Fei Huang; Yongbin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To tackle the limitations, we introduce SpokenWOZ, a large-scale speech-text dataset for spoken TOD, containing 8 domains, 203k turns, 5.7k dialogues and 249 hours of audios from human-to-human spoken conversations.
300, CP-SLAM: Collaborative Neural Point-based SLAM System
Jiarui Hu; Mao Mao; Hujun Bao; Guofeng Zhang; Zhaopeng Cui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a collaborative implicit neural simultaneous localization and mapping (SLAM) system with RGB-D image sequences, which consists of complete front-end and back-end modules including odometry, loop detection, sub-map fusion, and global refinement.
301, The Adversarial Consistency of Surrogate Risks for Binary Classification
Natalie Frank; Jonathan Niles-Weed;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the consistency of surrogate risks for robust binary classification.
302, Unified 3D Segmenter As Prototypical Classifiers
Zheyun Qin; Cheng Han; Lu Xiankai; Qifan Wang; Xiushan Nie; Yilong Yin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce ProtoSEG, a prototype-based model that unifies semantic, instance, and panoptic segmentation tasks.
303, Where Did I Come From? Origin Attribution of AI-Generated Images
Zhenting Wang; Chen Chen; Yi Zeng; Lingjuan Lyu; Shiqing Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods only focus on specific types of generative models and require additional procedures during the training phase or generation phase. This makes them unsuitable for pre-trained models that lack these specific operations and may impair generation quality. To address this problem, we first develop an alteration-free and model-agnostic origin attribution method via reverse-engineering on image generation models, i.e., inverting the input of a particular model for a specific image.
304, Private Estimation Algorithms for Stochastic Block Models and Mixture Models
Hongjie Chen; Vincent Cohen-Addad; Tommaso d'Orsi; Alessandro Epasto; Jacob Imola; David Steurer; Stefan Tiegel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce general tools for designing efficient private estimation algorithms, in the high-dimensional settings, whose statistical guarantees almost match those of the best known non-private algorithms.
305, Tailoring Self-Attention for Graph Via Rooted Subtrees
Siyuan Huang; Yunchong Song; Jiayue Zhou; Zhouhan Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel multi-hop graph attention mechanism, named Subtree Attention (STA), to address the aforementioned issues.
306, Learning Transformer Programs
Dan Friedman; Alexander Wettig; Danqi Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce a procedure for training Transformers that are mechanistically interpretable by design.
307, Binarized Neural Machine Translation
Yichi Zhang; Ankush Garg; Yuan Cao; Lukasz Lew; Behrooz Ghorbani; Zhiru Zhang; Orhan Firat;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind.
308, MADLAD-400: Monolingual And Document-Level Large Audited Dataset
Sneha Kudugunta; Isaac Caswell; Biao Zhang; Xavier Garcia; Derrick Xin; Aditya Kusupati; Romi Stella; Ankur Bapna; Orhan Firat;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages.
309, DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
Qingkai Fang; Yan Zhou; Yang Feng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose DASpeech, a non-autoregressive direct S2ST model which realizes both fast and high-quality S2ST.
310, Mixed Samples As Probes for Unsupervised Model Selection in Domain Adaptation
Dapeng Hu; Jian Liang; Jun Hao Liew; Chuhui Xue; Song Bai; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose MixVal, a novel target-only method that employs \textit{mixup} to synthesize in-between target samples for validation.
311, GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
Xin Li; Dongze Lian; Zhihe Lu; Jiawang Bai; Zhibo Chen; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To mitigate that, we propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge (i.e., the correlation of different semantics/classes in textual and visual modalities) with a dual knowledge graph.
312, Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation
Keji He; Chenyang Si; Zhihe Lu; Yan Huang; Liang Wang; Xinchao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast to conventional approaches, which primarily focus on the spatial domain exploration, we propose a paradigm shift toward the Fourier domain.
313, Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner
Zhengxiang Shi; Aldo Lipani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on task-related texts improves the performance of fine-tuning (FT) in downstream tasks.
314, Can LLM Already Serve As A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
Jinyang Li; Binyuan Hui; Ge Qu; Binhua Li; Jiaxi Yang; Bowen Li; Bailin Wang; Bowen Qin; Ruiying Geng; Nan Huo; Xuanhe Zhou; Ma Chenhao; Guoliang Li; Kevin Chang; Fei Huang; Reynold Cheng; Yongbin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, most of the prevalent benchmarks, i.e., Spider, and WikiSQL, focus on database schema with few rows of database contents leaving the gap between academic study and real-world applications. To mitigate this gap, we present BIRD, a BIg benchmark for laRge-scale Database grounded in text-to-SQL tasks, containing 12,751 pairs of text-to-SQL data and 95 databases with a total size of 33.4 GB, spanning 37 professional domains.
315, Pre-Training Protein Encoder Via Siamese Sequence-Structure Diffusion Trajectory Prediction
Zuobai Zhang; Minghao Xu; Aurelie Lozano; Vijil Chenthamarakshan; Payel Das; Jian Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, inspired by the success of denoising diffusion models in generative tasks, we propose the DiffPreT approach to pre-train a protein encoder by sequence-structure joint diffusion modeling.
316, Hierarchical Randomized Smoothing
Yan Scholten; Jan Schuchardt; Aleksandar Bojchevski; Stephan Günnemann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a solution, we introduce hierarchical randomized smoothing: We partially smooth objects by adding random noise only on a randomly selected subset of their entities.
317, A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking
Hao Yan; Chaozhuo Li; Ruosong Long; Chao Yan; Jianan Zhao; Wenwen Zhuang; Jun Yin; Peiyan Zhang; Weihao Han; Hao Sun; Weiwei Deng; Qi Zhang; Lichao Sun; Xing Xie; Senzhang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose CS-TAG, a comprehensive and diverse collection of challenging benchmark datasets for TAGs.
318, SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Bill Yuchen Lin; Yicheng Fu; Karina Yang; Prithviraj (Raj) Ammanabrolu; Faeze Brahman; Shiyu Huang; Chandra Bhagavatula; Yejin Choi; Xiang Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks.
319, Simplicity Bias in 1-Hidden Layer Neural Networks
Depen Morwani; Jatin Batra; Prateek Jain; Praneeth Netrapalli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we rigorously define as well as thoroughly establish SB for *one hidden layer* neural networks in the infinite width regime.
320, StyleDrop: Text-to-Image Synthesis of Any Style
Kihyuk Sohn; Lu Jiang; Jarred Barber; Kimin Lee; Nataniel Ruiz; Dilip Krishnan; Huiwen Chang; Yuanzhen Li; Irfan Essa; Michael Rubinstein; Yuan Hao; Glenn Entis; Irina Blok; Daniel Castro Chin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce *StyleDrop*, a method that enables the synthesis of images that faithfully follow a specific style using a text-to-image model.
321, Information Maximization Perspective of Orthogonal Matching Pursuit with Applications to Explainable AI
Aditya Chattopadhyay; Ryan Pilgrim; Rene Vidal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our first contribution is to establish a fundamental connection between IP and OMP, where we prove that IP with random, continuous and linear queries ``almost'' reduces to OMP, with the difference being that IP selects atoms in order of \emph{normalized correlation gain}.
322, Language Model Tokenizers Introduce Unfairness Between Languages
Aleksandar Petrov; Emanuele La Malfa; Philip Torr; Adel Bibi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we show how disparity in the treatment of different languages arises at the tokenization stage, well before a model is even invoked.
323, Direct Diffusion Bridge Using Data Consistency for Inverse Problems
Hyungjin Chung; Jeongsol Kim; Jong Chul Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Several recent works have tried to alleviate this problem by building a diffusion process, directly bridging the clean and the corrupted for specific inverse problems. In this paper, we first unify these existing works under the name Direct Diffusion Bridges (DDB), showing that while motivated by different theories, the resulting algorithms only differ in the choice of parameters.
324, Transformer-based Planning for Symbolic Regression
Parshin Shojaee; Kazem Meidani; Amir Barati Farimani; Chandan Reddy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, these models primarily rely on supervised pretraining goals borrowed from text generation and overlook equation-specific objectives like accuracy and complexity. To address this, we propose TPSR, a Transformer-based Planning strategy for Symbolic Regression that incorporates Monte Carlo Tree Search into the transformer decoding process.
325, Simplifying Neural Network Training Under Class Imbalance
Ravid Shwartz-Ziv; Micah Goldblum; Yucen Li; C. Bayan Bruss; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, architecture size, pre-training, optimizer, and label smoothing, can achieve state-of-the-art performance without any specialized loss functions or samplers.
326, The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium
Shuyue Hu; Harold Soh; Georgios Piliouras;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that smooth fictitious play, a well-known learning model in game theory, can achieve both consensus and convergence to equilibrium in diverse multi-agent settings.
327, High-dimensional Asymptotics of Denoising Autoencoders
Hugo Cui; Lenka Zdeborová;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We address the problem of denoising data from a Gaussian mixture using a two-layer non-linear autoencoder with tied weights and a skip connection.
328, Clifford Group Equivariant Neural Networks
David Ruhe; Johannes Brandstetter; Patrick Forré;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Clifford Group Equivariant Neural Networks: a novel approach for constructing $\mathrm{E}(n)$-equivariant networks.
329, Improving Few-Shot Generalization By Exploring and Exploiting Auxiliary Data
Alon Albalak; Colin Raffel; William Yang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we focus on Few-shot Learning with Auxiliary Data (FLAD), a training paradigm that assumes access to auxiliary data during few-shot learning in hopes of improving generalization.
330, Few-shot Generation Via Recalling The Episodic-Semantic Memory Like Human Being
Zhibin Duan; Zhiyi Lv; Chaojie Wang; Bo Chen; Bo An; Mingyuan Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the cognitive systems of human being, in this work, we carefully design a variational structured memory module (VSM), which can simultaneously store both episodic and semantic memories to assistant existing generative models to efficiently recall memory during generation.
331, Training Private Models That Know What They Don’t Know
Stephan Rabanser; Anvith Thudi; Abhradeep Guha Thakurta; Krishnamurthy Dvijotham; Nicolas Papernot;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This challenge is further exacerbated when learning has to be differentially private: protection provided to sensitive data comes at the price of injecting additional randomness into the learning process. In this work, we conduct a thorough empirical investigation of selective classifiers---that can abstain when they are unsure---under a differential privacy constraint.
332, A Unified Conditional Framework for Diffusion-based Image Restoration
Yi Zhang; Xiaoyu Shi; Dasong Li; Xiaogang Wang; Jian Wang; Hongsheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a unified conditional framework based on diffusion models for image restoration.
333, Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss
An Zhang; Leheng Sheng; Zhibo Cai; Xiang Wang; Tat-Seng Chua;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To bridge the gap, we delve into the reasons underpinning the success of contrastive loss in CF, and propose a principled Adversarial InfoNCE loss (AdvInfoNCE), which is a variant of InfoNCE, specially tailored for CF methods.
334, Feature-Learning Networks Are Consistent Across Widths At Realistic Scales
Nikhil Vyas; Alexander Atanasov; Blake Bordelon; Depen Morwani; Sabarish Sainathan; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets.
335, UniControl: A Unified Diffusion Model for Controllable Visual Generation In The Wild
Can Qin; Shu Zhang; Ning Yu; Yihao Feng; Xinyi Yang; Yingbo Zhou; Huan Wang; Juan Carlos Niebles; Caiming Xiong; Silvio Savarese; Stefano Ermon; Yun Fu; Ran Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In response, we introduce UniControl, a new generative foundation model that consolidates a wide array of controllable condition-to-image (C2I) tasks within a singular framework, while still allowing for arbitrary language prompts.
336, Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
Tao Lei; Junwen Bai; Siddhartha Brahma; Joshua Ainslie; Kenton Lee; Yanqi Zhou; Nan Du; Vincent Zhao; Yuexin Wu; Bo Li; Yu Zhang; Ming-Wei Chang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency.
337, Two-Stage Learning to Defer with Multiple Experts
Anqi Mao; Mehryar Mohri; Yutao Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study a two-stage scenario for learning to defer, which we argue is crucial in practice for many applications.
338, Structured Prediction with Stronger Consistency Guarantees
Anqi Mao; Mehryar Mohri; Yutao Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These loss functions readily lead to new structured prediction algorithms with stronger theoretical guarantees, based on their minimization. We describe efficient algorithms for minimizing several of these surrogate losses, including a new *structured logistic loss*.
339, $H$-Consistency Bounds: Characterization and Extensions
Anqi Mao; Mehryar Mohri; Yutao Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present new and tight $H$-consistency bounds for both the family of constrained losses and that of comp-sum losses, which covers the familiar cross-entropy, or logistic loss applied to the outputs of a neural network.
340, Segment Anything in High Quality
Lei Ke; Mingqiao Ye; Martin Danelljan; Yifan liu; Yu-Wing Tai; Chi-Keung Tang; Fisher Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability.
341, Derandomized Novelty Detection with FDR Control Via Conformal E-values
Meshi Bashari; Amir Epstein; Yaniv Romano; Matteo Sesia;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose to make conformal inferences more stable by leveraging suitable conformal e-values instead of p-values to quantify statistical significance.
342, Pengi: An Audio Language Model for Audio Tasks
Soham Deshmukh; Benjamin Elizalde; Rita Singh; Huaming Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Pengi, a novel Audio Language Model that leverages Transfer Learning by framing all audio tasks as text-generation tasks.
343, Module-wise Adaptive Distillation for Multimodality Foundation Models
Chen Liang; Jiahui Yu; Ming-Hsuan Yang; Matthew Brown; Yin Cui; Tuo Zhao; Boqing Gong; Tianyi Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by our observation that certain architecture components, referred to as modules, contribute more significantly to the student's performance than others, we propose to track the contributions of individual modules by recording the loss decrement after distillation each module and choose the module with a greater contribution to distill more frequently.
344, Contrastive Lift: 3D Object Instance Segmentation By Slow-Fast Contrastive Fusion
Yash Bhalgat; Iro Laina; João Henriques; Andrea Vedaldi; Andrew Zisserman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instance segmentation in 3D is a challenging task due to the lack of large-scale annotated datasets. In this paper, we show that this task can be addressed effectively by leveraging instead 2D pre-trained models for instance segmentation.
345, FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation
Xinyu Sun; Peihao Chen; Jugang Fan; Jian Chen; Thomas Li; Mingkui Tan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods try to solve this problem by learning a navigation policy, which captures semantic features of the goal image and observation image independently and lastly fuses them for predicting a sequence of navigation actions. However, these methods suffer from two major limitations. 1) They may miss detailed information in the goal image, and thus fail to reason the goal location. 2) More critically, it is hard to focus on the goal-relevant regions in the observation image, because they attempt to understand observation without goal conditioning. In this paper, we aim to overcome these limitations by designing a Fine-grained Goal Prompting (\sexyname) method for image-goal navigation.
346, Transfer Visual Prompt Generator Across LLMs
Ao Zhang; Hao Fei; Yuan Yao; Wei Ji; Li Li; Zhiyuan Liu; Tat-Seng Chua;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate VPG transferability across LLMs for the first time, aiming to reduce the cost of VPG training.
347, Diverse Conventions for Human-AI Collaboration
Bidipta Sarkar; Andy Shih; Dorsa Sadigh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present a technique for generating diverse conventions by (1) maximizing their rewards during self-play, while (2) minimizing their rewards when playing with previously discovered conventions (cross-play), stimulating conventions to be semantically different.
348, Representational Strengths and Limitations of Transformers
Clayton Sanford; Daniel Hsu; Matus Telgarsky;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we establish both positive and negative results on the representation power of attention layers, with a focus on intrinsic complexity parameters such as width, depth, and embedding dimension.
349, Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models
Haonan Duan; Adam Dziedzic; Nicolas Papernot; Franziska Boenisch;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this comes at the expense of the practicality and efficiency offered by prompting. Therefore, we propose to privately learn to prompt.
350, JourneyDB: A Benchmark for Generative Image Understanding
Junting Pan; Keqiang Sun; Yuying Ge; Hao Li; Haodong Duan; Xiaoshi Wu; Renrui Zhang; Aojun Zhou; Zipeng Qin; Yi Wang; Jifeng Dai; Yu Qiao; Hongsheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Synthetic images, in comparison to real data, encompass a higher level of diversity in terms of both content and style, thereby presenting significant challenges for the models to fully grasp. In light of this challenge, we introduce a comprehensive dataset, referred to as JourneyDB, that caters to the domain of generative images within the context of multi-modal visual understanding.
351, InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
Junda Wu; Tong Yu; Rui Wang; Zhao Song; Ruiyi Zhang; Handong Zhao; Chaochao Lu; Shuai Li; Ricardo Henao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we develop an information-theoretic framework that formulates soft prompt tuning as maximizing mutual information between prompts and other model parameters (or encoded representations).
352, Proximity-Informed Calibration for Deep Neural Networks
Miao Xiong; Ailin Deng; Pang Wei Koh; Jiaying Wu; Shen Li; Jianqing Xu; Bryan Hooi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Motivated by the empirical findings, we propose ProCal, a plug-and-play algorithm with a theoretical guarantee to adjust sample confidence based on proximity.
353, Context-TAP: Tacking Any Point Demands Context Features
Weikang Bian; Zhaoyang Huang; Xiaoyu Shi; Yitong Dong; Yijin Li; Hongsheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel framework Context-TAP, which effectively improves point trajectory accuracy by aggregating spatial context features in videos.
354, Generate What You Prefer: Reshaping Sequential Recommendation Via Guided Diffusion
Zhengyi Yang; Jiancan Wu; Zhicai Wang; Xiang Wang; Yancheng Yuan; Xiangnan He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Sequential recommendation aims to recommend the next item that matches a user's interest, based on a sequence of items he/she interacted with before. Scrutinizing previous studies, we can summarize a common learning-to-classify paradigm --- given a positive item, a recommender model performs negative sampling to add negative items and learns to classify whether the user prefers them or not, based on his/her historical item sequence.
355, VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning
Jiayi Guan; Guang Chen; Jiaming Ji; Long Yang; ao zhou; Zhijun Li; changjun jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a Variational Optimization with Conservative Eestimation algorithm (VOCE) to solve the problem of optimizing safety policies in the offline dataset.
356, Consensus and Subjectivity of Skin Tone Annotation for ML Fairness
Candice Schumann; Gbolahan Olanubi; Auriel Wright; Ellis Monk; Courtney Heldreth; Susanna Ricco;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper examines the subjectivity of skin tone annotation through a series of annotation experiments using the Monk Skin Tone (MST) scale~\cite{Monk2022Monk}, a small pool of professional photographers, and a much larger pool of trained crowdsourced annotators.
357, Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity
Zijiao Chen; Jiaxin Qing; Juan Helen Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Mind-Video that learns spatiotemporal information from continuous fMRI data of the cerebral cortex progressively through masked brain modeling, multimodal contrastive learning with spatiotemporal attention, and co-training with an augmented Stable Diffusion model that incorporates network temporal inflation.
358, The Quantization Model of Neural Scaling
Eric Michaud; Ziming Liu; Uzay Girit; Max Tegmark;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the Quantization Model of neural scaling laws, explaining both the observed power law dropoff of loss with model and data size, and also the sudden emergence of new capabilities with scale.
359, Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
Matthew Le; Bowen Shi; Apoorv Vyas; Brian Karrer; Leda Sari; Yossi Adi; Vimal Manohar; Jay Mahadeokar; Wei-Ning Hsu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present Voicebox, the most versatile text-guided generative model for speech at scale.
360, CLadder: Assessing Causal Reasoning in Language Models
Zhijing Jin; Yuen Chen; Felix Leeb; Luigi Gresele; Ojasv Kamal; Zhiheng LYU; Kevin Blin; Fernando Gonzalez Adauto; Max Kleiman-Weiner; Mrinmaya Sachan; Bernhard Schölkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Much of the existing work in NLP on causality focuses on understanding commonsense causal relationships, thus failing to assess whether the model's reasoning abilities include *formal* causal inference. To address this, we propose a new NLP task, *causal inference in natural language*, inspired by the ``causal inference engine'' postulated by Judea Pearl.
361, OpenMask3D: Open-Vocabulary 3D Instance Segmentation
Ayca Takmaz; Elisabetta Fedele; Robert Sumner; Marc Pollefeys; Federico Tombari; Francis Engelmann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While such a representation can be directly employed to perform semantic segmentation, existing methods have limitations in their ability to handle object instances. In this work, we address this limitation, and propose OpenMask3D, which is a zero-shot approach for open-vocabulary 3D instance segmentation.
362, Block-State Transformers
Jonathan Pilault; Mahan Fathi; Pierre-Luc Bacon; Chris Pal; Orhan Firat; Ross Goroshin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a hybrid layer named Block-State Transformer (*BST*), that internally combines an SSM sublayer for long-range contextualization, and a Block Transformer sublayer for short-term representation of sequences.
363, BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents That Solve Fuzzy Tasks
Stephanie Milani; Anssi Kanervisto; Karolis Ramanauskas; Sander Schulhoff; Brandon Houghton; Rohin Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These comparisons serve as a fixed, preliminary leaderboard for evaluating newly-developed algorithms. To enable this comparison, we present a streamlined codebase for benchmarking new algorithms against the leaderboard.
364, Random-Access Infinite Context Length for Transformers
Amirkeivan Mohtashami; Martin Jaggi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel approach that allows access to the complete context while retaining random-access flexibility, closely resembling running attention on the entire context.
365, Unsupervised Image Denoising with Score Function
Yutong Xie; Mingze Yuan; Bin Dong; Quanzheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new approach which is more general and applicable to complicated noise models.
366, A Meta Learning Model for Scalable Hyperbolic Graph Neural Networks
Nurendra Choudhary; Nikhil Rao; Chandan Reddy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel method, Hyperbolic GRAph Meta Learner (H-GRAM), that learns transferable information from a set of support local subgraphs, in the form of hyperbolic meta gradients and label hyperbolic protonets, to enable faster learning over a query set of new tasks dealing with disjoint subgraphs.
367, Learning to Augment Distributions for Out-of-distribution Detection
Qizhou Wang; Zhen Fang; Yonggang Zhang; Feng Liu; Yixuan Li; Bo Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Accordingly, we propose Distributional-Augmented OOD Learning (DAOL), alleviating the OOD distribution discrepancy by crafting an OOD distribution set that contains all distributions in a Wasserstein ball centered on the auxiliary OOD distribution.
368, MAViL: Masked Audio-Video Learners
Po-Yao Huang; Vasu Sharma; Hu Xu; Chaitanya Ryali; haoqi fan; Yanghao Li; Shang-Wen Li; Gargi Ghosh; Jitendra Malik; Christoph Feichtenhofer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present Masked Audio-Video Learners (MAViL) to learn audio-visual representations with three complementary forms of self-supervision: (1) reconstructing masked raw audio and video inputs, (2) intra-modal and inter-modal contrastive learning with masking, and (3) self-training to predict aligned and contextualized audio-video representations learned from the first two objectives.
369, Energy-based Attention for Associative Memory
Benjamin Hoover; Yuchen Liang; Bao Pham; Rameswar Panda; Hendrik Strobelt; Duen Horng Chau; Mohammed Zaki; Dmitry Krotov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel architecture, called the Energy transformer (or ET for short), that uses a sequence of attention layers that are purposely designed to minimize a specifically engineered energy function, which is responsible for representing the relationships between the tokens. In this work, we introduce the theoretical foundations of ET, explore its empirical capabilities using the image completion task, and obtain strong quantitative results on the graph anomaly detection and graph classification tasks.
370, On Quantum Backpropagation, Information Reuse, and Cheating Measurement Collapse
Amira Abbas; Robbie King; Hsin-Yuan Huang; William J. Huggins; Ramis Movassagh; Dar Gilboa; Jarrod McClean;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that achieving backpropagation scaling is impossible without access to multiple copies of a state. With this added ability, we introduce an algorithm with foundations in shadow tomography that matches backpropagation scaling in quantum resources while reducing classical auxiliary computational costs to open problems in shadow tomography.
371, Noise-Adaptive Thompson Sampling for Linear Contextual Bandits
Ruitu Xu; Yifei Min; Tianhao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study linear contextual bandits with heteroscedastic noise and propose the first noise-adaptive Thompson sampling-style algorithm that achieves a variance-dependent regret upper bound of $\widetilde O\Big(d^{3/2} + d^{3/2} \sqrt{\sum_{t=1}^T \sigma_t^2}\Big)$, where $d$ is the dimension of the context vectors and $\sigma_t^2$ is the variance of the reward in round $t$.
372, Disentangled Wasserstein Autoencoder for Protein Engineering
Tianxiao Li; Hongyu Guo; Filippo Grazioli; Mark Gerstein; Martin Renqiang Min;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Identifying and modifying those functional sites is critical for protein engineering but computationally non-trivial, and requires significant domain knowledge. To automate this process from a data-driven perspective, we propose a disentangled Wasserstein autoencoder with an auxiliary classifier, which isolates the function-related patterns from the rest with theoretical guarantees.
373, DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Boxin Wang; Weixin Chen; Hengzhi Pei; Chulin Xie; Mintong Kang; Chenhui Zhang; Chejian Xu; Zidi Xiong; Ritik Dutta; Rylan Schaeffer; Sang Truong; Simran Arora; Mantas Mazeika; Dan Hendrycks; Zinan Lin; Yu Cheng; Sanmi Koyejo; Dawn Song; Bo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, this work proposes a comprehensive trustworthiness evaluation for large language models with a focus on GPT-4 and GPT-3.5, considering diverse perspectives – including toxicity, stereotype bias, adversarial robustness, out-of-distribution robustness, robustness on adversarial demonstrations, privacy, machine ethics, and fairness.
374, EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models
Michael Wornow; Rahul Thapa; Ethan Steinberg; Jason Fries; Nigam Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We are one of the first to fully release such a model for coded EHR data; in contrast, most prior models released for clinical data (e.g. GatorTron, ClinicalBERT) only work with unstructured text and cannot process the rich, structured data within an EHR. We provide an end-to-end pipeline for the community to validate and build upon its performance.
375, Multi-Head Adapter Routing for Cross-Task Generalization
Lucas Page-Caccia; Edoardo Maria Ponti; Zhan Su; Matheus Pereira; Nicolas Le Roux; Alessandro Sordoni;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Polytropon [Ponti et al., 2023] ($\texttt{Poly}$) jointly learns an inventory of adapters and a *routing* function that selects a (variable-size) subset of adapters for each task during both pre-training and few-shot adaptation. In this paper, we investigate the role that adapter routing plays in its success and design new variants based on our findings.
376, Equivariant Flow Matching
Leon Klein; Andreas Krämer; Frank Noe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce equivariant flow matching, a new training objective for equivariant CNFs that is based on the recently proposed optimal transport flow matching.
377, Interpretability at Scale: Identifying Causal Mechanisms in Alpaca
Zhengxuan Wu; Atticus Geiger; Christopher Potts; Noah Goodman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In the present paper, we scale DAS significantly by replacing the remaining brute-force search steps with learned parameters -- an approach we call Boundless DAS.
378, How Does GPT-2 Compute Greater-than?: Interpreting Mathematical Abilities in A Pre-trained Language Model
Michael Hanna; Ollie Liu; Alexandre Variengien;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we investigate the basic mathematical abilities often acquired by pre-trained language models.
379, Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking
Frederik Kunstner; Victor Sanches Portella; Mark Schmidt; Nicholas Harvey;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose multidimensional backtracking, an extension of the backtracking line-search to find good diagonal preconditioners for smooth convex problems.
380, Deep Reinforcement Learning with Plasticity Injection
Evgenii Nikishin; Junhyuk Oh; Georg Ostrovski; Clare Lyle; Razvan Pascanu; Will Dabney; Andre Barreto;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces plasticity injection, a minimalistic intervention that increases the network plasticity without changing the number of trainable parameters or biasing the predictions.
381, LANCE: Stress-testing Visual Models By Generating Language-guided Counterfactual Images
Viraj Prabhu; Sriram Yenamandra; Prithvijit Chattopadhyay; Judy Hoffman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE).
382, Domain Watermark: Effective and Harmless Dataset Copyright Protection Is Closed at Hand
Junfeng Guo; Yiming Li; Lixu Wang; Shu-Tao Xia; Heng Huang; Cong Liu; Bo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we revisit backdoor-based dataset ownership verification (DOV), which is currently the only feasible approach to protect the copyright of open-source datasets.
383, The Probability Flow ODE Is Provably Fast
Sitan Chen; Sinho Chewi; Holden Lee; Yuanzhi Li; Jianfeng Lu; Adil Salim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide the first polynomial-time convergence guarantees for the probabilistic flow ODE implementation (together with a corrector step) of score-based generative modeling.
384, Towards Robust and Expressive Whole-body Human Pose and Shape Estimation
Hui En Pang; Zhongang Cai; Lei Yang; Tianwei Zhang; Qingyi Tao; Zhonghua Wu; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel framework to enhance the robustness of whole-body pose and shape estimation.
385, FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
Mingyuan Zhang; Huirong Li; Zhongang Cai; Jiawei Ren; Lei Yang; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This lack of fine controllability limits the usage of motion generation to a larger audience. To tackle these challenges, we present FineMoGen, a diffusion-based motion generation and editing framework that can synthesize fine-grained motions, with spatial-temporal composition to the user instructions.
386, SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
Zhongang Cai; Wanqi Yin; Ailing Zeng; CHEN WEI; Qingping SUN; Wang Yanjun; Hui En Pang; Haiyi Mei; Mingyuan Zhang; Lei Zhang; Chen Change Loy; Lei Yang; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate scaling up EHPS towards the first generalist foundation model (dubbed SMPLer-X), with up to ViT-Huge as the backbone and training with up to 4.5M instances from diverse data sources.
387, Language Models Are Visual Reasoning Coordinators
Liangyu Chen; Bo Li; Sheng Shen; Jingkang Yang; Chunyuan Li; Kurt Keutzer; Trevor Darrell; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning.
388, Segment Any Point Cloud Sequences By Distilling Vision Foundation Models
Youquan Liu; Lingdong Kong; Jun CEN; Runnan Chen; Wenwei Zhang; Liang Pan; Kai Chen; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce ***Seal***, a novel framework that harnesses VFMs for segmenting diverse automotive point cloud sequences.
389, InsActor: Instruction-driven Physics-based Characters
Jiawei Ren; Mingyuan Zhang; Cunjun Yu; Xiao Ma; Liang Pan; Ziwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present $\textbf{InsActor}$, a principled generative framework that leverages recent advancements in diffusion-based human motion models to produce instruction-driven animations of physics-based characters.
390, Towards The Difficulty for A Deep Neural Network to Learn Concepts of Different Complexities
Dongrui Liu; Huiqi Deng; Xu Cheng; Qihan Ren; Kangrui Wang; Quanshi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Each interactive concept is encoded by the DNN to represent the collaboration between a set of input variables. Therefore, in this study, we aim to theoretically explain that interactive concepts involving more input variables (i.e., more complex concepts) are more difficult to learn.
391, CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models
Denis Kuznedelev; Eldar Kurtić; Elias Frantar; Dan Alistarh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These highly-accurate models are challenging to deploy, as they appear harder to compress using standard techniques such as pruning. We address this issue by introducing the Correlation Aware Pruner (CAP), a new unstructured pruning framework which significantly pushes the compressibility limits for state-of-the-art architectures.
392, ZipLM: Inference-Aware Structured Pruning of Language Models
Eldar Kurtić; Elias Frantar; Dan Alistarh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The breakthrough performance of large language models (LLMs) comes with major computational footprints and high deployment costs. In this paper, we progress towards resolving this problem by proposing a novel structured compression approach for LLMs, called ZipLM.
393, Knowledge Distillation Performs Partial Variance Reduction
Mher Safaryan; Alexandra Peste; Dan Alistarh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we shed new light on the inner workings of this method, by examining it from an optimization perspective.
394, To Repeat or Not To Repeat: Insights from Scaling LLM Under Token-Crisis
Fuzhao Xue; Yao Fu; Wangchunshu Zhou; Zangwei Zheng; Yang You;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we empirically investigate three key aspects under this approach.
395, Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
Zangwei Zheng; Xiaozhe Ren; Fuzhao Xue; Yang Luo; Xin Jiang; Yang You;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose an efficient LLM inference pipeline that harnesses the power of LLMs.
396, Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
Shengchao Liu; weitao Du; Yanjing Li; Zhuoxinran Li; Zhiling Zheng; Chenru Duan; Zhi-Ming Ma; Omar Yaghi; Animashree Anandkumar; Christian Borgs; Jennifer Chayes; Hongyu Guo; Jian Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Nevertheless, due to the rapidly evolving process of the field and the knowledge gap between science (e.g., physics, chemistry, \& biology) and machine learning communities, a benchmarking study on geometrical representation for such data has not been conducted. To address such an issue, in this paper, we first provide a unified view of the current symmetry-informed geometric methods, classifying them into three main categories: invariance, equivariance with spherical frame basis, and equivariance with vector frame basis.
397, Self-Chained Image-Language Model for Video Localization and Question Answering
Shoubin Yu; Jaemin Cho; Prateek Yadav; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Although humans often find a video moment to focus on and rewind the moment to answer questions, training a query-aware video moment localizer often requires expensive annotations and high computational costs. To address this issue, we propose Self-Chained Video Localization-Answering (SeViLA), a novel framework that leverages a single image-language model (BLIP-2) to tackle both temporal keyframe localization and question answering on videos.
398, Can Language Models Teach? Teacher Explanations Improve Student Performance Via Theory of Mind
Swarnadeep Saha; Peter Hase; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Next, when the teacher is constrained by a budget, we decompose the teaching problem along two axes for better efficiency: (1) deciding when it is worth explaining a data point, and (2) understanding how the teacher should personalize explanations to better teach the student. We tackle both these problems by proposing a Theory of Mind approach, in which the teacher builds two few-shot mental models of the student.
399, Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization
Xiangsen Wang; Haoran Xu; Yinan Zheng; Xianyuan Zhan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present OMIGA, a new offline multi-agent RL algorithm with implicit global-to-local value regularization.
400, Text-to-Image Diffusion Models Are Zero Shot Classifiers
Kevin Clark; Priyank Jaini;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, what knowledge their representations capture is not fully understood, and they have not been thoroughly explored on downstream tasks. We investigate diffusion models by proposing a method for evaluating them as zero-shot classifiers.
401, MomentDiff: Generative Video Moment Retrieval from Random to Real
Pandeng Li; Chen-Wei Xie; Hongtao Xie; Liming Zhao; Lei Zhang; Yun Zheng; Deli Zhao; Yongdong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To evaluate the influence of the temporal location biases, we propose two ``anti-bias'' datasets with location distribution shifts, named Charades-STA-Len and Charades-STA-Mom.
402, MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory
Yinan Liang; Ziwei Wang; Xiuwei Xu; Yansong Tang; Jie Zhou; Jiwen Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a hardware-algorithm co-design method called MCUFormer to deploy vision transformers on microcontrollers with extremely limited memory, where we jointly design transformer architectures and construct the inference compiler to fit the memory resource constraint.
403, How Does Adaptive Optimization Impact Local Neural Network Geometry?
Kaiqi Jiang; Dhruv Malik; Yuanzhi Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For iterate trajectories produced by running a generic optimization algorithm OPT, we introduce $R^{\text{OPT}}\_{\text{med}}$, a statistic that is analogous to the condition number of the loss Hessian evaluated at the iterates.
404, ResShift: Efficient Diffusion Model for Image Super-resolution By Residual Shifting
Zongsheng Yue; Jianyi Wang; Chen Change Loy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing acceleration sampling techniques inevitably sacrifice performance to some extent, leading to over-blurry SR results. To address this issue, we propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps, thereby eliminating the need for post-acceleration during inference and its associated performance deterioration.
405, Rubik's Cube: High-Order Channel Interactions with A Hierarchical Receptive Field
Naishan Zheng; man zhou; Chong Zhou; Chen Change Loy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most of these methods, \emph{e.g.}, convolution and the FFN architecture of transformers, only take implicit advantage of the first-order channel interaction and have yet to fully tap into its potential for high-order modeling. To address this, our study delves into modeling channel-dimension relationships, and proposes a simple yet effective and efficient high-order channel-wise operator for image restoration.
406, Guiding Diffusion Models for Versatile Face Restoration Via Partial Guidance
Peiqing Yang; Shangchen Zhou; Qingyi Tao; Chen Change Loy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce $\textit{partial guidance}$, a fresh perspective that is more adaptable to real-world degradations compared to existing works.
407, Mutual Information Regularized Offline Reinforcement Learning
Xiao Ma; Bingyi Kang; Zhongwen Xu; Min Lin; Shuicheng Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel MISA framework to approach offline RL from the perspective of Mutual Information between States and Actions in the dataset by directly constraining the policy improvement direction.
408, Towards Self-Interpretable Graph-Level Anomaly Detection
Yixin Liu; Kaize Ding; Qinghua Lu; Fuyi Li; Leo Yu Zhang; Shirui Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we investigate a new challenging problem, explainable GLAD, where the learning objective is to predict the abnormality of each graph sample with corresponding explanations, i.e., the vital subgraph that leads to the predictions.
409, Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data
Xin Zheng; Miao Zhang; Chunyang Chen; Quoc Viet Hung Nguyen; Xingquan Zhu; Shirui Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set without explicit graph structures, i.e., graph-free data.
410, GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels
Xin Zheng; Miao Zhang; Chunyang Chen; Soheila Molaei; Chuan Zhou; Shirui Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Evaluating the performance of graph neural networks (GNNs) is an essential task for practical GNN model deployment and serving, as deployed GNNs face significant performance uncertainty when inferring on unseen and unlabeled test graphs, due to mismatched training-test graph distributions. In this paper, we study a *new* problem, **GNN model evaluation**, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs, by precisely estimating its performance (e.g., node classification accuracy) on unseen graphs without labels.
411, Open Visual Knowledge Extraction Via Relation-Oriented Multimodality Model Prompting
Hejie Cui; Xinyu Fang; Zihan Zhang; Ran Xu; Xuan Kan; Xin Liu; Manling Li; Yangqiu Song; Carl Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we take a first exploration to a new paradigm of open visual knowledge extraction.
412, Semantic Image Synthesis with Unconditional Generator
JungWoo Chae; Hyunin Cho; Sooyeon Go; Kyungmook Choi; Youngjung Uh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a new approach, for reflecting user's detailed guiding masks on a pretrained unconditional generator.
413, Autodecoding Latent 3D Diffusion Models
Evangelos Ntavelis; Aliaksandr Siarohin; Kyle Olszewski; Chaoyang Wang; Luc V Gool; Sergey Tulyakov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Such data is scarce for 3D generation, prohibiting the learning of large-scale diffusion models for 3D synthesis. We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core.
414, Your Representations Are in The Network: Composable and Parallel Adaptation for Large Scale Models
Yonatan Dukler; Alessandro Achille; Hao Yang; Varsha Vivek; Luca Zancato; Benjamin Bowman; Avinash Ravichandran; Charless Fowlkes; Ashwin Swaminathan; Stefano Soatto;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a framework for transfer learning that efficiently adapts a large base-model by learning lightweight cross-attention modules attached to its intermediate activations.
415, Optimal Cross-learning for Contextual Bandits with Unknown Context Distributions
Jon Schneider; Julian Zimmert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of designing contextual bandit algorithms in the ``cross-learning'' setting of Balseiro et al., where the learner observes the loss for the action they play in all possible contexts, not just the context of the current round.
416, Calibration By Distribution Matching: Trainable Kernel Calibration Metrics
Charles Marx; Sofian Zalouk; Stefano Ermon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Drawing on the insight that calibration can be viewed as a distribution matching task, we introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression.
417, Learning to Compress Prompts with Gist Tokens
Jesse Mu; Xiang Li; Noah Goodman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Finetuning and distillation methods allow for specialization of LMs without prompting, but require retraining the model for each task. To avoid this trade-off entirely, we present gisting, which trains an LM to compress prompts into smaller sets of gist tokens which can be cached and reused for compute efficiency.
418, Thinker: Learning to Plan and Act
Stephen Chung; Ivan Anokhin; David Krueger;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model.
419, Bypassing The Simulator: Near-Optimal Adversarial Linear Contextual Bandits
Haolin Liu; Chen-Yu Wei; Julian Zimmert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the adversarial linear contextual bandit problem, where the loss vectors are selected fully adversarially and the per-round action set (i.e. the context) is drawn from a fixed distribution.
420, Robust Mean Estimation Without Moments
Gleb Novikov; David Steurer; Stefan Tiegel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, the guarantees that they achieve in the heavy-tailed setting are weaker than those for sub-Gaussian distributions with known covariance. In this work, we show that such a tradeoff, between error guarantees and heavy-tails, is not necessary for symmetric distributions.
421, Hardware Resilience Properties of Text-Guided Image Classifiers
Syed Talal Wasim; Kabila Haile Soboka; Abdulrahman Mahmoud; Salman Khan; David Brooks; Gu-Yeon Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This research paper presents a novel method to enhance the reliability of image classification models during deployment in the face of transient hardware errors.
422, Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning
Xinyi Wang; Wanrong Zhu; Michael Saxon; Mark Steyvers; William Yang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as implicit topic models. On this premise, we propose an algorithm to select optimal demonstrations from a set of annotated data with a small LLM, then directly generalize the selected demonstrations to larger LLMs.
423, KuaiSim: A Comprehensive Simulator for Recommender Systems
Kesen Zhao; Shuchang Liu; Qingpeng Cai; Xiangyu Zhao; Ziru Liu; Dong Zheng; Peng Jiang; Kun Gai;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing simulators have shown promising results but also have limitations such as simplified user feedback, lacking consistency with real-world data, the challenge of simulator evaluation, and difficulties in migration and expansion across RSs. To address these challenges, we propose KuaiSim, a comprehensive user environment that provides user feedback with multi-behavior and cross-session responses.
424, Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes
Yishi Xu; Jianqiao Sun; Yudi Su; Xinyang Liu; Zhibin Duan; Bo Chen; Mingyuan Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the issue, we propose an effective approach for topic modeling under the low-resource regime, the core of which is the adaptive generation of semantic matching word embeddings by integrating the contextual information of each task.
425, Dynamically Masked Discriminator for GANs
Wentian Zhang; Haozhe Liu; Bing Li; Jinheng Xie; Yawen Huang; Yuexiang Li; Yefeng Zheng; Bernard Ghanem;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel method for GANs from the viewpoint of online continual learning.
426, Preference-grounded Token-level Guidance for Language Model Fine-tuning
Shentao Yang; Shujian Zhang; Congying Xia; Yihao Feng; Caiming Xiong; Mingyuan Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: There is, therefore, a *granularity mismatch* between the preference and the LM training losses, which may complicate the learning problem. In this paper, we address this issue by developing an alternate training process, where we iterate between grounding the sequence-level preference into token-level training guidance, and improving the LM with the learned guidance.
427, CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
Guohao Li; Hasan Hammoud; Hani Itani; Dmitrii Khizbullin; Bernard Ghanem;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing.
428, Norm-guided Latent Space Exploration for Text-to-image Generation
Dvir Samuel; Rami Ben-Ari; Nir Darshan; Haggai Maron; Gal Chechik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To address this issue, we propose a novel method for interpolating between two seeds and demonstrate that it defines a new non-Euclidean metric that takes into account a norm-based prior on seeds. We describe a simple yet efficient algorithm for approximating this metric and use it to further define centroids in the latent seed space.
429, A Randomized Approach for Tight Privacy Accounting
Jiachen T. Wang; Saeed Mahloujifar; Tong Wu; Ruoxi Jia; Prateek Mittal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new differential privacy paradigm called estimate-verify-release (EVR), which tackles the challenges of providing a strict upper bound for the privacy parameter in DP compositions by converting an *estimate* of privacy parameter into a formal guarantee.
430, Diversify Your Vision Datasets with Automatic Diffusion-based Augmentation
Lisa Dunlap; Alyssa Umino; Han Zhang; Jiezhi Yang; Joseph Gonzalez; Trevor Darrell;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset's domains and augment the training data via language-guided image editing.
431, A Privacy-Friendly Approach to Data Valuation
Jiachen T. Wang; Yuqing Zhu; Yu-Xiang Wang; Ruoxi Jia; Prateek Mittal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We first emphasize the inherent privacy risks of KNN-Shapley, and demonstrate the significant technical challenges in adapting KNN-Shapley to accommodate differential privacy (DP). To overcome these challenges, we introduce TKNN-Shapley, a refined variant of KNN-Shapley that is privacy-friendly, allowing for straightforward modifications to incorporate DP guarantee (DP-TKNN-Shapley).
432, An Inverse Scaling Law for CLIP Training
Xianhang Li; Zeyu Wang; Cihang Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a surprising finding that there exists an inverse scaling law for CLIP training, whereby the larger the image/text encoders used, the shorter the sequence length of image/text tokens that can be applied in training.
433, Robust Multi-Agent Reinforcement Learning Via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
Alexander Bukharin; Yan Li; Yue Yu; Qingru Zhang; Zhehui Chen; Simiao Zuo; Chao Zhang; Songan Zhang; Tuo Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we show that we can gain robustness by controlling a policy’s Lipschitz constant, and under mild conditions, establish the existence of a Lipschitz and close-to-optimal policy. Motivated by these insights, we propose a new robust MARL framework, ERNIE, that promotes the Lipschitz continuity of the policies with respect to the state observations and actions by adversarial regularization.
434, Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms
Shenao Zhang; Boyi Liu; Zhaoran Wang; Tuo Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on our analysis, we propose a spectral normalization method to mitigate the exploding variance issue caused by long model unrolls.
435, Subject-driven Text-to-Image Generation Via Apprenticeship Learning
wenhu chen; Hexiang Hu; Yandong Li; Nataniel Ruiz; Xuhui Jia; Ming-Wei Chang; William Cohen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present SuTI, a Subject-driven Text-to-Image generator that replaces subject-specific fine tuning with {in-context} learning.
436, Why Deep Models Often Cannot Beat Non-deep Counterparts on Molecular Property Prediction?
Jun Xia; Lecheng Zhang; Xiao Zhu; Yue Liu; Zhangyang Gao; Bozhen Hu; Cheng Tan; Jiangbin Zheng; Siyuan Li; Stan Z. Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we benchmark 12 representative models (3 non-deep models and 9 deep models) on 15 molecule datasets.
437, Foundation Model Is Efficient Multimodal Multitask Model Selector
fanqing meng; Wenqi Shao; zhanglin peng; Chonghe Jiang; Kaipeng Zhang; Yu Qiao; Ping Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Although recent-advanced approaches employed lightweight metrics to measure models’ transferability, they often depend heavily on the prior knowledge of a single task, making them inapplicable in a multi-modal multi-task scenario. To tackle this issue, we propose an efficient multitask model selector (EMMS), which employs large-scale foundation models to transform diverse label formats such as categories, texts, and bounding boxes of different downstream tasks into a unified noisy label embedding.
438, Video-Mined Task Graphs for Keystep Recognition in Instructional Videos
Kumar Ashutosh; Santhosh Kumar Ramakrishnan; Triantafyllos Afouras; Kristen Grauman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Prior work largely treats keystep recognition in isolation of this broader structure, or else rigidly confines keysteps to align with a particular sequential script. We propose discovering a task graph automatically from how-to videos to represent probabilistically how people tend to execute keysteps, then leverage this graph to regularize keystep recognition in novel videos.
439, Augmentation-free Dense Contrastive Distillation for Efficient Semantic Segmentation
Jiawei Fan; Chao Li; Xiaolong Liu; Meina Song; Anbang Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods heavily rely on data augmentation and memory buffer, which entail high computational resource demands when applying them to handle semantic segmentation that requires to preserve high-resolution feature maps for making dense pixel-wise predications. In order to alleviate this problem, we present Augmentation-free Dense Contrastive Knowledge Distillation (Af-DCD), a new contrastive distillation learning paradigm to train compact and accurate deep neural networks for semantic segmentation applications.
440, LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
Neel Guha; Julian Nyarko; Daniel Ho; Christopher Ré; Adam Chilton; Aditya K; Alex Chohlas-Wood; Austin Peters; Brandon Waldon; Daniel Rockmore; Diego Zambrano; Dmitry Talisman; Enam Hoque; Faiz Surani; Frank Fagan; Galit Sarfaty; Gregory Dickinson; Haggai Porat; Jason Hegland; Jessica Wu; Joe Nudell; Joel Niklaus; John Nay; Jonathan Choi; Kevin Tobia; Margaret Hagan; Megan Ma; Michael Livermore; Nikon Rasumov-Rahe; Nils Holzenberger; Noam Kolt; Peter Henderson; Sean Rehaag; Sharad Goel; Shang Gao; Spencer Williams; Sunny Gandhi; Tom Zur; Varun Iyer; Zehua Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The advent of large language models (LLMs) and their adoption by the legal community has given rise to the question: what types of legal reasoning can LLMs perform? To enable greater study of this question, we present LegalBench: a collaboratively constructed legal reasoning benchmark consisting of 162 tasks covering six different types of legal reasoning.
441, Cola: A Benchmark for Compositional Text-to-image Retrieval
Arijit Ray; Filip Radenovic; Abhimanyu Dubey; Bryan Plummer; Ranjay Krishna; Kate Saenko;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Compositional reasoning is a hallmark of human visual intelligence; yet despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of compositional capability, we design Cola, a text-to-image retrieval benchmark to Compose Objects Localized with Attributes.
442, Learning Threshold Neurons Via Edge of Stability
Kwangjun Ahn; Sebastien Bubeck; Sinho Chewi; Yin Tat Lee; Felipe Suarez; Yi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take a step towards understanding genuinely non-convex training dynamics with large learning rates by performing a detailed analysis of gradient descent for simplified models of two-layer neural networks.
443, Improving Category Discovery When No Representation Rules Them All
Sagar Vaze; Andrea Vedaldi; Andrew Zisserman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we tackle the problem of Generalized Category Discovery (GCD).
444, FaceComposer: A Unified Framework for Versatile Facial Content Creation
Jiayu Wang; Kang Zhao; Yifeng Ma; Shiwei Zhang; Yingya Zhang; Yujun Shen; Deli Zhao; Jingren Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work presents FaceComposer, a unified generative model that accomplishesa variety of facial content creation tasks, including text-conditioned face synthesis,text-guided face editing, face animation etc.
445, VideoComposer: Compositional Video Synthesis with Motion Controllability
Xiang Wang; Hangjie Yuan; Shiwei Zhang; Dayou Chen; Jiuniu Wang; Yingya Zhang; Yujun Shen; Deli Zhao; Jingren Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions.
446, Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms
Peiyao Xiao; Hao Ban; Kaiyi Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a new direction-oriented multi-objective problem by regularizing the common descent direction within a neighborhood of a direction that optimizes a linear combination of objectives such as the average loss in MTL.
447, Fairness-guided Few-shot Prompting for Large Language Models
Huan Ma; Changqing Zhang; Yatao Bian; Lemao Liu; Zhirui Zhang; Peilin Zhao; Shu Zhang; Huazhu Fu; Qinghua Hu; Bingzhe Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Therefore, the construction of an appropriate prompt is essential for improving the performance of in-context learning. In this paper, we revisit this problem from the view of predictive bias.
448, DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
Ahmed Khaled; Konstantin Mishchenko; Chi Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce DoWG (Distance over Weighted Gradients), a new parameter-free optimizer that combines adaptive gradient weighting with distance estimation.
449, Revisiting The Evaluation of Image Synthesis with GANs
mengping yang; Ceyuan Yang; Yichi Zhang; Qingyan Bai; Yujun Shen; Bo Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models.
450, Language Models Can Improve Event Prediction By Few-Shot Abductive Reasoning
Xiaoming Shi; Siqiao Xue; Kangrui Wang; Fan Zhou; James Zhang; Jun Zhou; Chenhao Tan; Hongyuan Mei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction accuracy of event sequence models.
451, Can Language Models Solve Graph Problems in Natural Language?
Heng Wang; Shangbin Feng; Tianxing He; Zhaoxuan Tan; Xiaochuang Han; Yulia Tsvetkov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we propose NLGraph (Natural Language Graph), a comprehensive benchmark of graph-based problem solving designed in natural language.
452, NeuralGF: Unsupervised Point Normal Estimation By Learning Neural Gradient Function
Qing Li; Huifang Feng; Kanle Shi; Yue Gao; Yi Fang; Yu-Shen Liu; Zhizhong Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In addition, normal orientation consistency across shapes remains difficult to achieve without a separate post-processing procedure. To resolve these issues, we propose a novel method for estimating oriented normals directly from point clouds without using ground truth normals as supervision.
453, Is Distance Matrix Enough for Geometric Deep Learning?
Zian Li; Xiyuan Wang; Yinan Huang; Muhan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we expand on the families of counterexamples that MPNNs are unable to distinguish from their distance matrices, by constructing families of novel and symmetric geometric graphs, to better understand the inherent limitations of MPNNs.
454, Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks
Yaoyu Zhu; Wei Fang; Xiaodong Xie; Tiejun Huang; Zhaofei Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: After that, we infer that loss functions providing adequate positive overall gradients help training by theoretical analysis. Based on this, we propose the enhanced counting loss to replace the commonly used mean square counting loss.
455, Learning Neural Implicit Through Volume Rendering with Attentive Depth Fusion Priors
Pengchong Hu; Zhizhong Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, rendering a view each time suffers from incomplete depth at holes and unawareness of occluded structures from the depth supervision, which severely affects the accuracy of geometry inference via volume rendering. To resolve this issue, we propose to learn neural implicit representations from multi-view RGBD images through volume rendering with an attentive depth fusion prior.
456, Diffusion Optimization Models with Trajectory Alignment for Constrained Design Generation
Giorgio Giannone; Akash Srivastava; Ole Winther; Faez Ahmed;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, engineering optimization methods based on physics still outperform generative models when dealing with constrained environments where data is scarce and precision is paramount. To address these challenges, we introduce Diffusion Optimization Models (DOM) and Trajectory Alignment (TA), a learning framework that demonstrates the efficacy of aligning the sampling trajectory of diffusion models with the optimization trajectory derived from traditional physics-based methods.
457, Meta-Adapter: An Online Few-shot Learner for Vision-Language Model
cheng cheng; Lin Song; Ruoyi Xue; Hang Wang; Hongbin Sun; Yixiao Ge; Ying Shan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Nevertheless, few-shot learning methods based on CLIP typically require offline fine-tuning of the parameters on few-shot samples, resulting in longer inference time and the risk of overfitting in certain domains. To tackle these challenges, we propose the Meta-Adapter, a lightweight residual-style adapter, to refine the CLIP features guided by the few-shot samples in an online manner.
458, Resolving Interference When Merging Models
Prateek Yadav; Derek Tam; Leshem Choshen; Colin Raffel; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we demonstrate that prior merging techniques inadvertently lose valuable information due to two major sources of interference: (a) interference due to redundant parameter values and (b) disagreement on the sign of a given parameter’s values across models. To address this, we propose our method, TrIm, Elect Sign & Merge (TIES-Merging), which introduces three novel steps when merging models: (1) resetting parameters that only changed a small amount during fine-tuning, (2) resolving sign conflicts, and (3) merging only the parameters that are in alignment with the final agreed-upon sign.
459, Margin Maximization in Attention Mechanism
Davoud Ataee Tarzanagh; Yingcong Li; Xuechen Zhang; Samet Oymak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we initiate the study of a softmax-attention model $f(X)=v^\top X^\top \text{softmax}(XW^\top p)$, where, $X$ is the tokenized input, $v$ is the value weights, $W$ is the key-query weights, and $p$ is a tunable token/prompt.
460, Replicability in Reinforcement Learning
Amin Karbasi; Grigoris Velegkas; Lin Yang; Felix Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We initiate the mathematical study of replicability as an algorithmic property in the context of reinforcement learning (RL).
461, Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games
Zihan Zhu; Ethan Fang; Zhuoran Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, since agents are strategically coupled, traditional gradient-based methods are infeasible without the gradient oracle. To overcome this challenge, we model the strategic interactions by a general parametric model and propose a novel online algorithm, Online Performative Gradient Descent (OPGD), which leverages the ideas of online stochastic approximation and projected gradient descent to learn the Nash equilibrium in the context of function approximation for the unknown gradient.
462, Towards Optimal Caching and Model Selection for Large Model Inference
Banghua Zhu; Ying Sheng; Lianmin Zheng; Clark Barrett; Michael Jordan; Jiantao Jiao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, the large-scale deployment of these models is hindered by the significant resource requirements during inference. In this paper, we study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model selector to choose from an ensemble of models for query processing.
463, Doubly-Robust Self-Training
Banghua Zhu; Mingyu Ding; Philip Jacobson; Ming Wu; Wei Zhan; Michael Jordan; Jiantao Jiao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce doubly-robust self-training, an innovative semi-supervised algorithm that provably balances between two extremes.
464, Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback
Jangwon Kim; Hangyeol Kim; Jiwook Kang; Jongchan Baek; Soohee Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel actor-critic algorithm for an environment with delayed feedback, which addresses the state-space explosion problem of conventional approaches.
465, Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
ZHIYUAN LIU; Yaorui Shi; An Zhang; Enzhi Zhang; Kenji Kawaguchi; Xiang Wang; Tat-Seng Chua;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Masked graph modeling excels in the self-supervised representation learning of molecular graphs. Scrutinizing previous studies, we can reveal a common scheme consisting of three key components: (1) graph tokenizer, which breaks a molecular graph into smaller fragments (\ie subgraphs) and converts them into tokens; (2) graph masking, which corrupts the graph with masks; (3) graph autoencoder, which first applies an encoder on the masked graph to generate the representations, and then employs a decoder on the representations to recover the tokens of the original graph.
466, Saddle-to-Saddle Dynamics in Diagonal Linear Networks
Scott Pesme; Nicolas Flammarion;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we fully describe the trajectory of gradient flow over $2$-layer diagonal linear networks for the regression setting in the limit of vanishing initialisation.
467, Testing The General Deductive Reasoning Capacity of Large Language Models Using OOD Examples
Abulhair Saparov; Richard Yuanzhe Pang; Vishakh Padmakumar; Nitish Joshi; Mehran Kazemi; Najoung Kim; He He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To measure the general deductive reasoning ability of LLMs, we test on a broad set of deduction rules and measure their ability to generalize to more complex proofs from simpler demonstrations from multiple angles: depth-, width-, and compositional generalization.
468, Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach
Jinqiu Jin; Haoxuan Li; Fuli Feng; Sihao Ding; Peng Wu; Xiangnan He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce social attribute-aware IGF metrics from the perspective of social utility, and propose a new IGF problem that considers both direct and social utilities.
469, Unleashing The Power of Graph Data Augmentation on Covariate Shift
Yongduo Sui; Qitian Wu; Jiancan Wu; Qing Cui; Longfei Li; Jun Zhou; Xiang Wang; Xiangnan He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most strategies, such as invariant learning or graph augmentation, typically struggle with limited training environments or perturbed stable features, thus exposing limitations in handling the covariate shift issue. To address this, we develop a simple yet effective data augmentation strategy, Adversarial Invariant Augmentation (AIA), to handle the graph covariate shift.
470, Understanding Contrastive Learning Via Distributionally Robust Optimization
Junkang Wu; Jiawei Chen; Jiancan Wu; Wentao Shi; Xiang Wang; Xiangnan He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This study reveals the inherent tolerance of contrastive learning (CL) towards sampling bias, wherein negative samples may encompass similar semantics (\eg labels).
471, Evaluating Post-hoc Explanations for Graph Neural Networks Via Robustness Analysis
Junfeng Fang; Wei Liu; Xiang Wang; Zemin Liu; An Zhang; Yuan Gao; Xiangnan He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Conversely, in this work, we endeavor to confront the issue via introducing a novel evaluation metric, termed **O**OD-resistant **A**dversarial **R**obustness (OAR).
472, 3D Open-vocabulary Segmentation with Foundation Models
Kunhao Liu; Fangneng Zhan; Jiahui Zhang; MUYU XU; Yingchen Yu; Abdulmotaleb El Saddik; Christian Theobalt; Eric Xing; Shijian Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We tackle the challenges in 3D open-vocabulary segmentation by exploiting the open-vocabulary multimodal knowledge and object reasoning capability of pre-trained foundation models CLIP and DINO, without necessitating any fine-tuning.
473, MixFormerV2: Efficient Fully Transformer Tracking
Yutao Cui; Tianhui Song; Gangshan Wu; Limin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as \emph{MixFormerV2}, without any dense convolutional operation and complex score prediction module.
474, Solving A Class of Non-Convex Minimax Optimization in Federated Learning
Xidong Wu; Jianhui Sun; Zhengmian Hu; Aidong Zhang; Heng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study a class of federated nonconvex minimax optimization problems.
475, Federated Conditional Stochastic Optimization
Xidong Wu; Jianhui Sun; Zhengmian Hu; Junyi Li; Aidong Zhang; Heng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper considers the nonconvex conditional stochastic optimization in federated learning and proposes the first federated conditional stochastic optimization algorithm (FCSG) with a conditional stochastic gradient estimator.
476, Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks
Yiwen Kou; Zixiang Chen; Quanquan Gu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, implicit bias in non-smooth neural networks trained by gradient descent remains an open question. In this paper, we aim to answer this question by studying the implicit bias of gradient descent for training two-layer fully connected (leaky) ReLU neural networks.
477, ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields
Jiahua Dong; Yu-Xiong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce ViCA-NeRF, a view-consistency-aware method for 3D editing with text instructions.
478, EDGI: Equivariant Diffusion for Planning with Embodied Agents
Johann Brehmer; Joey Bose; Pim de Haan; Taco Cohen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the Equivariant Diffuser for Generating Interactions (EDGI), an algorithm for MBRL and planning that is equivariant with respect to the product of the spatial symmetry group SE(3), the discrete-time translation group ℤ, and the object permutation group Sₙ.
479, Geometric Algebra Transformers
Johann Brehmer; Pim de Haan; Sönke Behrends; Taco Cohen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we introduce the Geometric Algebra Transformer (GATr), a general-purpose architecture for geometric data.
480, Diversify \& Conquer: Outcome-directed Curriculum RL Via Out-of-Distribution Disagreement
Daesol Cho; Seungjae Lee; H. Jin Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics of the environment or external rewards. To tackle these challenges, this work proposes a new approach for curriculum RL called $\textbf{D}$iversify for $\textbf{D}$isagreement \& $\textbf{C}$onquer ($\textbf{D2C}$).
481, Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model
Jiankai Sun; Yiqi Jiang; Jianing Qiu; Parth Nobel; Mykel J Kochenderfer; Mac Schwager;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we quantify the uncertainty of dynamics models using Conformal Prediction (CP), which is an effective technique for constructing prediction sets that achieve valid coverage.
482, The Expressive Power of Pooling in Graph Neural Networks
Filippo Maria Bianchi; Veronica Lachi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we derive sufficient conditions for a pooling operator to fully preserve the expressive power of the MP layers before it.
483, Learning to Reason and Memorize with Self-Notes
Jack Lanchantin; Shubham Toshniwal; Jason Weston; arthur szlam; Sainbayar Sukhbaatar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Large language models have been shown to struggle with multi-step reasoning, and do not retain previous reasoning steps for future use. We propose a simple method for solving both of these problems by allowing the model to take Self-Notes.
484, BiMatting: Efficient Video Matting Via Binarization
Haotong Qin; Lei Ke; Xudong Ma; Martin Danelljan; Yu-Wing Tai; Chi-Keung Tang; Xianglong Liu; Fisher Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, binarization of the video matting model is not a straightforward process, and our empirical analysis has revealed two primary bottlenecks: severe representation degradation of the encoder and massive redundant computations of the decoder. To address these issues, we propose BiMatting, an accurate and efficient video matting model using binarization.
485, Adversarial Training for Graph Neural Networks
Lukas Gosch; Simon Geisler; Daniel Sturm; Bertrand Charpentier; Daniel Zügner; Stephan Günnemann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that more flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints.
486, ProPILE: Probing Privacy Leakage in Large Language Models
Siwon Kim; Sangdoo Yun; Hwaran Lee; Martin Gubri; Sungroh Yoon; Seong Joon Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents ProPILE, a novel probing tool designed to empower data subjects, or the owners of the PII, with awareness of potential PII leakage in LLM-based services.
487, BeaverTails: A Human-Preference Dataset for LLM Harmlessness Alignment
Jiaming Ji; Mickel Liu; Josef Dai; Xuehai Pan; Chi Zhang; Ce Bian; Boyuan Chen; Ruiyang Sun; Yizhou Wang; Yaodong Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs).
488, Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark
Jiaming Ji; Borong Zhang; Jiayi Zhou; Xuehai Pan; Weidong Huang; Ruiyang Sun; Yiran Geng; Josef Dai; Yaodong Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input.
489, IEBins: Iterative Elastic Bins for Monocular Depth Estimation
Shuwei Shao; Zhongcai Pei; Xingming Wu; Zhong Liu; Weihai Chen; Zhengguo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel concept of iterative elastic bins (IEBins) for the classification-regression-based MDE.
490, A New Perspective on Building Efficient and Expressive 3D Equivariant Graph Neural Networks
weitao Du; Yuanqi Du; Limei Wang; Dieqiao Feng; Guifeng Wang; Shuiwang Ji; Carla Gomes; Zhi-Ming Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a local hierarchy of 3D isomorphism to evaluate the expressive power of equivariant GNNs and investigate the process of representing global geometric information from local patches.
491, OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents
Hugo Laurençon; Lucile Saulnier; Leo Tronchon; Stas Bekman; Amanpreet Singh; Anton Lozhkov; Thomas Wang; Siddharth Karamcheti; Alexander Rush; Douwe Kiela; Matthieu Cord; Victor Sanh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce the OBELICS dataset, an open web-scale filtered dataset of interleaved image-text documents comprising 141 million web pages extracted from Common Crawl, 353 million associated images, and 115 billion text tokens.
492, M$^2$Hub: Unlocking The Potential of Machine Learning for Materials Discovery
Yuanqi Du; Yingheng Wang; Yining Huang; Jianan Canal Li; Yanqiao Zhu; Tian Xie; Chenru Duan; John Gregoire; Carla Gomes;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce M$^2$Hub, a toolkit for advancing machine learning in materials discovery.
493, Greedy Poisson Rejection Sampling
Gergely Flamich;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we conclusively solve one-shot channel simulation for one-dimensional problems where the target-proposal density ratio is unimodal by describing an algorithm with optimal runtime.
494, Rethinking The Role of Token Retrieval in Multi-Vector Retrieval
Jinhyuk Lee; Zhuyun Dai; Sai Meher Karthik Duddu; Tao Lei; Iftekhar Naim; Ming-Wei Chang; Vincent Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to simplify the multi-vector retrieval by rethinking the role of token retrieval.
495, Real-Time Motion Prediction Via Heterogeneous Polyline Transformer with Relative Pose Encoding
Zhejun Zhang; Alexander Liniger; Christos Sakaridis; Fisher Yu; Luc V Gool;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, they suffer from high computational overhead and poor scalability as the number of agents to be predicted increases. To address this problem, we introduce the K-nearest neighbor attention with relative pose encoding (KNARPE), a novel attention mechanism allowing the pairwise-relative representation to be used by Transformers.
496, NICE: NoIse-modulated Consistency REgularization for Data-Efficient GANs
Yao Ni; Piotr Koniusz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The bottleneck imposed by limited data presents substantial obstacles for efficient training of GAN, including discriminator overfitting and training instability. In this paper, we present a novel approach called NoIse-modulated Consistency rEgularization (NICE) to overcome these challenges.
497, A Bayesian Perspective On Training Data Attribution
Elisa Nguyen; Minjoon Seo; Seong Joon Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce a Bayesian perspective on the TDA task, where the learned model is treated as a Bayesian posterior and the TDA estimates as random variables.
498, Estimating The Rate-Distortion Function By Wasserstein Gradient Descent
Yibo Yang; Stephan Eckstein; Marcel Nutz; Stephan Mandt;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a method to compute $R(D)$ based on Wasserstein gradient descent.
499, Riemannian Laplace Approximations for Bayesian Neural Networks
Federico Bergamin; Pablo Moreno-Muñoz; Søren Hauberg; Georgios Arvanitidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a simple parametric approximate posterior that adapts to the shape of the true posterior through a Riemannian metric that is determined by the log-posterior gradient.
500, Is This Loss Informative? Faster Text-to-Image Customization By Tracking Objective Dynamics
Anton Voronov; Mikhail Khoroshikh; Artem Babenko; Max Ryabinin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, many efficient methods of adaptation have a long training time, which limits their practical applications, slows down research experiments, and spends excessive GPU resources. In this work, we study the training dynamics of popular text-to-image personalization methods (such as Textual Inversion or DreamBooth), aiming to speed them up.
501, Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation
Haoran Chen; Xintong Han; Zuxuan Wu; Yu-Gang Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by recent advances in prompt learning that adapts high-capacity models for downstream tasks in a computationally economic way, we introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA.
502, Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples
Shashanka Venkataramanan; Ewa Kijak; laurent amsaleg; Yannis Avrithis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In most methods, the number of generated examples is limited to the mini-batch size and the number of examples being interpolated is limited to two (pairs), in the input space. We make progress in this direction by introducing MultiMix, which generates an arbitrarily large number of interpolated examples beyond the mini-batch size and interpolates the entire mini-batch in the embedding space.
503, Approximation-Generalization Trade-offs Under (Approximate) Group Equivariance
Mircea Petrache; Shubhendu Trivedi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, it is posited that when the data and/or the model exhibits only approximate or partial symmetry, the optimal or best-performing model is one where the model symmetry aligns with the data symmetry. In this paper, we conduct a formal unified investigation of these intuitions.
504, Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization
Kaiyue Wen; Tengyu Ma; Zhiyuan Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Through theoretical and empirical investigation, we identify the following three scenarios for two-layer ReLU networks:(1) flatness provably implies generalization; (2) there exist non-generalizing flattest models and sharpness minimization algorithms fail to generalize poorly, and (3) perhaps most strikingly, there exist non-generalizing flattest models, but sharpness minimization algorithms still generalize.
505, On The Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: An Improved Analysis
Ta Duy Nguyen; Alina Ene; Huy Nguyen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we revisit the generalization error of stochastic mirror descent for quadratically bounded losses studied in Telgarsky (2022).
506, DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models
威佳 吴; Yuzhong Zhao; Hao Chen; Yuchao Gu; Rui Zhao; Yefei He; Hong Zhou; Mike Zheng Shou; Chunhua Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse syntheticimages and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth).
507, Adversarial Examples Might Be Avoidable: The Role of Data Concentration in Adversarial Robustness
Ambar Pal; Jeremias Sulam; Rene Vidal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we theoretically demonstrate that a key property of the data distribution -- concentration on small-volume subsets of the input space -- determines whether a robust classifier exists.
508, Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration
Dongyoung Kim; Jinwoo Shin; Pieter Abbeel; Younggyo Seo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel exploration technique that maximizes the value-conditional state entropy, which separately estimates the state entropies that are conditioned on the value estimates of each state, then maximizes their average.
509, SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models
Ziyi Wu; Jingyu Hu; Wuyue Lu; Igor Gilitschenski; Animesh Garg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we focus on improving slot-to-image decoding, a crucial aspect for high-quality visual generation.
510, Many-body Approximation for Non-negative Tensors
Kazu Ghalamkari; Mahito Sugiyama; Yoshinobu Kawahara;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present an alternative approach to decompose non-negative tensors, called many-body approximation.
511, BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
Darko Drakulic; Sofia Michel; Florian Mai; Arnaud Sors; Jean-Marc Andreoli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a novel formulation of Combinatorial Optimization Problems (COPs) as Markov Decision Processes (MDPs) that effectively leverages common symmetries of COPs to improve out-of-distribution robustness.
512, Exploring Why Object Recognition Performance Degrades Across Income Levels and Geographies with Factor Annotations
Laura Gustafson; Megan Richards; Melissa Hall; Caner Hazirbas; Diane Bouchacourt; Mark Ibrahim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study a range of modern vision models, finding that performance disparities are most associated with differences in _texture, occlusion_, and images with _darker lighting_.
513, Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
Maxime Chevalier-Boisvert; Bolun Dai; Mark Towers; Rodrigo Perez-Vicente; Lucas Willems; Salem Lahlou; Suman Pal; Pablo Samuel Castro; J Terry;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present the Minigrid and Miniworld libraries, which provide a suite of modular and highly customizable simulation environments to facilitate the development of reinforcement learning (RL) algorithms for solving goal-oriented tasks.
514, ADGym: Design Choices for Deep Anomaly Detection
Minqi Jiang; Chaochuan Hou; Ao Zheng; Songqiao Han; Hailiang Huang; Qingsong Wen; Xiyang Hu; Yue Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Meanwhile, we may neglect the contribution of other meaningful prerequisite steps like preprocessing by giving all credits to newly designed loss functions and/or architectures. In this paper, we address the above gaps by answering: (i) which components (i.e., design choices) of deep AD methods play crucial roles in detecting anomalies?
515, QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution
Haotong Qin; Yulun Zhang; Yifu Ding; Yifan liu; Xianglong Liu; Martin Danelljan; Fisher Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, many quantized SR models suffer from accuracy degradation compared to their full-precision counterparts, especially at ultra-low bit widths (2-4 bits), limiting their practical applications. To address this issue, we propose a novel quantized image SR network, called QuantSR, which achieves accurate and efficient SR processing under low-bit quantization.
516, Graphs Contrastive Learning with Stable and Scalable Spectral Encoding
Deyu Bo; Yuan Fang; Yang Liu; Chuan Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing spectral-based graph views either ignore the eigenvectors that encode valuable positional information or suffer from high complexity when trying to address the instability of spectral features. To tackle these challenges, we first design an informative, stable, and scalable spectral encoder, termed EigenMLP, to learn effective representations from the spectral features.
517, Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity
Weichao Mao; Haoran Qiu; Chen Wang; Hubertus Franke; Zbigniew Kalbarczyk; Ravishankar Iyer; Tamer Basar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the benefits of meta-learning in solving multiple MARL tasks collectively.
518, Post Hoc Explanations of Language Models Can Improve Language Models
Satyapriya Krishna; Jiaqi Ma; Dylan Slack; Asma Ghandeharioun; Sameer Singh; Himabindu Lakkaraju;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a novel framework, Amplifying Model Performance by Leveraging In-Context Learning with Post Hoc Explanations (AMPLIFY), which addresses the aforementioned challenges by automating the process of rationale generation.
519, Star-Shaped Denoising Diffusion Probabilistic Models
Andrey Okhotin; Dmitry Molchanov; Arkhipkin Vladimir; Grigory Bartosh; Viktor Ohanesian; Aibek Alanov; Dmitry Vetrov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce Star-Shaped DDPM (SS-DDPM).
520, Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning
Casey Meehan; Florian Bordes; Pascal Vincent; Kamalika Chaudhuri; Chuan Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we perform a systematic study of the unintended memorization of image-specific information in SSL models -- which we refer to as déjà vu memorization.
521, Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection
Lingchen Meng; Xiyang Dai; Jianwei Yang; Dongdong Chen; Yinpeng Chen; Mengchen Liu; Yi-Ling Chen; Zuxuan Wu; Lu Yuan; Yu-Gang Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One popular strategy is to explore extra data with image-level labels, yet it produces limited results due to (1) semantic ambiguity---an image-level label only captures a salient part of the image, ignoring the remaining rich semantics within the image; and (2) location sensitivity---the label highly depends on the locations and crops of the original image, which may change after data transformations like random cropping. To remedy this, we propose RichSem, a simple but effective method, which is robust to learn rich semantics from coarse locations without the need of accurate bounding boxes.
522, Understanding Expertise Through Demonstrations: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
Siliang Zeng; Chenliang Li; Alfredo Garcia; Mingyi Hong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new algorithmic framework to solve the bi-level optimization problem formulation and provide statistical and computational guarantees of performance for the associated optimal reward estimator.
523, DaTaSeg: Taming A Universal Multi-Dataset Multi-Task Segmentation Model
Xiuye Gu; Yin Cui; Jonathan Huang; Abdullah Rashwan; Xuan Yang; Xingyi Zhou; Golnaz Ghiasi; Weicheng Kuo; Huizhong Chen; Liang-Chieh Chen; David Ross;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.
524, Statistical Guarantees for Variational Autoencoders Using PAC-Bayesian Theory
Diarra Mbacke; Florence Clerc; Pascal Germain;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Using PAC-Bayesian theory, this work develops statistical guarantees for VAEs.
525, Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise
Ta Duy Nguyen; Thien H Nguyen; Alina Ene; Huy Nguyen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the convergence in high probability of clipped gradient methods when the noise distribution has heavy tails, i.e., with bounded $p$th moments, for some $1
526, NeRF Revisited: Fixing Quadrature Instability in Volume Rendering
Mikaela Angelina Uy; Guandao Yang; Kiyohiro Nakayama; Leonidas Guibas; Ke Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a mathematically principled solution by reformulating the sample-based rendering equation so that it corresponds to the exact integral under piecewise linear volume density.
527, Neural Approximation of Wasserstein Distance Via A Universal Architecture for Symmetric and Factorwise Group Invariant Functions
Samantha Chen; Yusu Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we first present a general neural network architecture for approximating SFGI functions. The main contribution of this paper combines this general NN with a sketching idea in order to develop a specific and efficient neural network which can approximate the $p$-th Wasserstein distance between point sets.
528, Knowledge Distillation for High Dimensional Search Index
Zepu Lu; Jin Chen; Defu Lian; ZAIXI ZHANG; Yong Ge; Enhong Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel KnowledgeDistillation for high dimensional search index framework (KDindex), with the aim of efficiently learning lightweight indexes by distilling knowledge from high-precision ANNS and MIPS models such as graph-based indexes.
529, Markovian Sliced Wasserstein Distances: Beyond Independent Projections
Khai Nguyen; Tongzheng Ren; Nhat Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To address the problem, we introduce a new family of SW distances, named Markovian sliced Wasserstein (MSW) distance, which imposes a first-order Markov structure on projecting directions.
530, Energy-Based Sliced Wasserstein Distance
Khai Nguyen; Nhat Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To address the issues, we propose to design the slicing distribution as an energy-based distribution that is parameter-free and has the density proportional to an energy function of the projected one-dimensional Wasserstein distance.
531, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Yuchao Gu; Xintao Wang; Jay Zhangjie Wu; Yujun Shi; Yunpeng Chen; Zihan Fan; WUYOU XIAO; Rui Zhao; Shuning Chang; 威佳 吴; Yixiao Ge; Ying Shan; Mike Zheng Shou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion.
532, BIOT: Biosignal Transformer for Cross-data Learning in The Wild
Chaoqi Yang; M Westover; Jimeng Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To overcome the unique challenges associated with biosignals of various formats, such as mismatched channels, variable sample lengths, and prevalent missing values, we propose a Biosignal Transformer (BIOT).
533, Concept Algebra for Score-based Conditional Model
Zihao Wang; Lin Gui; Jeffrey Negrea; Victor Veitch;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper concerns the structure of learned representations in text-guided generative models, focusing on score-based models.
534, Restart Sampling for Improving Generative Processes
Yilun Xu; Mingyang Deng; Xiang Cheng; Yonglong Tian; Ziming Liu; Tommi Jaakkola;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We attribute this difference to sampling errors: ODE-samplers involve smaller discretization errors while stochasticity in SDE contracts accumulated errors. Based on these findings, we propose a novel sampling algorithm called *Restart* in order to better balance discretization errors and contraction.
535, Towards Better Dynamic Graph Learning: New Architecture and Unified Library
Le Yu; Leilei Sun; Bowen Du; Weifeng Lv;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose DyGFormer, a new Transformer-based architecture for dynamic graph learning.
536, Stability and Generalization of The Decentralized Stochastic Gradient Descent Ascent Algorithm
Miaoxi Zhu; Li Shen; Bo Du; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the primal-dual generalization bound of the decentralized stochastic gradient descent ascent (D-SGDA) algorithm using the approach of algorithmic stability under both convex-concave and nonconvex-nonconcave settings.
537, Domain Re-Modulation for Few-Shot Generative Domain Adaptation
Yi Wu; Ziqiang Li; Chaoyue Wang; Heliang Zheng; Shanshan Zhao; Bin Li; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we investigate the task of few-shot Generative Domain Adaptation (GDA), which involves transferring a pre-trained generator from one domain to a new domain using a few reference images.
538, VanillaNet: The Power of Minimalism in Deep Learning
Hanting Chen; Yunhe Wang; Jianyuan Guo; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this study, we introduce VanillaNet, a neural network architecture that embraces elegance in design.
539, ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding
Lunhao Duan; Shanshan Zhao; Nan Xue; Mingming Gong; Gui-Song Xia; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we attempt to reduce the costs and model the local geometry prior by developing a new transformer block, named ConDaFormer.
540, Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning
Guozheng Ma; Linrui Zhang; Haoyu Wang; Lu Li; Zilin Wang; Zhen Wang; Li Shen; Xueqian Wang; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To investigate this issue and further explore the potential of DA, this work conducts comprehensive experiments to assess the impact of DA's attributes on its efficacy and provides the following insights and improvements: (1) For individual DA operations, we reveal that both ample spatial diversity and slight hardness are indispensable. Building on this finding, we introduce Random PadResize (Rand PR), a new DA operation that offers abundant spatial diversity with minimal hardness.
541, Understanding How Consistency Works in Federated Learning Via Stage-wise Relaxed Initialization
Yan Sun; Li Shen; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To alleviate the negative impact of the client drift and explore its substance in FL, in this paper, we first design an efficient FL algorithm FedInit, which allows employing the personalized relaxed initialization state at the beginning of each local training stage.
542, All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation
Liyao Tang; Zhe Chen; Shanshan Zhao; Chaoyue Wang; Dacheng Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly. To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
543, Evaluating Neuron Interpretation Methods of NLP Models
Yimin Fan; Fahim Dalvi; Nadir Durrani; Hassan Sajjad;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The commonly used evaluation metric is suboptimal for several reasons and creating ground truth annotation of neurons is infeasible. In this work, we tackle these challenges and propose an evaluation framework based on the voting theory.
544, Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information
Arman Zharmagambetov; Brandon Amos; Aaron Ferber; Taoan Huang; Bistra Dilkina; Yuandong Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The training is further challenged by sparse gradients of $\mathbf{g}$, especially for combinatorial solvers. To address these challenges, we propose using a smooth and learnable **Landscape Surrogate** $\mathcal{M}$ as a replacement for $f\circ \mathbf{g}$.
545, The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
Saurabh Saxena; Charles Herrmann; Junhwa Hur; Abhishek Kar; Mohammad Norouzi; Deqing Sun; David Fleet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly without task-specific architectures and loss functions that are predominant for these tasks.
546, Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer
Yuandong Tian; Yiping Wang; Beidi Chen; Simon Du;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, with a simple predictive loss, how the representation emerges from the gradient \emph{training dynamics} remains a mystery. In this paper, for 1-layer transformer with one self-attention layer plus one decoder layer, we analyze its SGD training dynamics for the task of next token prediction in a mathematically rigorous manner.
547, Allievating The Semantic Gap for Generalized FMRI-to-Image Reconstruction
Tao Fang; Qian Zheng; Gang Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we leverage the pre-trained CLIP model to map the training data to a compact feature representation, which essentially extends the sparse semantics of training data to dense ones, thus alleviating the semantic gap for instances within known semantic space(i.e., inside the expanded semantic subspace).
548, Robust Learning with Progressive Data Expansion Against Spurious Correlation
Yihe Deng; Yu Yang; Baharan Mirzasoleiman; Quanquan Gu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process. In light of this, we propose a new training algorithm called **PDE** that efficiently enhances the model's robustness for a better worst-group performance.
549, Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving
Xiaoyu Tian; Tao Jiang; Longfei Yun; Yucheng Mao; Huitong Yang; Yue Wang; Yilun Wang; Hang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To support 3D occupancy prediction, we develop a label generation pipeline that produces dense, visibility-aware labels for any given scene.
550, Benchmarking and Analyzing 3D-aware Image Synthesis with A Modularized Codebase
Qiuyu Wang; Zifan Shi; Kecheng Zheng; Yinghao Xu; Sida Peng; Yujun Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Following the most popular and effective paradigm in this field, which incorporates a neural radiance field (NeRF) into the generator of a generative adversarial network (GAN), we builda well-structured codebase through modularizing the generation process. Such a design allows researchers to develop and replace each module independently, and hence offers an opportunity to fairly compare various approaches and recognize their contributions from the module perspective.
551, Online Learning in Multi-unit Auctions with Uniform Pricing
Simina Branzei; Mahsa Derakhshan; Negin Golrezaei; Yanjun Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Both of these rules represent the Walrasian mechanism, where the $K$-th highest bid represents the maximum Walrasian price, while the $(K+1)$-st highest bid represents the minimum Walrasian price. Our contribution is to analyze the bidding strategies and properties of these auctions in both the offline and online settings.
552, Brain Dissection: FMRI-trained Networks Reveal Spatial Selectivity in The Processing of Natural Images
Gabriel Sarch; Michael Tarr; Leila Wehbe; Katerina Fragkiadaki;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we train networks to directly predict, from scratch, brain responses to images from a large-scale dataset of natural scenes.
553, Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment
Yutong Xia; Yuxuan Liang; Haomin Wen; Xu Liu; Kun Wang; Zhengyang Zhou; Roger Zimmermann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Spatio-Temporal Graph Neural Networks have emerged as the most popular method for STG forecasting, but they often struggle with temporal out-of-distribution (OoD) issues and dynamic spatial causation. In this paper, we propose a novel framework called CaST to tackle these two challenges via causal treatments.
554, Weakly-Supervised Audio-Visual Segmentation
Shentong Mo; Bhiksha Raj;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel Weakly-Supervised Audio-Visual Segmentation framework, namely WS-AVS, that can learn multi-scale audio-visual alignment with multi-scale multiple-instance contrastive learning for audio-visual segmentation.
555, DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation
Shentong Mo; Enze Xie; Ruihang Chu; Lanqing Hong; Matthias Niessner; Zhenguo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, it is unclear how the Transformer architecture performs equally well in 3D shape generation, as previous 3D diffusion methods mostly adopted the U-Net architecture. To bridge this gap, we propose a novel Diffusion Transformer for 3D shape generation, named DiT-3D, which can directly operate the denoising process on voxelized point clouds using plain Transformers.
556, Efficiently Incorporating Quintuple Interactions Into Geometric Deep Learning Force Fields
Zun Wang; Guoqing Liu; Yichi Zhou; Tong Wang; Bin Shao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose the quintuple network (QuinNet), an end-to-end graph neural network that efficiently expresses many-body interactions up to five-body interactions with ab initio accuracy.
557, Grammar Prompting for Domain-Specific Language Generation with Large Language Models
Bailin Wang; Zi Wang; Xuezhi Wang; Yuan Cao; Rif A. Saurous; Yoon Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore \emph{grammar prompting} as a simple approach for enabling LLMs to use external knowledge and domain-specific constraints, expressed through a grammar expressed in Backus--Naur Form (BNF), during in-context learning.
558, SituatedGen: Incorporating Geographical and Temporal Contexts Into Generative Commonsense Reasoning
Yunxiang Zhang; Xiaojun Wan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a corresponding English dataset consisting of 8,268 contrastive sentence pairs, which are built upon several existing commonsense reasoning benchmarks with minimal manual labor.
559, Feature Likelihood Score: Evaluating The Generalization of Generative Models Using Samples
Marco Jiralerspong; Joey Bose; Ian Gemp; Chongli Qin; Yoram Bachrach; Gauthier Gidel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current methods for evaluating such models remain incomplete: standard likelihood-based metrics do not always apply and rarely correlate with perceptual fidelity, while sample-based metrics, such as FID, are insensitive to overfitting, i.e., inability to generalize beyond the training set. To address these limitations, we propose a new metric called the Feature Likelihood Score (FLS), a parametric sample-based score that uses density estimation to provide a comprehensive trichotomic evaluation accounting for novelty (i.e., different from the training samples), fidelity, and diversity of generated samples.
560, Learning Regularized Monotone Graphon Mean-Field Games
Fengzhuo Zhang; Vincent Tan; Zhaoran Wang; Zhuoran Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Previous literature either only analyzed continuous-time algorithms or required extra conditions to analyze discrete-time algorithms. In contrast, we design a discrete-time algorithm and derive its convergence rate solely under weakly monotone conditions.
561, RRHF: Rank Responses to Align Language Models with Human Feedback Without Tears
Zheng Yuan; Hongyi Yuan; Chuanqi Tan; Wei Wang; Songfang Huang; Fei Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, PPO is sensitive to hyperparameters and requires a minimum of four models in its standard implementation, making it hard to train and scale up to larger parameter counts. In contrast, we propose a novel learning paradigm called RRHF, which scores sampled responses from different sources via logarithm of conditional probabilities and learns to align these probabilities with human preferences through ranking loss.
562, Masked Two-channel Decoupling Framework for Incomplete Multi-view Weak Multi-label Learning
Chengliang Liu; Jie Wen; Yabo Liu; Chao Huang; Zhihao Wu; Xiaoling Luo; Yong Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Multi-view learning has become a popular research topic in recent years, but research on the cross-application of classic multi-label classification and multi-view learning is still in its early stages. In this paper, we focus on the complex yet highly realistic task of incomplete multi-view weak multi-label learning and propose a masked two-channel decoupling framework based on deep neural networks to solve this problem.
563, LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer
Haoyu Chen; Hao Tang; Radu Timofte; Luc V Gool; Guoying Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel 3D Transformer framework called LART for 3D motion transfer.
564, Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
Lin Guan; Karthik Valmeekam; Sarath Sreedharan; Subbarao Kambhampati;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a novel alternative paradigm that constructs an explicit world (domain) model in planning domain definition language (PDDL) and then uses it to plan with sound domain-independent planners.
565, Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes
Aran Nayebi; Rishi Rajalingham; Mehrdad Jazayeri; Guangyu Robert Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the neural mechanisms underlying these computations are unclear. We combine a goal-driven modeling approach with dense neurophysiological data and high-throughput human behavioral readouts to directly impinge on this question.
566, A Novel Approach for Few-Shot Learning with Kendall's Rank Correlation
Kaipeng Zheng; Huishuai Zhang; Weiran Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we demonstrate that the importance ranking of feature channels is a more reliable indicator for few-shot learning than geometric similarity metrics.
567, Geometric Analysis of Matrix Sensing Over Graphs
Haixiang Zhang; Ying Chen; Javad Lavaei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we consider the problem of matrix sensing over graphs (MSoG).
568, GeoDE: A Geographically Diverse Evaluation Dataset for Object Recognition
Vikram V. Ramaswamy; Sing Yu Lin; Dora Zhao; Aaron Adcock; Laurens van der Maaten; Deepti Ghadiyaram; Olga Russakovsky;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we rethink the dataset collection paradigm and introduce GeoDE, a geographically diverse dataset with 61,940 images from 40 classes and 6 world regions, and no personally identifiable information, collected by soliciting images from people across the world.
569, Similarity-based Cooperative Equilibrium
Caspar Oesterheld; Johannes Treutlein; Roger Grosse; Vincent Conitzer; Jakob Foerster;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, it is challenging for agents to learn their way to cooperation in the full transparency setting. In this paper, we introduce a more realistic setting in which agents only observe a single number indicating how similar they are to each other.
570, Emergent Communication in Interactive Sketch Question Answering
Zixing Lei; Yiming Zhang; Yuxin Xiong; Siheng Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Ironically, previous works neglect multi-round interaction, which is indispensable in human communication. To fill this gap, we first introduce a novel Interactive Sketch Question Answering (ISQA) task, where two collaborative players are interacting through sketches to answer a question about an image.
571, On The Robustness of Distributed Machine Learning with Heterogeneous Data
Youssef Allouah; Rachid Guerraoui; Nirupam Gupta; Rafael Pinot; Geovani Rizk;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider in this paper a more realistic heterogeneity model, namely $(G,B)$-gradient dissimilarity, and show that it covers a larger class of learning problems than existing theory.
572, Feature Decoupling Alignment for Fine-tuning Pre-trained Models in Few-shot Learning
Kun Song; Huimin Ma; Bochao Zou; Huishuai Zhang; Weiran Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces a feature decoupled alignment (FD-Align) fine-tuning approach, aiming to maximize the preservation of category-related information during fine-tuning while retaining category-independent information to maintain the model's generalizability.
573, Provable Guarantees for Neural Networks Via Gradient Feature Learning
Zhenmei Shi; Junyi Wei; Yingyu Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work proposes a unified analysis framework for two-layer networks trained by gradient descent.
574, Second-Order Degradation and Reconstruction for Test-Time Image Super-Resolution
Zeshuai Deng; Zhuokun Chen; Shuaicheng Niu; Thomas Li; Bohan Zhuang; Mingkui Tan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, these methods largely concentrate on the estimation of one degradation type (e.g., blur degradation), overlooking other degradation types like noise and JPEG in the real-world test-time scenario, thus limiting their practicality. To tackle this, we present a fast test-time adaptation framework for SR, named SRTTA, which is able to super-resolve images with various degradation types while maintaining high efficiency.
575, Frequency-domain MLPs Are More Effective Learners in Time Series Forecasting
Kun Yi; Qi Zhang; Wei Fan; Hui He; Pengyang Wang; Shoujin Wang; Ning An; Defu Lian; Longbing Cao; Zhendong Niu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most MLP-based forecasting methods suffer from the point-wise mappings and information bottleneck, which largely hinders the forecasting performance. To overcome this problem, we explore a novel direction of applying MLPs in the frequency domain for time series forecasting.
576, FourierGNN: Rethinking Multivariate Time Series Forecasting from A Pure Graph Perspective
Kun Yi; Qi Zhang; Wei Fan; Hui He; Liang Hu; Pengyang Wang; Ning An; Longbing Cao; Zhendong Niu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the uncertain compatibility of the two networks puts an extra burden on handcrafted model designs. Moreover, the separate spatial and temporal modeling naturally violates the unified spatiotemporal inter-dependencies in real world, which largely hinders the forecasting performance. To overcome these problems, we explore an interesting direction of directly applying graph networks and rethink MTS forecasting from a pure graph perspective.
577, Satisfiability-Aided Language Models Using Declarative Prompting
Xi Ye; Qiaochu Chen; Isil Dillig; Greg Durrett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new satisfiability-aided language modeling (SATLM) approach for improving the reasoning capabilities of LLMs.
578, Semi-Implicit Denoising Diffusion Models (SIDDMs)
yanwu xu; Mingming Gong; Shaoan Xie; Wei Wei; Matthias Grundmann; Kayhan Batmanghelich; Tingbo Hou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, DDGAN encountered scalability limitations when applied to large datasets. To address these limitations, we introduce a novel approach that tackles the problem by matching implicit and explicit factors.
579, Learning Modulated Transformation in GANs
Ceyuan Yang; Qihang Zhang; Yinghao Xu; Jiapeng Zhu; Yujun Shen; Bo Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the instance-wise stochasticity is typically introduced via regular convolution, where kernels interact with features at some $\textit{fixed}$ locations, limiting its capacity for modeling geometric variation. To alleviate this problem, we equip the generator in generative adversarial networks (GANs) with a plug-and-play module, termed as modulated transformation module ($\texttt{MTM}$).
580, Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
Shihao Zhao; Dongdong Chen; Yen-Chun Chen; Jianmin Bao; Shaozhe Hao; Lu Yuan; Kwan-Yee K. Wong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce Uni-ControlNet, a novel approach that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one model.
581, Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference
Ran Ran; Nuo Xu; Tao Liu; Wei Wang; Gang Quan; Wujie Wen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a result, in this paper, we propose a novel HE-based ciphertext packing technique, i.e., Penguin, that can take advantage of the unique computation pattern during the HE-GCN inference to significantly reduce the computation and memory overhead associated with HE operations.
582, BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
Subhro Roy; Samuel Thomson; Tongfei Chen; Richard Shin; Adam Pauls; Jason Eisner; Benjamin Van Durme;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent work has shown that generation from a prompted or fine-tuned language model can perform well at semantic parsing when the output is constrained to be a valid semantic representation. We introduce BenchCLAMP, a Benchmark to evaluate Constrained LAnguage Model Parsing, that includes context-free grammars for seven semantic parsing datasets and two syntactic parsing datasets with varied output meaning representations, as well as a constrained decoding interface to generate only valid outputs covered by these grammars.
583, MultiVENT: Multilingual Videos of Events and Aligned Natural Text
Kate Sanders; David Etter; Reno Kriz; Benjamin Van Durme;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Datasets that reflect the diverse array of multimodal, multilingual news sources available online could be used to teach models to benefit from this shift, but existing news video datasets focus on traditional news broadcasts produced for English-speaking audiences. We address this limitation by constructing MultiVENT, a dataset of multilingual, event-centric videos grounded in text documents across five target languages.
584, GraphACL: Simple Asymmetric Contrastive Learning of Graphs
Teng Xiao; Huaisheng Zhu; Zhengyu Chen; Suhang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the problem of effectively conducting contrastive learning on both homophilic and heterophilic graphs.
585, Certifiably Robust Graph Contrastive Learning
Minhua Lin; Teng Xiao; Enyan Dai; Xiang Zhang; Suhang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we develop the first certifiably robust framework in GCL.
586, S-CLIP: Semi-supervised Vision-Language Pre-training Using Few Specialist Captions
Sangwoo Mo; Minkyu Kim; Kyungmin Lee; Jinwoo Shin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these models often struggle when applied to specialized domains like remote sensing, and adapting to such domains is challenging due to the limited number of image-text pairs available for training. To address this, we propose S-CLIP, a semi-supervised learning method for training CLIP that utilizes additional unpaired images.
587, Collaborative Score Distillation for Consistent Visual Synthesis
Subin Kim; Kyungmin Lee; June Suk Choi; Jongheon Jeong; Kihyuk Sohn; Jinwoo Shin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, when adapting these priors to complex visual modalities, often represented as multiple images (e.g., video), achieving consistency across a set of images is challenging. In this paper, we address this challenge with a novel method, Collaborative Score Distillation (CSD).
588, Decomposition Enhances Reasoning Via Self-Evaluation Guided Decoding
Yuxi Xie; Kenji Kawaguchi; Yiran Zhao; James Xu Zhao; Min-Yen Kan; Junxian He; Michael Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an effective prompting approach that integrates self-evaluation guidance through stochastic beam search.
589, Reconciling Competing Sampling Strategies of Network Embedding
Yuchen Yan; Baoyu Jing; Lihui Liu; Ruijie Wang; Jinning Li; Tarek Abdelzaher; Hanghang Tong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, under different or even competing sampling strategies, some methods champion sampling distant node pairs as positive samples to encapsulate longer distance information in link prediction, whereas others advocate adding close nodes into the negative sample set to boost the performance of node recommendation. In this paper, we seek to understand the intrinsic relationships between these competing strategies.
590, On The Exploitability of Instruction Tuning
Manli Shu; Jiongxiao Wang; Jonas Geiping; Chaowei Xiao; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into the training data that intentionally changes the model's behavior.
591, BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information
Mehran Kazemi; Quan Yuan; Deepti Bhatia; Najoung Kim; Xin Xu; Vaiva Imbrasaite; Deepak Ramachandran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One widely-applicable way of resolving conflicts is to impose preferences over information sources (e.g., based on source credibility or information recency) and adopt the source with higher preference. In this paper, we formulate the problem of reasoning with contradictory information guided by preferences over sources as the classical problem of defeasible reasoning, and develop a dataset called BoardgameQA for measuring the reasoning capacity of LMs in this setting.
592, Taming Local Effects in Graph-based Spatiotemporal Forecasting
Andrea Cini; Ivan Marisca; Daniele Zambon; Cesare Alippi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the gain achieved in computational and data efficiency w.r.t. fitting a set of local models, relying on a single global model can be a limitation whenever some of the time series are generated by a different spatiotemporal stochastic process. The main objective of this paper is to understand the interplay between globality and locality in graph-based spatiotemporal forecasting, while contextually proposing a methodological framework to rationalize the practice of including trainable node embeddings in such architectures.
593, Sparse Graph Learning from Spatiotemporal Time Series
Andrea Cini; Daniele Zambon; Cesare Alippi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose novel, principled - yet practical - probabilistic score-based methods that learn the relational dependencies as distributions over graphs while maximizing end-to-end the performance at task.
594, Correlation Aware Distributed Vector Mean Estimation
Shuli Jiang; PRANAY SHARMA; Gauri Joshi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the Rand-Proj-Spatial estimator with a more flexible encoding-decoding procedure, which generalizes the encoding of Rand-$k$ by projecting the client vectors to a random $k$-dimensional subspace.
595, DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
Lazar Atanackovic; Alexander Tong; Jason Hartford; Leo J Lee; Bo Wang; Yoshua Bengio;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper we leverage the fact that it is possible to estimate the ``velocity'' of the expression of a gene with RNA velocity techniques to develop an approach that addresses both challenges.
596, End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics
Alexander Shmakov; Kevin Greif; Michael Fenton; Aishik Ghosh; Pierre Baldi; Daniel Whiteson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel unified architecture, termed latent variation diffusion models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework.
597, NAP: Neural 3D Articulation Prior
Jiahui Lei; Congyue Deng; William B Shen; Leonidas Guibas; Kostas Daniilidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models.
598, A Deep Instance Generative Framework For MILP Solvers Under Limited Data Availability
Zijie Geng; Jie Wang; Xijun Li; Xiao Li; Yongdong Zhang; Feng Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing methods either rely heavily on expert-designed formulations or struggle to capture the rich features of real-world instances. To tackle this problem, we propose G2MILP, which to the best of our knowledge is *the first* deep generative framework for MILP instances.
599, Spiking PointNet: Spiking Neural Networks for Point Clouds
Dayong Ren; Zhe Ma; Yuanpei Chen; Weihang Peng; Xiaode Liu; Yuhan Zhang; Yufei Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we present Spiking PointNet in the paper, the first spiking neural model for efficient deep learning on point clouds.
600, SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Benjamin Ellis; Jonathan Cook; Skander Moalla; Mikayel Samvelyan; Mingfei Sun; Anuj Mahajan; Jakob Foerster; Shimon Whiteson;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we conduct new analysis demonstrating that SMAC lacks the stochasticity and partial observability to require complex *closed-loop* policies.
601, Learning Large Graph Property Prediction Via Graph Segment Training
Kaidi Cao; Phitchaya Phothilimtha; Sami Abu-El-Haija; Dustin Zelle; Yanqi Zhou; Charith Mendis; Jure Leskovec; Bryan Perozzi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer approach to allow learning large graph property prediction with a constant memory footprint.
602, On The Convergence of No-Regret Learning Dynamics in Time-Varying Games
Ioannis Anagnostides; Ioannis Panageas; Gabriele Farina; Tuomas Sandholm;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we characterize the convergence of optimistic gradient descent (OGD) in time-varying games.
603, On The Convergence and Welfare of Learning Algorithms in Smooth Games
Ioannis Anagnostides; Tuomas Sandholm;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Nevertheless, we show that when (approximate) full efficiency can be guaranteed via a smoothness argument \`a la Roughgarden, Nash equilibria are approachable under a family of no-regret learning algorithms, thereby guaranteeing fast and decentralized computation.
604, DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
Mohammadreza Pourreza; Davood Rafiei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance.
605, From Trainable Negative Depth to Edge Heterophily in Graphs
Yuchen Yan; Yuzhong Chen; Huiyuan Chen; Minghua Xu; Mahashweta Das; Hao Yang; Hanghang Tong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: An interesting question is whether breaking the constraint of $\mathbb{N}+$ by making $d$ a real number ($d \in \mathbb{R}$) can bring new insights into graph learning mechanisms. In this work, by redefining GCN's depth $d$ as a trainable parameter continuously adjustable within $(-\infty,+\infty)$, we open a new door of controlling its signal processing capability to model graph homophily/heterophily (nodes with similar/dissimilar labels/attributes tend to be inter-connected).
606, Multi-timescale Adaptive Whitening in Neural Circuits with Synaptic Plasticity and Gain-modulation
Lyndon Duong; Eero Simoncelli; Dmitri Chklovskii; David Lipshutz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing mechanistic models of adaptive whitening exclusively use either synaptic plasticity or gain modulation as the biological substrate for adaptation; however, on their own, each of these models has significant limitations. In this work, we unify these approaches in a normative multi-timescale mechanistic model that adaptively whitens its responses with complementary computational roles for synaptic plasticity and gain modulation.
607, What’s Left: Concept Grounding with Large Language Models
Joy Hsu; Jiayuan Mao; Josh Tenenbaum; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Neuro-FOL, a unified concept learning and reasoning framework that flexibly learns concepts across domains and reasons across unseen tasks.
608, Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
Tiancheng Jin; Junyan Liu; Haipeng Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recently, Ito [2021] took the first step to remove such an undesirable uniqueness assumption for one particular FTRL algorithm withthe 1/2-Tsallis entropy regularizer. In this work, we significantly improve and generalize this result, showing that uniqueness is unnecessary for FTRL with a broad family of regularizers and a new learning rate schedule.
609, Replicable Reinforcement Learning
Eric Eaton; Marcel Hussing; Michael Kearns; Jessica Sorrell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we initiate the study of replicable reinforcement learning, providing a provably replicable algorithm for parallel value iteration, and a provably replicable version of R-Max in the episodic setting.
610, QuIP: 2-Bit Quantization of Large Language Models With Guarantees
Jerry Chee; Yaohui Cai; Volodymyr Kuleshov; Christopher De Sa;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work studies post-training parameter quantization in large language models (LLMs). We introduce quantization with incoherence processing (QuIP), a new method based on the insight that quantization benefits from *incoherent* weight and Hessian matrices, i.e., from the weights and the directions in which it is important to round them accurately being unaligned with the coordinate axes.
611, Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
Fuyuan Lyu; Xing Tang; Dugang Liu; Chen Ma; Weihong Luo; xiuqiang He; Xue (Steve) Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce a hybrid-grained feature interaction selection approach that targets both feature field and feature value for deep sparse networks.
612, Balanced Training for Sparse GANs
Yite Wang; Jing Wu; NAIRA HOVAKIMYAN; Ruoyu Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel metric called the balance ratio (BR) to study the balance between the sparse generator and discriminator.
613, Retrieval-Augmented Multiple Instance Learning
Yufei CUI; Ziquan Liu; Yixin Chen; Yuchen Lu; Xinyue Yu; Xue (Steve) Liu; Tei-Wei Kuo; Miguel Rodrigues; Chun Jason XUE; Antoni Chan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this paper reveals a performance deterioration of MIL models when tested on an out-of-domain test set, exemplified by WSIs sourced from a novel hospital. To address this challenge, this paper introduces the Retrieval-AugMented MIL (RAM-MIL) framework, which integrates Optimal Transport (OT) as the distance metric for nearest neighbor retrieval.
614, Relative Entropic Optimal Transport: A (Prior-aware) Matching Perspective to (Unbalanced) Classification
Liangliang Shi; Haoyu Zhen; Gu Zhang; Junchi Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Departure from the Bayesian framework, this paper rethinks classification from a matching perspective by studying the matching probability between samples and labels with optimal transport (OT) formulation.
615, From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization
Yang Li; Jinpei Guo; Runzhong Wang; Junchi Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose T2TCO (Training to Testing) framework that first leverages the generative modeling to estimate the high-quality solution distribution for each instance during training, and then conducts a gradient-based search within the solution space during testing.
616, HubRouter: Learning Global Routing Via Hub Generation and Pin-hub Connection
Xingbo Du; Chonghua Wang; Ruizhe Zhong; Junchi Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, we propose a novel definition, called hub, which represents the key point in the route.
617, Generalized Information-theoretic Multi-view Clustering
Weitian Huang; Sirui Yang; Hongmin Cai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we reformulate the multi-view clustering problem from an information-theoretic perspective and propose a general theoretical framework.
618, H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection
Yi Yu; Xue Yang; Qingyun Li; Yue Zhou; Feipeng Da; Junchi Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents H2RBox-v2, to further bridge the gap between HBox-supervised and RBox-supervised oriented object detection.
619, Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality
Liyuan Wang; Jingyi Xie; Xingxing Zhang; Mingyi Huang; Hang Su; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To overcome these sub-optimality, we conduct a theoretical analysis of the continual learning objective in the context of pre-training and decompose it into hierarchical components: within-task prediction, task-identity inference, and task-adaptive prediction. Following such empirical and theoretical insights, we propose Hierarchical Decomposition (HiDe-)Prompt, an innovative approach that explicitly optimizes the hierarchical components with an ensemble of task-specific prompts and statistics of both uninstructed and instructed representations, further with the coordination of a contrastive regularization strategy.
620, Propagating Knowledge Updates to LMs Through Distillation
Shankar Padmanabhan; Yasumasa Onoe; Michael Zhang; Greg Durrett; Eunsol Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we demonstrate that a context distillation-based approach can both impart knowledge about entities \emph{and} propagate that knowledge to enable broader inferences.
621, Syntactic Binding in Diffusion Models: Enhancing Attribute Correspondence Through Attention Map Alignment
Royi Rassin; Eran Hirsch; Daniel Glickman; Shauli Ravfogel; Yoav Goldberg; Gal Chechik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As one notable example, a query like ``a yellow tomato and a red lemon'' may incorrectly produce an image of a yellow lemon and a red tomato. To remedy this issue, we propose SynGen, an approach which first syntactically analyses the prompt to identify entities and their modifiers, and then uses a novel loss function that encourages the cross-attention maps to agree with the linguistic binding reflected by the syntax.
622, Hierarchical Open-vocabulary Universal Image Segmentation
Xudong Wang; Shufan Li; Konstantinos Kallidromitis; Yusuke Kato; Kazuki Kozuka; Trevor Darrell;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a decoupled text-image fusion mechanism and representation learning modules for both “things” and “stuff”.
623, Differentially Private Image Classification By Learning Priors from Random Processes
Xinyu Tang; Ashwinee Panda; Vikash Sehwag; Prateek Mittal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: A recent focus in private learning research is improving the performance of DP-SGD on private data by incorporating priors that are learned on real-world public data. In this work, we explore how we can improve the privacy-utility tradeoff of DP-SGD by learning priors from images generated by random processes and transferring these priors to private data.
624, Characterizing The Optimal $0-1$ Loss for Multi-class Classification with A Test-time Attacker
Sihui Dai; Wenxin Ding; Arjun Nitin Bhagoji; Daniel Cullina; Heather Zheng; Ben Zhao; Prateek Mittal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we find achievable information-theoretic lower bounds onrobust loss in the presence of a test-time attacker for *multi-classclassifiers on any discrete dataset*.
625, ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
Zhengyi Wang; Cheng Lu; Yikai Wang; Fan Bao; Chongxuan LI; Hang Su; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose to model the 3D parameter as a random variable instead of a constant as in SDS and present *variational score distillation* (VSD), a principled particle-based variational framework to explain and address the aforementioned issues in text-to-3D generation.
626, Intriguing Properties of Quantization at Scale
Arash Ahmadian; Saurabh Dash; Hongyu Chen; Bharat Venkitesh; Zhen Stephen Gou; Phil Blunsom; Ahmet Üstün; Sara Hooker;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we ask _are quantization cliffs in performance solely a factor of scale?
627, The Grand Illusion: The Myth of Software Portability and Implications for ML Progress
Fraser Mince; Dzung Dinh; Jonas Kgomo; Neil Thompson; Sara Hooker;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we ask: How portable are popular ML software frameworks?
628, Rank-DETR for High Quality Object Detection
Yifan Pu; Weicong Liang; Yiduo Hao; YUHUI YUAN; Yukang Yang; Chao Zhang; Han Hu; Gao Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce a simple highly performant DETR-based object detector by proposing a set of rank-oriented designs, collectively called Rank-DETR.
629, MarioGPT: Open-Ended Text2Level Generation Through Large Language Models
Shyam Sudhakaran; Miguel González-Duque; Claire Glanois; Matthias Freiberger; Elias Najarro; Sebastian Risi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce MarioGPT, a fine-tuned GPT2 model trained to generate tile-based game levels, in our case Super Mario Bros levels.
630, Optimistic Meta-Gradients
Sebastian Flennerhag; Tom Zahavy; Brendan O'Donoghue; Hado van Hasselt; András György; Satinder Singh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the connection between gradient-based meta-learning and convex optimisation.
631, Offline Goal-Conditioned RL with Latent States As Actions
Seohong Park; Dibya Ghosh; Benjamin Eysenbach; Sergey Levine;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Importantly, it is easier to assess the effect of actions on getting to these closer states. Based on this idea, we propose a hierarchical algorithm for goal-conditioned RL from offline data.
632, Goal Driven Discovery of Distributional Differences Via Language Descriptions
Ruiqi Zhong; Peter Zhang; Steve Li; Jinwoo Ahn; Dan Klein; Jacob Steinhardt;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We build a D5 system, and to quantitatively evaluate its performance, we 1) build a diagnostic benchmark, SynD5, to test whether it can recover known differences between two synthetic corpora, and 2) contribute a meta-dataset, OpenD5, aggregating 675 open-ended problems ranging across business, social sciences, humanities, machine learning, and health. With both synthetic and real datasets, we confirm that language models can leverage the user-specified goals to propose more relevant candidate discoveries, and they sometimes produce discoveries previously unknown to the authors, including demographic differences in discussion topics, political stances in speech, insights in commercial reviews, and error patterns in NLP models.
633, Bootstrapping Vision-Language Learning with Decoupled Language Pre-training
Yiren Jian; Chongyang Gao; Soroush Vosoughi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a novel methodology aimed at optimizing the application of frozen large language models (LLMs) for resource-intensive vision-language (VL) pre-training.
634, PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning
Florian Bordes; Shashank Shekhar; Mark Ibrahim; Diane Bouchacourt; Pascal Vincent; Ari Morcos;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present a path to democratize the use of photorealistic synthetic data: we develop a new generation of interactive environments for representation learning research, that offer both controllability and realism.
635, CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
Jiwen Yu; Xuanyu Zhang; Youmin Xu; Jian Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In summary, we propose a novel image steganography framework, named Controllable, Robust and Secure Image Steganography (CRoSS), which has significant advantages in controllability, robustness, and security compared to cover-based image steganography methods.
636, A General Framework for Robust G-Invariance in G-Equivariant Networks
Sophia Sanborn; Nina Miolane;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a general method for achieving robust group-invariance in group-equivariant convolutional neural networks ($G$-CNNs), which we call the $G$-triple-correlation ($G$-TC) layer.
637, Prototypical Variational Autoencoder for 3D Few-shot Object Detection
Weiliang Tang; Biqi YANG; Xianzhi Li; Yun-Hui Liu; Pheng-Ann Heng; Chi-Wing Fu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Considering that the detection performance highly relies on the quality of the latent features, we design a VAE-based prototype learning scheme, named prototypical VAE (P-VAE), to learn a probabilistic latent space for enhancing the diversity and distinctiveness of the sampled features.
638, Self-Supervised Reinforcement Learning That Transfers Using Random Features
Boyuan Chen; Chuning Zhu; Pulkit Agrawal; Kaiqing Zhang; Abhishek Gupta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To get the best of both worlds, we propose a self-supervised reinforcement learning method that enables the transfer of behaviors across tasks with different rewards, while circumventing the challenges of model-based RL.
639, American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers
Melissa Dell; Jacob Carlson; Tom Bryan; Emily Silcock; Abhishek Arora; Zejiang Shen; Luca D'Amico-Wong; Quan Le; Pablo Querubin; Leander Heldring;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This study develops a novel, deep learning pipeline for extracting full article texts from newspaper images and applies it to the nearly 20 million scans in Library of Congress's public domain Chronicling America collection.
640, A Massive Scale Semantic Similarity Dataset of Historical English
Emily Silcock; Melissa Dell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study utilizes a novel source, newly digitized articles from off-copyright, local U.S. newspapers, to assemble a massive-scale semantic similarity dataset spanning 70 years from 1920 to 1989 and containing nearly 400M positive semantic similarity pairs.
641, Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
Fei Zhang; Tianfei Zhou; Boyang Li; Hao He; Chaofan Ma; Tianjiao Zhang; Jiangchao Yao; Ya Zhang; Yanfeng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, this paper proposes the non-learnable prototypical regularization (NPR) where non-learnable prototypes are estimated from source features to serve as supervision and enable contrastive matching of the group tokens.
642, Towards Label Position Bias in Graph Neural Networks
Haoyu Han; Xiaorui Liu; Feng Shi; MohamadAli Torkamani; Charu Aggarwal; Jiliang Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we uncover a new bias - label position bias, which indicates that the node closer to the labeled nodes tends to perform better.
643, Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
Haitao Mao; Zhikai Chen; Wei Jin; Haoyu Han; Yao Ma; Tong Zhao; Neil Shah; Jiliang Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In the present study, we provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes within homophilic graphs and heterophilic nodes within heterophilic graphs while struggling on the opposite node set, exhibiting a performance disparity.
644, Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval
Shijie Wang; Jianlong Chang; Haojie Li; Zhihui Wang; Wanli Ouyang; Qi Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel Visual Attribute Parameterization Network (VAPNet) to learn visual attributes from known categories and parameterize them into the retrieval model, without the involvement of any attribute annotations.
645, AiluRus: A Scalable ViT Framework for Dense Prediction
Jin Li; Yaoming Wang; XIAOPENG ZHANG; Bowen Shi; Dongsheng Jiang; Chenglin Li; Wenrui Dai; Hongkai Xiong; Qi Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Notably, dense prediction tasks, such as semantic segmentation or object detection, emphasize more on the contours or shapes of objects, while the texture inside objects is less informative. Motivated by this observation, we propose to apply adaptive resolution for different regions in the image according to their importance.
646, Mode Approximation Makes Good Multimodal Prompts
Haixin Wang; Xinlong Yang; Jianlong Chang; Dian Jin; Jinan Sun; Shikun Zhang; Xiao Luo; Qi Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, two critical issues remain unresolved: how to further reduce the complexity with lightweight design and how to boost alignment between modalities under extremely low parameters. In this paper, we propose A graceful prompt framework for cross-modal transfer (Aurora) to overcome these challenges.
647, Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
Qizhang Li; Yiwen Guo; Wangmeng Zuo; Hao Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, we establish a transfer-based attack benchmark (TA-Bench) which implements 30+ methods. In this paper, we evaluate and compare them comprehensively on 10 popular substitute/victim models on ImageNet.
648, ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training
Antonio Norelli; Marco Fumero; Valentino Maiorca; Luca Moschella; Emanuele Rodolà; Francesco Locatello;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we show that a common space can be created without any training at all, using single-domain encoders (trained with or without supervision) and a much smaller amount of image-text pairs.
649, Improving Adversarial Transferability Via Intermediate-level Perturbation Decay
Qizhang Li; Yiwen Guo; Wangmeng Zuo; Hao Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing methods in this category are normally formulated with two separate stages, where a directional guide is required to be determined at first and the scalar projection of the intermediate-level perturbation onto the directional guide is enlarged thereafter. The obtained perturbation deviates from the guide inevitably in the feature space, and it is revealed in this paper that such a deviation may lead to sub-optimal attack. To address this issue, we develop a novel intermediate-level method that crafts adversarial examples within a single stage of optimization.
650, Adaptive Test-Time Personalization for Federated Learning
Wenxuan Bao; Tianxin Wei; Haohan Wang; Jingrui He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce a novel setting called test-time personalized federated learning (TTPFL), where clients locally adapt a global model in an unsupervised way without relying on any labeled data.
651, Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations
Minshuo Chen; Yu Bai; H. Vincent Poor; Mengdi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces a theoretical investigation into efficient RL in control systems where agents must act with delayed and missing state observations.
652, Parallel Sampling of Diffusion Models
Andy Shih; Suneel Belkhale; Stefano Ermon; Dorsa Sadigh; Nima Anari;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In spite of the sequential nature of the denoising steps, we show that surprisingly it is possible to parallelize sampling via Picard iterations, by guessing the solution of future denoising steps and iteratively refining until convergence. With this insight, we present ParaDiGMS, a novel method to accelerate the sampling of pretrained diffusion models by denoising multiple steps in parallel.
653, Leveraging Sparse and Shared Feature Activations for Disentangled Representation Learning
Marco Fumero; Florian Wenzel; Luca Zancato; Alessandro Achille; Emanuele Rodolà; Stefano Soatto; Bernhard Schölkopf; Francesco Locatello;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation.
654, Mixup-based Data Augmentation for Differentially Private Learning
Wenxuan Bao; Francesco Pittaluga; Vijay Kumar B G; Vincent Bindschaedler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate why naive applications of multi-sample data augmentation techniques, such as mixup, fail to achieve good performance and propose two novel data augmentation techniques specifically designed for the constraints of differentially privacy learning.
655, LOVM: Language-Only Vision Model Selection
Orr Zohar; Shih-Cheng Huang; Kuan-Chieh Wang; Serena Yeung;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we introduce a new task LOVM: **L**anguage-**O**nly **V**ision **M**odel Selection , where methods are expected to perform both model selection and performance prediction based solely on a text description of the desired downstream application.
656, AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis
Susan Liang; Chao Huang; Yapeng Tian; Anurag Kumar; Chenliang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an acoustic-aware audio generation module that integrates prior knowledge of audio propagation into NeRF, in which we implicitly associate audio generation with the 3D geometry and material properties of a visual environment.
657, Faster Differentially Private Convex Optimization Via Second-Order Methods
Arun Ganesh; Mahdi Haghifam; Thomas Steinke; Abhradeep Guha Thakurta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate the prospect of using the second-order information from the loss function to accelerate DP convex optimization.
658, Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization
Wenzhi Gao; Qi Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that the delayed stochastic subgradient method ($\texttt{DSGD}$) obtains a tighter convergence rate which depends on the expected delay $\bar{\tau}$.
659, CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
Yangruibo Ding; Zijian Wang; Wasi Ahmad; Hantian Ding; Ming Tan; Nihal Jain; Murali Krishna Ramanathan; Ramesh Nallapati; Parminder Bhatia; Dan Roth; Bing Xiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To create examples that strictly require cross-file context to be completed correctly, we propose a simple yet efficient static-analysis-based approach to locate the cross-file context usages in the current file.
660, Is RLHF More Difficult Than Standard RL?
Yuanhao Wang; Qinghua Liu; Chi Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, (1) for preferences that are drawn from reward-based probabilistic models, we reduce the problem to robust reward-based RL that can tolerate small errors in rewards; (2) for general arbitrary preferences where the objective is to find the von Neumann winner, we reduce the problem to multiagent reward-based RL which finds Nash equilibria for factored Markov games under a restricted set of policies.
661, Query-based Temporal Fusion with Explicit Motion for 3D Object Detection
Jinghua Hou; Zhe Liu; dingkang liang; Zhikang Zou; Xiaoqing Ye; Xiang Bai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple and effective Query-based Temporal Fusion Network (QTNet).
662, Connecting Multi-modal Contrastive Representations
Zehan Wang; Yang Zhao; Xize 成; Haifeng Huang; Jiageng Liu; Aoxiong Yin; Li Tang; Linjun Li; Yongqi Wang; Ziang Zhang; Zhou Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper proposes a novel training-efficient method for learning MCR without paired data called Connecting Multi-modal Contrastive Representations (C-MCR).
663, Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks
Haoyi Duan; Yan Xia; Zhou Mingze; Li Tang; Jieming Zhu; Zhou Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This limitation arises due to the introduction of irrelevant modality-specific information during encoding, which adversely affects the performance of downstream tasks. To address this challenge, this paper proposes a novel Dual-Guided Spatial-Channel-Temporal (DG-SCT) attention mechanism.
664, Achieving Cross Modal Generalization with Multimodal Unified Representation
Yan Xia; Hai Huang; Jieming Zhu; Zhou Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces a novel task called Cross Modal Generalization (CMG), which addresses the challenge of learning a unified discrete representation from paired multimodal data during pre-training.
665, Universal Online Learning with Gradual Variations: A Multi-layer Online Ensemble Approach
Yuhu Yan; Peng Zhao; Zhi-Hua Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an online convex optimization method with two different levels of adaptivity.
666, Stochastic Approximation Approaches to Group Distributionally Robust Optimization
Lijun Zhang; Peng Zhao; Tianbao Yang; Zhi-Hua Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Denote by $n_i$ the sample budget for the $i$-th distribution, and assume $n_1 \geq n_2 \geq \cdots \geq n_m$. In the first approach, we incorporate non-uniform sampling into SMD such that the sample budget is satisfied in expectation, and prove the excess risk of the $i$-th distribution decreases at an $O(\sqrt{n_1 \log m}/n_i)$ rate.
667, Dynamic Regret of Adversarial Linear Mixture MDPs
Long-Fei Li; Peng Zhao; Zhi-Hua Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Denote by $d$ the dimension of the feature mapping, $H$ the planning horizon, $S$ the number of states, $K$ the number of episodes and $P_T$ the non-stationary measure, we propose a new algorithm that enjoys an $\tilde{\mathcal{O}}\big(\sqrt{d^2 H^3K} + \sqrt{H^4(K+P_T)(1+P_T)} + \sqrt{S H^4 K}\big)$ dynamic regret.
668, Rehearsal Learning for Avoiding Undesired Future
Tian Qin; Tian-Zuo Wang; Zhi-Hua Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a rehearsal learning framework, in which decisions that can persuasively avoid the happening of undesired outcomes can be found and recommended.
669, On The Gini-impurity Preservation For Privacy Random Forests
XinRan Xie; Man-Jie Yuan; Xuetong Bai; Wei Gao; Zhi-Hua Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work presents a new encryption to preserve data's Gini impurity, which plays a crucial role during the construction of random forests.
670, Explainable and Efficient Randomized Voting Rules
Soroush Ebadian; Aris Filos-Ratsikas; Mohamad Latifian; Nisarg Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the efficiency gains which can be unlocked by using voting rules that add a simple randomization step to a deterministic rule, thereby retaining explainability.
671, R-divergence for Estimating Model-oriented Distribution Discrepancy
Zhilin Zhao; Longbing Cao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Accordingly, for a supervised or unsupervised model, a fundamental question is whether the probability distributions of two given datasets can be treated as identical. Here, we propose R-divergence, which is used to evaluate the model-oriented distribution discrepancy, to address the above question.
672, Adapting Neural Link Predictors for Efficient Complex Query Answering
Erik Arakelyan; Pasquale Minervini; Daniel Daza; Michael Cochez; Isabelle Augenstein;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a result, the information gain offered by complex queries is discarded as a trade-off for computational efficiency. We propose to address these problems via CQD$^{\mathcal{A}}$, a parameter-efficient score *adaptation* model optimised to re-calibrate neural link prediction scores for the complex query answering task.
673, Complex-valued Neurons Can Learn More But Slower Than Real-valued Neurons Via Gradient Descent
Jin-Hui Wu; Shao-Qun Zhang; Yuan Jiang; Zhi-Hua Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite empirical successes, it remains unknown theoretically when and to what extent complex-valued neural networks outperform real-valued ones. We take one step in this direction by comparing the learnability of real-valued neurons and complex-valued neurons via gradient descent.
674, Training Transformers with 4-bit Integers
Haocheng Xi; ChangHao Li; Jianfei Chen; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a training method for transformers with all matrix multiplications implemented with the INT4 arithmetic.
675, GAUCHE: A Library for Gaussian Processes in Chemistry
Ryan-Rhys Griffiths; Leo Klarner; Henry Moss; Aditya Ravuri; Sang Truong; Yuanqi Du; Samuel Stanton; Gary Tom; Bojana Rankovic; Arian Jamasb; Aryan Deshwal; Julius Schwartz; Austin Tripp; Gregory Kell; Simon Frieder; Anthony Bourached; Alex Chan; Jacob Moss; Chengzhi Guo; Johannes Peter Dürholt; Saudamini Chaurasia; Ji Won Park; Felix Strieth-Kalthoff; Alpha Lee; Bingqing Cheng; Alan Aspuru-Guzik; Philippe Schwaller; Jian Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce GAUCHE, a library for GAUssian processes in CHEmistry.
676, Epistemic Neural Networks
Ian Osband; Zheng Wen; Seyed Mohammad Asghari; Vikranth Dwaracherla; MORTEZA IBRAHIMI; Xiuyuan Lu; Benjamin Van Roy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce the epinet: an architecture that can supplement any conventional neural network, including large pretrained models, and can be trained with modest incremental computation to estimate uncertainty.
677, Randomized and Deterministic Maximin-share Approximations for Fractionally Subadditive Valuations
Hannaneh Akrami; Kurt Mehlhorn; Masoud Seddighin; Golnoosh Shahkarami;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a randomized allocation that is $1/4$-$\MMS$ ex-ante and $1/8$-$\MMS$ ex-post for $\XOS$ valuations.
678, Pruning Vs Quantization: Which Is Better?
Andrey Kuzmin; Markus Nagel; Mart van Baalen; Arash Behboodi; Tijmen Blankevoort;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we set out to answer the question of which is better: neural network quantization or pruning?
679, AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution
Fangzhou Luo; Xiaolin Wu; Yanhui Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead of attempting to exhaust all degradation variants in simulation, which is unwieldy and impractical, we propose a novel adversarial neural degradation (AND) model that can, when trained in conjunction with a deep restoration neural network under a minmax criterion, generate a wide range of highly nonlinear complex degradation effects without any explicit supervision.
680, Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in The Wild
Yanhui Guo; Xinxin Zuo; Peng Dai; Juwei Lu; Xiaolin Wu; Li cheng; Youliang Yan; Songcen Xu; Xiaofei Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To advance the field of 3D content creation, we introduce Decorate3D, a novel approach for achieving 3D-consistent mesh decoration.
681, Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets
Zhang-Wei Hong; Aviral Kumar; Sathwik Karnik; Abhishek Bhandwaldar; Akash Srivastava; Joni Pajarinen; Romain Laroche; Abhishek Gupta; Pulkit Agrawal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Indeed, the constraint to align with the data leads the policy to imitate low-performing behaviors predominating the dataset. Our key insight to address this issue is to constrain the policy to the policy that collected the good parts of the dataset rather than all data.
682, Mask Propagation for Efficient Video Semantic Segmentation
Yuetian Weng; Mingfei Han; Haoyu He; Mingjie Li; Lina Yao; Xiaojun Chang; Bohan Zhuang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose an efficient mask propagation framework for VSS, called MPVSS.
683, Harnessing Hard Mixed Samples with Decoupled Regularizer
Zicheng Liu; Siyuan Li; Ge Wang; Lirong Wu; Cheng Tan; Stan Z. Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we thus are not trying to propose a more complicated dynamic mixup policy but rather an efficient mixup objective function with decoupled regularizer, named decoupled mixup (DM).
684, OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Cheng Tan; Siyuan Li; Zhangyang Gao; Wenfei Guan; Zedong Wang; Zicheng Liu; Lirong Wu; Stan Z. Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Without standardization, comparisons can be unfair and insights inconclusive. To address this dilemma, we propose OpenSTL, a comprehensive benchmark for spatio-temporal predictive learning that categorizes prevalent approaches into recurrent-based and recurrent-free models.
685, Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration
Haitao Lin; Yufei Huang; Yunfan Liu; Lirong Wu; Siyuan Li; Zhiyuan Chen; Stan Z. Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In recent years, AI-assisted drug design methods have been proposed to generate molecules given the pockets' structures of target proteins. Most of them are {\em atom-level-based} methods, which consider atoms as basic components and generate atom positions and types. In this way, however, it is hard to generate realistic fragments with complicated structures. To solve this, we propose \textsc{D3FG}, a {\em functional-group-based} diffusion model for pocket-specific molecule generation and elaboration.
686, A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design
Fang Wu; Stan Z. Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a \textbf{h}ierarchical \textbf{t}raining \textbf{p}aradigm (HTP) for the antibody sequence-structure co-design.
687, On The Spectral Bias of Two-layer Linear Networks
Aditya Vardhan Varre; Maria-Luiza Vladarean; Loucas PILLAUD-VIVIEN; Nicolas Flammarion;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper studies the behaviour of two-layer fully connected networks with linear activations trained with gradient flow on the square loss.
688, Graph Convolutional Kernel Machine Versus Graph Convolutional Networks
Zhihao Wu; Zhao Zhang; Jicong Fan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This implies that the complexity of graph data is often limited and shallow models are often sufficient to extract expressive features for various tasks such as node classification. Therefore, in this work, we present a framework called graph convolutional kernel machine (GCKM) for graph-based machine learning.
689, Transferable Adversarial Robustness for Categorical Data Via Universal Robust Embeddings
Klim Kireev; Maksym Andriushchenko; Carmela Troncoso; Nicolas Flammarion;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a method that allows us to train adversarially robust deep networks for tabular data and to transfer this robustness to other classifiers via universal robust embeddings tailored to categorical data.
690, Fully Dynamic $k$-Clustering in $\tilde O(k)$ Update Time
Sayan Bhattacharya; Martin Costa; Silvio Lattanzi; Nikos Parotsidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a $O(1)$-approximate fully dynamic algorithm for the $k$-median and $k$-means problems on metric spaces with amortized update time $\tilde O(k)$ and worst-case query time $\tilde O(k^2)$.
691, A Unified Framework for Rank-based Loss Minimization
Yuze Ge; Rujun Jiang; Rufeng Xiao; Yifan Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce a unified framework for the optimization of rank-based loss through the utilization of a proximal alternating direction method of multipliers.
692, Customizable Image Synthesis with Multiple Subjects
Zhiheng Liu; Yifei Zhang; Yujun Shen; Kecheng Zheng; Kai Zhu; Ruili Feng; Yu Liu; Deli Zhao; Jingren Zhou; Yang Cao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Towards controllable image synthesis with multiple subjects as the constraints, this work studies how to efficiently represent a particular subject as well as how to appropriately compose different subjects.
693, Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models
Simian Luo; Chuanhao Yan; Chenxu Hu; Hang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance.
694, Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification
Qiang Ding; Yixuan Cao; Ping Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by an interesting empirical result that the improvement of the ensemble largely comes from top-ambiguity samples where its member models diverge, we prove that, based on some assumptions, the ensemble has a lower selective risk than the member model for any coverage within a range.
695, Learning to Taste: A Multimodal Wine Dataset
Thoranna Bender; Simon Sørensen; Alireza Kashani; Kristjan Hjorleifsson; Grethe Hyldig; Søren Hauberg; Serge Belongie; Frederik Warburg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a low-dimensional concept embedding algorithm that combines human experience with automatic machine similarity kernels.
696, Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood Vs. Independence Testing
Xiangyu Sun; Oliver Schulte;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our analysis shows that the failure occurs mainly when the conditional variance in the anti-causal direction is smaller than that in the causal direction.
697, SHOT: Suppressing The Hessian Along The Optimization Trajectory for Gradient-Based Meta-Learning
JunHoo Lee; Jayeon Yoo; Nojun Kwak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we hypothesize that gradient-based meta-learning (GBML) implicitly suppresses the Hessian along the optimization trajectory in the inner loop.
698, Private Distribution Learning with Public Data: The View from Sample Compression
Shai Ben-David; Alex Bie; Clément L Canonne; Gautam Kamath; Vikrant Singhal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of private distribution learning with access to public data.
699, Online Map Vectorization for Autonomous Driving: A Rasterization Perspective
Gongjie Zhang; Jiahao Lin; Shuang Wu; yilin song; Zhipeng Luo; Yang Xue; Shijian Lu; Zuoguan Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, current map vectorization methods often exhibit deviations, and the existing evaluation metric for map vectorization lacks sufficient sensitivity to detect these deviations. To address these limitations, we propose integrating the philosophy of rasterization into map vectorization.
700, Federated Multi-Objective Learning
Haibo Yang; Zhuqing Liu; Jia Liu; Chaosheng Dong; Michinari Momma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Notably, our FMOL framework allows a different set of objective functions across different clients to support a wide range of applications, which advances and generalizes the MOO formulation to the federated learning paradigm for the first time. For this FMOL framework, we propose two new federated multi-objective optimization (FMOO) algorithms called federated multi-gradient descent averaging (FMGDA) and federated stochastic multi-gradient descent averaging (FSMGDA).
701, A Self-Balanced Co-Advice Contrastive Framework for Long-Tailed Open-World Classification
Jianhong Bai; Zuozhu Liu; Hualiang Wang; Ruizhe Chen; Lianrui Mu; Xiaomeng Li; Joey Tianyi Zhou; YANG FENG; Jian Wu; Haoji Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we formally define a more realistic task as long-tailed open-world classification (LT-OPC): generating fine-grained predictions for both close- and open-set classes in a long-tailed open-world setting.
702, A Unified Framework for Inference-Stage Backdoor Defenses
Xun Xian; Ganghua Wang; Jayanth Srinivasa; Ashish Kundu; Xuan Bi; Mingyi Hong; Jie Ding;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we devise a unified inference-stage detection framework to defend against backdoor attacks.
703, Learning Human Action Recognition Representations Without Real Humans
Howard Zhong; Samarth Mishra; Donghyun Kim; SouYoung Jin; Rameswar Panda; Hilde Kuehne; Leonid Karlinsky; Venkatesh Saligrama; Aude Oliva; Rogerio Feris;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: On the other hand, analysis on the {\em transferability} of privacy-preserving pre-trained models to downstream tasks has been limited. In this work, we study this problem by first asking the question: can we pre-train models for human action recognition with data that does not include real humans?
704, Unleashing The Power of Randomization in Auditing Differentially Private ML
Krishna Pillutla; Galen Andrew; Peter Kairouz; H. Brendan McMahan; Alina Oprea; Sewoong Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a rigorous methodology for auditing differentially private machine learning by adding multiple carefully designed examples called canaries.
705, Koopman Kernel Regression
Petar Bevanda; Max Beier; Armin Lederer; Stefan Sosnowski; Eyke Hüllermeier; Sandra Hirche;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While there exists a variety of approaches, they usually lack crucial learning-theoretic guarantees, such that the behavior of the obtained models with increasing data and dimensionality is often unclear. We address the aforementioned by deriving a novel reproducing kernel Hilbert space (RKHS) that solely spans transformations into linear dynamical systems.
706, Differentiable Sampling of Categorical Distributions Using The CatLog-Derivative Trick
Lennert De Smet; Emanuele Sansone; Pedro Zuidberg Dos Martires;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our first contribution addresses this shortcoming by introducing the CatLog-Derivative trick -- a variation of the Log-Derivative trick tailored towards categorical distributions. Secondly, we use the CatLog-Derivative trick to introduce IndeCateR, a novel and unbiased gradient estimator for the important case of products of independent categorical distributions with provably lower variance than REINFORCE.
707, Rethinking Conditional Diffusion Sampling with Progressive Guidance
Anh-Dung Dinh; Daochang Liu; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a generalized classifier guidance method called Progressive Guidance, which mitigates the problems by allowing relevant classes' gradients to contribute to shared information construction when the image is noisy in early sampling steps.
708, Adaptive Privacy Composition for Accuracy-first Mechanisms
Ryan Rogers; Gennady Samorodnitsk; Steven Wu; Aaditya Ramdas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop privacy filters that allow an analyst to adaptively switch between differentially private mechanisms and ex-post private mechanisms subject to an overall privacy loss guarantee.
709, BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
Zelin Ni; Hang Yu; Shizhan Liu; Jianguo Li; Weiyao Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current state-of-the-art methods are limited in their ability to satisfy both of these requirements simultaneously. To address this challenge, we propose BasisFormer, an end-to-end time series forecasting architecture that leverages learnable and interpretable bases.
710, Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation
Susung Hong; Donghoon Ahn; Seungryong Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem---the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation.
711, GPT4Tools: Teaching Large Language Model to Use Tools Via Self-instruction
Rui Yang; Lin Song; Yanwei Li; Sijie Zhao; Yixiao Ge; Xiu Li; Ying Shan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper aims to efficiently enable Large Language Models (LLMs) to use multi-modal tools.
712, Nash Regret Guarantees for Linear Bandits
Ayush Sawarni; Soumyabrata Pal; Siddharth Barman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the stochastic linear bandits problem over a horizon of $\mathsf{T}$ rounds and with a set of arms ${\cal X}$ in ambient dimension $d$.
713, Fixing Unsupervised Depth Estimation for Dynamical Scenes
Yihong Sun; Bharath Hariharan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This ambiguity causes depth estimators to predict erroneous depth for moving objects. To resolve this issue, we present an unifying approach for jointly learning the estimation of monocular depth, 3D independent flow field, and motion segmentation from unlabeled monocular videos.
714, ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers
Kexun Zhang; Danqing Wang; Jingtao Xia; William Yang Wang; Lei Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Moreover, LLM-generated programs lack guaranteed correctness and require human verification. To address these challenges, we propose ALGO, a framework that synthesizes **A**lgorithmic programs with **L**LM-**G**enerated **O**racles to guide the creation and verify their correctness.
715, When Do Graph Neural Networks Help with Node Classification: Investigating The Homophily Principle on Node Distinguishability
Sitao Luan; Chenqing Hua; Minkai Xu; Qincheng Lu; Jiaqi Zhu; Xiao-Wen Chang; Jie Fu; Jure Leskovec; Doina Precup;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we first demonstrate the aforementioned insufficiency with examples and argue that an ideal situation for ND is to have smaller intra-class ND than inter-class ND. To formulate this idea, we propose Contextual Stochastic Block Model for Homophily (CSBM-H) and define two metrics, Probabilistic Bayes Error (PBE) and negative generalized Jeffreys divergence, to quantify ND, through which we can find how intra- and inter-class ND influence ND together.
716, Optimal Learners for Realizable Regression: PAC Learning and Online Learning
Idan Attias; Steve Hanneke; Alkis Kalavasis; Amin Karbasi; Grigoris Velegkas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting.
717, A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning
Junmin Zhong; Ruofan Wu; Jennie Si;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we show that LNSS, which utilizes a long reward trajectory of rewards of future steps, provides consistent performance improvement measured by average reward, convergence speed, learning success rate,and variance reduction in $Q$ values and rewards.
718, Evaluating and Inducing Personality in Pre-trained Language Models
Guangyuan Jiang; Manjie Xu; Song-Chun Zhu; Wenjuan Han; Chi Zhang; Yixin Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Further, given this evaluation framework, how can we **induce** a particular personality in a controllable fashion? To answer these three questions, we propose the Machine Personality Inventory (MPI) dataset for evaluating the machine personality; MPI follows standardized personality tests, built upon the Big Five Personality Factors (Big Five) theory and personality assessment inventories.
719, The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications
Mirac Suzgun; Luke Melas-Kyriazi; Suproteem Sarkar; Scott D Kominers; Stuart Shieber;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce the Harvard USPTO Patent Dataset (HUPD), a large-scale, well-structured, and multi-purpose corpus of English-language patent applications filed to the United States Patent and Trademark Office (USPTO) between 2004 and 2018.
720, Structured Semidefinite Programming for Recovering Structured Preconditioners
Arun Jambulapati; Jerry Li; Christopher Musco; Kirankumar Shiragur; Aaron Sidford; Kevin Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop a general framework for finding approximately-optimal preconditioners for solving linear systems.
721, Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection
Eli Chien; Wei-Ning Chen; Chao Pan; Pan Li; Ayfer Ozgur; Olgica Milenkovic;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This is especially the case for node predictions that leverage neighboring node attributes directly via graph convolutions that create additional risks of privacy leakage. To address this problem, we introduce Graph Differential Privacy (GDP), a new formal DP framework tailored to graph learning settings that ensures both provably private model parameters and predictions.
722, Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
Anna Hedström; Leander Weber; Daniel Krakowczyk; Dilyara Bareeva; Franz Motzkus; Wojciech Samek; Sebastian Lapuschkin; Marina Höhne;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To increase transparency and reproducibility in the field, we therefore built Quantus�a comprehensive, evaluation toolkit in Python that includes a growing, well-organised collection of evaluation metrics and tutorials for evaluating explainable methods.
723, The Double-Edged Sword of Implicit Bias: Generalization Vs. Robustness in ReLU Networks
Spencer Frei; Gal Vardi; Peter Bartlett; Nati Srebro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the implications of the implicit bias of gradient flow on generalization and adversarial robustness in ReLU networks.
724, Boosting Adversarial Transferability By Achieving Flat Local Maxima
Zhijin Ge; Fanhua Shang; Hongying Liu; Yuanyuan Liu; Wang Xiaosen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, inspired by the fact that flat local minima are correlated with good generalization, we assume and empirically validate that adversarial examples at a flat local region tend to have good transferability by introducing a penalized gradient norm to the original loss function.
725, Universality Laws for Gaussian Mixtures in Generalized Linear Models
Yatin Dandi; Ludovic Stephan; Florent Krzakala; Bruno Loureiro; Lenka Zdeborová;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we consider the hypothesis class of generalized linear models $\hat{y} = F(\mathbf{\Theta}^{\top}\mathbf{x})$ and investigate the asymptotic joint statistics of a family of generalized linear estimators $(\mathbf{\Theta}^{(1)}, \dots, \mathbf{\Theta}^{(M)})$, obtained either from (a) minimizing an empirical risk $\hat{R_n}^{(m)}(\mathbf{\Theta}^{(m)};\mathbf{X},\mathbf{y})$ or (b) sampling from the associated Gibbs measure $\exp(-\beta n \hat{R_n}^{(m)}(\mathbf{\Theta}^{(m)};\mathbf{X},\mathbf{y}))$. Our main contribution is to characterize under which conditions the asymptotic joint statistics of this family depends (on a weak sense) only on the means and covariances of the class conditional features distribution $P_{c}^{\mathbf{x}}$.
726, A Measure-Theoretic Axiomatisation of Causality
Junhyung Park; Simon Buchholz; Bernhard Schölkopf; Krikamol Muandet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To that end, we propose the notion of a causal space, consisting of a probability space along with a collection of transition probability kernels, called causal kernels, that encode the causal information of the space.
727, Self-Correcting Bayesian Optimization Through Bayesian Active Learning
Carl Hvarfner; Erik Hellsten; Frank Hutter; Luigi Nardi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We demonstrate the impact of selecting good hyperparameters for GPs and present two acquisition functions that explicitly prioritize hyperparameter learning.
728, Modeling Human Few-Shot Learning Using Bayesian Inference Over Natural Language
Kevin Ellis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We give a computational model of how humans learn abstract symbolic concepts from few examples.
729, Optimality of Message-Passing Architectures for Sparse Graphs
Aseem Baranwal; Kimon Fountoulakis; Aukosh Jagannath;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the node classification problem on feature-decorated graphs in the sparse setting, i.e., when the expected degree of a node is $O(1)$ in the number of nodes.
730, The Emergence of Clusters in Self-attention Dynamics
Borjan Geshkovski; Cyril Letrouit; Yury Polyanskiy; Philippe Rigollet;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Viewing Transformers as interacting particle systems, we describe the geometry of learned representations when the weights are not time-dependent.
731, Students Parrot Their Teachers: Membership Inference on Model Distillation
Matthew Jagielski; Milad Nasr; Katherine Lee; Christopher A. Choquette-Choo; Nicholas Carlini; Florian Tramer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we design membership inference attacks to systematically study the privacy provided by knowledge distillation to both the teacher and student training sets.
732, Thought Cloning: Learning to Think While Acting By Imitating Human Thinking
Shengran Hu; Jeff Clune;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We hypothesize one reason for such cognitive deficiencies is that they lack the benefits of thinking in language and that we can improve AI agents by training them to $\textit{think like humans do}$. We introduce a novel Imitation Learning framework, Thought Cloning, where the idea is to not just clone the behaviors of human demonstrators, $\textit{but also the thoughts humans have as they perform these behaviors}$.
733, Revisiting Area Convexity: Faster Box-Simplex Games and Spectrahedral Generalizations
Arun Jambulapati; Kevin Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate area convexity [Sherman17], a mysterious tool introduced to tackle optimization problems under the challenging $\ell_\infty$ geometry.
734, Puzzlefusion: Unleashing The Power of Diffusion Models for Spatial Puzzle Solving
Sepidehsadat (Sepid) Hossieni; Mohammad Amin Shabani; Saghar Irandoust; Yasutaka Furukawa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents an end-to-end neural architecture based on Diffusion Models for spatial puzzle solving, particularly jigsaw puzzle and room arrangement tasks.
735, Performance-optimized Deep Neural Networks Are Evolving Into Worse Models of Inferotemporal Visual Cortex
Drew Linsley; Ivan F Rodriguez Rodriguez; Thomas FEL; Michael Arcaro; Saloni Sharma; Margaret Livingstone; Thomas Serre;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These neuronal activity maps reveal that DNNs trained on ImageNet learn to rely on different visual features than those encoded by IT and that this problem worsens as their accuracy increases. We successfully resolved this issue with the neural harmonizer, a plug-and-play training routine for DNNs that aligns their learned representations with humans.
736, PolyDiffuse: Polygonal Shape Reconstruction Via Guided Set Diffusion Models
Jiacheng Chen; Ruizhi Deng; Yasutaka Furukawa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents \textit{PolyDiffuse}, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating reconstruction as a generation process conditioned on sensor data.
737, Variance-Reduced Gradient Estimation Via Noise-Reuse in Online Evolution Strategies
Oscar Li; James Harrison; Jascha Sohl-Dickstein; Virginia Smith; Luke Metz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a general class of unbiased online evolution strategies methods.
738, Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors
Farzad Pourkamali; Nicolas Macris;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a statistical model for matrix factorization in a regime where the rank of the two hidden matrix factors grows linearly with their dimension and their product is corrupted by additive noise.
739, On The Role of Entanglement and Statistics in Learning
Louis Schatzki; Srinivasan Arunachalam; Vojtech Havlicek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we make progress in understanding the relationship between learning models when given access to entangled measurements, separable measurements and statistical measurements in the quantum statistical query ($\mathsf{QSQ}$) model.
740, Chatting Makes Perfect - Chat-based Image Retrieval
Matan Levy; Rami Ben-Ari; Nir Darshan; Dani Lischinski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These questions form a dialog with the user in order to retrieve the desired image from a large corpus. In this study, we explore the capabilities of such a system tested on a large dataset and reveal that engaging in a dialog yields significant gains in image retrieval.
741, Sequential Predictive Two-Sample and Independence Testing
Aleksandr Podkopaev; Aaditya Ramdas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problems of sequential nonparametric two-sample and independence testing.
742, Active Negative Loss Functions for Learning with Noisy Labels
Xichen Ye; Xiaoqiang Li; songmin dai; Tong Liu; Yan Sun; Weiqin Tong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a new class of theoretically robust passive loss functions different from MAE, namely *Normalized Negative Loss Functions* (NNLFs), which focus more on memorized clean samples.
743, Mass-Producing Failures of Multimodal Models
Shengbang Tong; Erik Jones; Jacob Steinhardt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Deployed multimodal models can fail in ways that evaluators did not anticipate. In order to find these failures before deployment, we introduce MultiMon, a system that automatically identifies systematic failures---generalizable, natural-language descriptions that describe categories of individual failures.
744, UNSSOR: Unsupervised Neural Speech Separation By Leveraging Over-determined Training Mixtures
Zhong-Qiu Wang; Shinji Watanabe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In over-determined conditions where the microphones out-number speakers, we can narrow down the solutions to speaker images by leveraging each mixture signal as a constraint (i.e., the estimated speaker images at a microphone should add up to the mixture) to realize unsupervised speech separation. Equipped with this insight, we propose UNSSOR, an algorithm for $\underline{u}$nsupervised $\underline{n}$eural $\underline{s}$peech $\underline{s}$eparation by leveraging $\underline{o}$ver-determined training mixtu$\underline{r}$es.
745, Scaling Up Differentially Private LASSO Regularized Logistic Regression Via Faster Frank-Wolfe Iterations
Edward Raff; Amol Khanna; Fred Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To the best of our knowledge, there are no methods today for training differentially private regression models on sparse input data. To remedy this, we adapt the Frank-Wolfe algorithm for $L_1$ penalized linear regression to be aware of sparse inputs and to use them effectively.
746, On Generalization Bounds for Projective Clustering
Maria Sofia Bucarelli; Matilde Larsen; Chris Schwiegelshohn; Mads Toftrup;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One may also choose centers to be $j$ dimensional subspaces, which gives rise to subspace clustering. In this paper, we consider learning bounds for these problems.
747, PTQD: Accurate Post-Training Quantization for Diffusion Models
Yefei He; Luping Liu; Jing Liu; 威佳 吴; Bohan Zhuang; Hong Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, as the sampling process proceeds, the quantization noise may accumulate, resulting in a low signal-to-noise ratio (SNR) in late denoising steps. To address these challenges, we propose a unified formulation for the quantization noise and diffusion perturbed noise in the quantized denoising process.
748, PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
Phillip Lippe; Bas Veeling; Paris Perdikaris; Richard Turner; Johannes Brandstetter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a large-scale analysis of common temporal rollout strategies, identifying the neglect of non-dominant spatial frequency information, often associated with high frequencies in PDE solutions, as the primary pitfall limiting stable, accurate rollout performance.
749, LoTR: Logic-Guided Transformer Reasoner for Human-Object Interaction Detection
Liulei Li; Jianan Wei; Wenguan Wang; Yi Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present LoTR: Logic-Guided Transformer Reasoner, a novel approach for HOI detection that leverages Transformer as the reasoner to infer feasible interactions between entities.
750, Bottleneck Structure in Learned Features: Low-Dimension Vs Regularity Tradeoff
Arthur Jacot;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Previous work has shown that DNNs withlarge depth $L$ and $L_{2}$-regularization are biased towards learninglow-dimensional representations of the inputs, which can be interpretedas minimizing a notion of rank $R^{(0)}(f)$ of the learned function$f$, conjectured to be the Bottleneck rank. We compute finite depthcorrections to this result, revealing a measure $R^{(1)}$ of regularitywhich bounds the pseudo-determinant of the Jacobian $\left|Jf(x)\right|_{+}$and is subadditive under composition and addition.
751, CAT-Walk: Inductive Hypergraph Learning Via Set Walks
Ali Behrouz; Farnoosh Hashemi; Sadaf Sadeghian; Margo Seltzer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present CAT-Walk, an inductive method that learns the underlying dynamic laws that govern the temporal and structural processes underlying a temporal hypergraph.
752, Towards Unbounded Machine Unlearning
Meghdad Kurmanji; Peter Triantafillou; Eleni Triantafillou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper is the first, to our knowledge, to study unlearning for different applications (RB, RC, UP), with the view that each has its own desiderata, definitions for 'forgetting' and associated metrics for forget quality.
753, LoCoOp: Few-Shot Out-of-Distribution Detection Via Prompt Learning
Atsuyuki Miyai; Qing Yu; Go Irie; Kiyoharu Aizawa;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection.
754, SyncDiffusion: Coherent Montage Via Synchronized Joint Diffusions
Yuseung Lee; Kunho Kim; Hyunjin Kim; Minhyuk Sung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these approaches, which focus on seamless montage generation, often yield incoherent outputs by blending different scenes within a single image. To overcome this limitation, we propose SyncDiffusion, a plug-and-play module that synchronizes multiple diffusions through gradient descent from a perceptual similarity loss.
755, Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria
Fivos Kalogiannis; Ioannis Panageas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by zero-sum polymatrix normal-form games (Cai et al., 2016), we define a class of zero-sum multi-agent Markov games in which there are only pairwise interactions described by a graph that changes per state.
756, Protein Design with Guided Discrete Diffusion
Nate Gruver; Samuel Stanton; Nathan Frey; Tim G. J. Rudner; Isidro Hotzel; Julien Lafrance-Vanasse; Arvind Rajpal; Kyunghyun Cho; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose new methods for discrete diffusion guidance, making it possible to optimize protein sequences for local and global properties while retaining high sequence likelihood.
757, Transformers Learn to Implement Preconditioned Gradient Descent for In-context Learning
Kwangjun Ahn; Xiang Cheng; Hadi Daneshmand; Suvrit Sra;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Going beyond the question of expressivity, we ask: \emph{Can transformers can learn to implement such algorithms by training over random problem instances?} To our knowledge, we make the first theoretical progress toward this question via analysis of the loss landscape for linear transformers trained over random instances of linear regression.
758, Bridging RL Theory and Practice with The Effective Horizon
Cassidy Laidlaw; Stuart J Russell; Anca Dragan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We compare standard deep RL algorithms to prior sample complexity bounds by introducing a new dataset, BRIDGE.
759, Self-supervised Neural Maps for Visual Positioning and Semantic Understanding
Paul-Edouard Sarlin; Eduard Trulls; Marc Pollefeys; Simon Lynen; Jan Hosang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce SNAP, a deep network that learns rich 2D _neural_ maps from ground-level and overhead images.
760, PrObeD: Proactive Object Detection Wrapper
Vishal Asnani; Abhinav Kumar; Suya You; Xiaoming Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, convergence to global minima is not optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors.
761, Robust Covariance Estimation with Missing Values and Cell-wise Contamination
Grégoire Pacreau; Karim Lounici;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose an unbiased estimator for the covariance in the presence of missing values that does not require any imputation step and still achieves minimax statistical accuracy with the operator norm.
762, Evaluating The Moral Beliefs Encoded in LLMs
Nino Scherrer; Claudia Shi; Amir Feder; David Blei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we design a survey, a set of evaluation metrics, and a statistical workflow on how to elicit the moral beliefs encoded in an LLM.
763, Zero-Regret Performative Prediction Under Inequality Constraints
Wenjing YAN; Xuanyu Cao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper bridges this gap by studying performative prediction under inequality constraints. Unlike most existing work that provides only performative stable points, we aim to find the optimal solutions.
764, Learning New Dimensions of Human Visual Similarity Using Synthetic Data
Stephanie Fu; Netanel Tamir; Shobhita Sundaram; Lucy Chai; Richard Zhang; Tali Dekel; Phillip Isola;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop a perceptual metric that assesses images holistically.
765, Non-Asymptotic Analysis of A UCB-based Top Two Algorithm
Marc Jourdan; Rémy Degenne;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we derive the first non-asymptotic upper bound on the expected sample complexity of a Top Two algorithm, which holds for any error level.
766, Norm-based Generalization Bounds for Sparse Neural Networks
Tomer Galanti; Mengjia Xu; Liane Galanti; Tomaso Poggio;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the Rademacher complexity of deep sparse neural networks, where each neuron receives a small number of inputs.
767, Model-free Posterior Sampling Via Learning Rate Randomization
Daniil Tiapkin; Denis Belomestny; Daniele Calandriello; Eric Moulines; Remi Munos; Alexey Naumov; Pierre Perrault; Michal Valko; Pierre Ménard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-free algorithm for regret minimization in episodic Markov Decision Processes (MDPs).
768, TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials
Guillem Simeon; Gianni De Fabritiis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce TensorNet, an innovative $\mathrm{O}(3)$-equivariant message-passing neural network architecture that leverages Cartesian tensor representations.
769, Counterfactually Comparing Abstaining Classifiers
Yo Joong Choe; Aditya Gangrade; Aaditya Ramdas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel approach and perspective to the problem of evaluating and comparing abstaining classifiers by treating abstentions as missing data.
770, AGD: An Auto-switchable Optimizer Using Stepwise Gradient Difference As Preconditioning Matrix
Yun Yue; Zhiling Ye; Jiadi Jiang; Yongchao Liu; Yin Lou; Ke Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel approach to designing the preconditioning matrix by utilizing the gradient difference between the current and previous steps as the diagonal elements.
771, Effective Bayesian Heteroscedastic Neural Networks: Model Selection and Epistemic Uncertainties
Alexander Immer; Emanuele Palumbo; Julia Vogt; Alexander Marx;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that the problem of gradient scaling can be alleviated by instead using the natural parameterization of the Gaussian likelihood.
772, Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
Eduard Tulchinskii; Kristian Kuznetsov; Laida Kushnareva; Daniil Cherniavskii; Sergey Nikolenko; Irina Piontkovskaya; Serguei Barannikov; Evgeny Burnaev;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, it becomes increasingly important to study the properties of human texts that are invariant over text domains and various proficiency of human writers, can be easily calculated for any language, and can robustly separate natural and AI-generated texts regardless of the generation model and sampling method. In this work, we propose such an invariant of human texts, namely the intrinsic dimensionality of the manifold underlying the set of embeddings of a given text sample.
773, Variational Monte Carlo on A Budget — Fine-tuning Pre-trained Neural Wavefunctions
Michael Scherbela; Leon Gerard; Philipp Grohs;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We instead propose a DL-VMC model which has been pre-trained using self-supervised wavefunction optimization on a large and chemically diverse set of molecules.
774, Reward Scale Robustness for Proximal Policy Optimization Via DreamerV3 Tricks
Ryan Sullivan; Akarsh Kumar; Shengyi Huang; John Dickerson; Joseph Suarez;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present extensive ablation studies totaling over 10,000 A100 hours of compute on the Arcade Learning Environment and the Deepmind Control Suite.
775, Information Theoretic Lower Bounds for Information Theoretic Upper Bounds
Roi Livni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We examine the relationship between the mutual information between the output model and the empirical sample and the algorithm's generalization in the context of stochastic convex optimization.
776, Bounding Training Data Reconstruction in DP-SGD
Jamie Hayes; Borja Balle; Saeed Mahloujifar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent works provide evidence that if one does not need to protect against membership attacks but instead only wants to protect against a training data reconstruction, then utility of private models can be improved because less noise is required to protect against these more ambitious attacks. We investigate this question further in the context of DP-SGD, a standard algorithm for private deep learning, and provide an upper bound on the success of any reconstruction attack against DP-SGD together with an attack that empirically matches the predictions of our bound.
777, Are Neural Operators Really Neural Operators? Frame Theory Meets Operator Learning
Francesca Bartolucci; Emmanuel de Bézenac; Bogdan Raonic; Roberto Molinaro; Siddhartha Mishra; Rima Alaifari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose to employ frames, a concept in applied harmonic analysis and signal processing that gives rise to exact and stable discrete representations of continuous signals. Extending these concepts to operators, we introduce a unifying mathematical framework of Representation equivalent Neural Operator (ReNO) to ensure operations at the continuous and discrete level are equivalent.
778, Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation
Berivan Isik; Wei-Ning Chen; Ayfer Ozgur; Tsachy Weissman; Albert No;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we take a step towards characterizing the exact-optimal approach in the presence of shared randomness (a random variable shared between the server and the user) and identify several necessary conditions for exact optimality.
779, Learning The Efficient Frontier
Philippe Chatigny; Ivan Sergienko; Ryan Ferguson; Jordan Weir; Maxime Bergeron;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce NeuralEF: a fast neural approximation framework that robustly forecasts the result of the EF convex optimizations problems with respect to heterogeneous linear constraints and variable number of optimization inputs.
780, Optimal and Fair Encouragement Policy Evaluation and Learning
Angela Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop a two-stage, online learning-based algorithm for solving over parametrized policy classes under general constraints to obtain variance-sensitive regret bounds.
781, RapidBERT: Pretraining BERT from Scratch for $20
Jacob Portes; Alexander Trott; Sam Havens; DANIEL KING; Abhinav Venigalla; Moin Nadeem; Nikhil Sardana; Daya Khudia; Jonathan Frankle;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we introduce RapidBERT, a BERT-style encoder architecture and training recipe that is empirically optimized for fast pretraining.
782, Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval
Frederik Warburg; Marco Miani; Silas Brack; Søren Hauberg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose three methods that ensure a positive definite covariance matrix.
783, Test-time Model DeBias Via Machine Unlearning
Ruizhe Chen; Jianfei Yang; Huimin Xiong; Jianhong Bai; Tianxiang Hu; Jin Hao; YANG FENG; Joey Tianyi Zhou; Jian Wu; Zuozhu Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing debiasing methods suffer from high costs in bias labeling or model re-training, while also exhibiting a deficiency in terms of elucidating the origins of biases within the model. To this respect, we propose a fast model debiasing method (FMD) which offers an efficient approach to identify, evaluate and remove biases inherent in trained models.
784, OKRidge: Scalable Optimal K-Sparse Ridge Regression for Learning Dynamical Systems
Jiachang Liu; Sam Rosen; Chudi Zhong; Cynthia Rudin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a fast algorithm, OKRidge, for sparse ridge regression, using a novel lower bound calculation involving, first, a saddle point formulation, and from there, either solving (i) a linear system or (ii) using an ADMM-based approach, where the proximal operators can be efficiently evaluated by solving another linear system and an isotonic regression problem.
785, Stable Vectorization of Multiparameter Persistent Homology Using Signed Barcodes As Measures
Luis Scoccola; David Loiseaux; Mathieu Carrière; Magnus Bakke Botnan; Steve OUDOT;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we aim to bring together the best of both worlds by showing how the interpretation of signed barcodes---a recent family of MPH descriptors---as signed Radon measures leads to natural extensions of vectorization strategies from one parameter to multiple parameters.
786, Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers Over Continuous-time Sequences of Complex Events
Matthew McDermott; Bret Nestor; Peniel Argaw; Isaac S Kohane;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite their potential, the adoption of foundation models in these domains has been hampered by the lack of suitable tools for model construction and evaluation. To bridge this gap, we introduce Event Stream GPT (ESGPT), an open-source library designed to streamline the end-to-end process for building GPTs for continuous-time event sequences.
787, LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark
Zhenfei Yin; Jiong WANG; Jianjian Cao; Zhelun Shi; Dingning Liu; Mukai Li; Lu Sheng; Xiaoshui Huang; LEI BAI; Zhiyong Wang; Wanli Ouyang; Jing Shao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we extend the research of MLLMs to point clouds and present the LAMM-Dataset and LAMM-Benchmark for 2D image and 3D point cloud understanding.
788, Object Reprojection Error (ORE): Camera Pose Benchmarks from Lightweight Tracking Annotations
Xingyu Chen; Weiyao Wang; Hao Tang; Matt Feiszli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel evaluation protocol, Object Reprojection Error (ORE) to benchmark camera trajectories; ORE computes reprojection error for static objects within the video and requires only lightweight object tracklet annotations.
789, DAC-DETR: Divide The Attention Layers and Conquer
Zhengdong Hu; Yifan Sun; Jingdong Wang; Yi Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we observe the cross-attention tends to gather multiple queries around the same object, while the self-attention disperses these queries far away. To improve the training efficacy, we propose a Divide-And-Conquer DETR (DAC-DETR) that divides the cross-attention out from this contrary for better conquering.
790, Principlism Guided Responsible Data Curation
Jerone Andrews; Dora Zhao; William Thong; Apostolos Modas; Orestis Papakyriakopoulos; Alice Xiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our research focuses on proactive, domain-specific recommendations, covering purpose, privacy and consent, as well as diversity, for curating HCCV evaluation datasets, addressing privacy and bias.
791, EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset
Hao Tang; Kevin J Liang; Kristen Grauman; Matt Feiszli; Weiyao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We thus introduce EgoTracks, a new dataset for long-term egocentric visual object tracking.
792, RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
Dongwei Pan; Long Zhuo; Jingtan Piao; Huiwen Luo; Wei Cheng; Yuxin WANG; Siming Fan; Shengqi Liu; Lei Yang; Bo Dai; Ziwei Liu; Chen Change Loy; Chen Qian; Wayne Wu; Dahua Lin; Kwan-Yee Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present RenderMe-360, a comprehensive 4D human head dataset to drive advance in head avatar algorithms across different scenarios.
793, From Pixels to UI Actions: Learning to Follow Instructions Via Graphical User Interfaces
Peter Shaw; Mandar Joshi; James Cohan; Jonathan Berant; Panupong Pasupat; Hexiang Hu; Urvashi Khandelwal; Kenton Lee; Kristina N Toutanova;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper focuses on creating agents that interact with the digital world using the same conceptual interface that humans commonly use — via pixel-based screenshots and a generic action space corresponding to keyboard and mouse actions.
794, Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance
Congyue Deng; Jiahui Lei; William B Shen; Kostas Daniilidis; Leonidas Guibas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present Banana, a Banach fixed-point network for equivariant segmentation with inter-part equivariance by construction.
795, Online Ad Procurement in Non-stationary Autobidding Worlds
Jason Cheuk Nam Liang; Haihao Lu; Baoyu Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In practice, advertisers may receive minimal information on platforms' procurement details, and procurement outcomes are subject to non-stationary factors like seasonal patterns, occasional system corruptions, and market trends which make it difficult for advertisers to optimize lever decisions effectively. Motivated by this, we present an online learning framework that helps advertisers dynamically optimize ad platform lever decisions while subject to general long-term constraints in a realistic bandit feedback environment with non-stationary procurement outcomes.
796, [Re] VAE Approximation Error: ELBO and Exponential Families
Volodymyr Kyrylov; Navdeep Singh Bedi; Qianbo Zang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Exponential family variational autoencoders struggle with reconstruction when encoders output limited information. We reproduce two experiments in which we first train the decoder and encoder separately. Then, we train both modules jointly using ELBO and observe the degradation of reconstruction.
797, [Re] Numerical Influence of ReLU'(0) on Backpropagation
Tommaso Martorella; Hector Manuel Ramirez Contreras; Daniel Garcia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we extended some experiments to see how the training and test loss are affected in simple and more complex models.
798, Adversarial Counterfactual Environment Model Learning
Xiong-Hui Chen; Yang Yu; Zhengmao Zhu; ZhiHua Yu; Chen Zhenjun; Chenghe Wang; Yinan Wu; Rong-Jun Qin; Hongqiu Wu; Ruijin Ding; Huang Fangsheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, we first show that, particularly in the sequential decision-making setting, this approach may catastrophically fail to predict counterfactual action effects due to the selection bias of behavior policies during data collection. To tackle this problem, we introduce a novel model-learning objective called adversarial weighted empirical risk minimization (AWRM).
799, Efficient Online Clustering with Moving Costs
Dimitris Christou; Stratis Skoulakis; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we consider an online learning problem, called Online $k$-Clustering with Moving Costs, at which a learner maintains a set of $k$ facilities over $T$ rounds so as to minimize the connection cost of an adversarially selected sequence of clients.
800, CLIP-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments
Jessica Dai; Paula Gradu; Christopher Harshaw;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we study the problem of Adaptive Neyman Allocation in a design-based potential outcomes framework, where the experimenter seeks to construct an adaptive design which is nearly as efficient as the optimal (but infeasible) non-adaptive Neyman design, which has access to all potential outcomes.
801, Scaling Laws for Language Encoding Models in FMRI
Richard Antonello; Aditya Vaidya; Alexander Huth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we tested whether larger open-source models such as those from the OPT and LLaMA families are better at predicting brain responses recorded using fMRI.
802, Evaluating Open-QA Evaluation
Cunxiang Wang; Sirui Cheng; Qipeng Guo; Zhikun Xu; Bowen Ding; Yidong Wang; Xiangkun Hu; Zheng Zhang; Yue Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a new task, QA Evaluation (QA-Eval) and the corresponding dataset EVOUNA, designed to assess the accuracy of AI-generated answers in relation to standard answers within Open-QA.
803, Face Reconstruction from Facial Templates By Learning Latent Space of A Generator Network
Hatef Otroshi Shahreza; Sébastien Marcel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we focus on the template inversion attack against face recognition systems and propose a new method to reconstruct face images from facial templates.
804, Using Large Language Model Annotations for Valid Downstream Statistical Inference in Social Science: Design-Based Semi-Supervised Learning
Naoki Egami; Musashi Hinck; Brandon Stewart; Hanying Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new algorithm for using outputs from LLMs for downstream statistical analyses while guaranteeing statistical properties—like asymptotic unbiasedness and proper uncertainty quantification—which are fundamental to CSS research.
805, DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views
Paul Yoo; Jiaxian Guo; Yutaka Matsuo; Shixiang (Shane) Gu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we explore leveraging the strong 2D priors in pre-trained diffusion models for synthesizing novel view images.
806, Test-Time Amendment with A Coarse Classifier for Fine-Grained Classification
Kanishk Jain; Shyamgopal Karthik; Vineet Gandhi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we present a novel approach for Post-Hoc Correction called Hierarchical Ensembles (HiE) that utilizes label hierarchy to improve the performance of fine-grained classification at test-time using the coarse-grained predictions.
807, Binarized Spectral Compressive Imaging
Yuanhao Cai; Yuxin Zheng; Jing Lin; Haoqian Wang; Xin Yuan; Yulun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel method, Binarized Spectral-Redistribution Network (BiSRNet), for efficient and practical HSI restoration from compressed measurement in snapshot compressive imaging (SCI) systems.
808, Learning Better with Dale’s Law: A Spectral Perspective
Pingsheng Li; Jonathan Cornford; Arna Ghosh; Blake Richards;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Overall, this work sheds light on a long-standing mystery in neuroscience-inspired AI and computational neuroscience, paving the way for greater alignment between neural networks and biology.
809, Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer
Zikai Xiao; Zihan Chen; Songshang Liu; Hualiang Wang; YANG FENG; Jin Hao; Joey Tianyi Zhou; Jian Wu; Howard Yang; Zuozhu Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In response, we propose a method termed $\texttt{Fed-GraB}$, comprised of a Self-adjusting Gradient Balancer (SGB) module that re-weights clients' gradients in a closed-loop manner, based on the feedback of global long-tailed distribution evaluated by a Direct Prior Analyzer (DPA) module.
810, Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization
Shurui Gui; Meng Liu; Xiner Li; Youzhi Luo; Shuiwang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose to simultaneously incorporate label and environment causal independence (LECI) to fully make use of label and environment information, thereby addressing the challenges faced by prior methods on identifying causal and invariant subgraphs.
811, Non-Stationary Bandits with Auto-Regressive Temporal Dependency
Qinyi Chen; Negin Golrezaei; Djallel Bouneffouf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Traditional multi-armed bandit (MAB) frameworks, predominantly examined under stochastic or adversarial settings, often overlook the temporal dynamics inherent in many real-world applications such as recommendation systems and online advertising. This paper introduces a novel non-stationary MAB framework that captures the temporal structure of these real-world dynamics through an auto-regressive (AR) reward structure.
812, Single-Pass Pivot Algorithm for Correlation Clustering. Keep It Simple!
Konstantin Makarychev; Sayak Chakrabarty;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is a slight improvement over the recent results of Cambus, Kuhn, Lindy, Pai, and Uitto, who gave a (3+eps)-approximation using O(n log n) words of memory, and Behnezhad, Charikar, Ma, and Tan, who gave a 5-approximation using O(n) words of memory. One of the main contributions of our paper is that the algorithm and its analysis are simple and easy to understand.
813, OBJECT 3DIT: Language-guided 3D-aware Image Editing
Oscar Michel; Anand Bhattad; Ranjay Krishna; Tanmay Gupta; Aniruddha Kembhavi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we formulate the new task of language-guided 3D-aware editing, where objects in an image should be edited according to a language instruction while remaining consistent with the underlying 3D scene.
814, MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks
Vinitra Swamy; Malika Satayeva; Jibril Frej; Thierry Bossy; Thijs Vogels; Martin Jaggi; Tanja Käser; Mary-Anne Hartley;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Multimodal (MM) models aim to extract the synergistic predictive potential of multiple data types to create a shared feature space with aligned semantic meaning across inputs of drastically varying sizes (i.e. images, text, sound).
815, Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models
Anant Raj; Umut Simsekli; Alessandro Rudi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper deals with the problem of efficient sampling from a stochastic differential equation, given the drift function and the diffusion matrix.
816, TRIAGE: Characterizing and Auditing Training Data for Improved Regression
Nabeel Seedat; Jonathan Crabbé; Zhaozhi Qian; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, current data characterization methods are largely focused on classification settings, with regression settings largely understudied. To address this, we introduce TRIAGE, a novel data characterization framework tailored to regression tasks and compatible with a broad class of regressors.
817, Optimal Algorithms for The Inhomogeneous Spiked Wigner Model
Aleksandr Pak; Justin Ko; Florent Krzakala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study a spiked Wigner problem with an inhomogeneous noise profile. Our aim in this problem is to recover the signal passed through an inhomogeneous low-rank matrix channel.
818, NetHack Is Hard to Hack
Ulyana Piterbarg; Lerrel Pinto; Rob Fergus;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Intriguingly, the NeurIPS 2021 NetHack Challenge revealed that symbolic agents outperformed neural approaches by over four times in median game score. In this paper, we delve into the reasons behind this performance gap and present an extensive study on neural policy learning for NetHack.
819, Non-adversarial Training of Neural SDEs with Signature Kernel Scores
Zacharia Issa; Blanka Horvath; Maud Lemercier; Cristopher Salvi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, as typical for GAN architectures, training is notoriously unstable, often suffers from mode collapse, and requires specialised techniques such as weight clipping and gradient penalty to mitigate these issues. In this paper, we introduce a novel class of scoring rules on pathspace based on signature kernels and use them as objective for training Neural SDEs non-adversarially.
820, Transformers As Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
Yu Bai; Fan Chen; Huan Wang; Caiming Xiong; Song Mei;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We establish this in theory by explicit constructions, and also observe this phenomenon experimentally. In theory, we construct two general mechanisms for algorithm selection with concrete examples: (1) Pre-ICL testing, where the transformer determines the right task for the given sequence (such as choosing between regression and classification) by examining certain summary statistics of the input sequence; (2) Post-ICL validation, where the transformer selects---among multiple base ICL algorithms (such as ridge regression with multiple regularization strengths)---a near-optimal one for the given sequence using a train-validation split.
821, A Pseudo-Semantic Loss for Deep Generative Models with Logical Constraints
Kareem Ahmed; Kai-Wei Chang; Guy Van den Broeck;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead of attempting to enforce the constraint on the entire likelihood distribution, we propose to do so on a random, local approximation thereof.
822, Privacy Auditing with One (1) Training Run
Thomas Steinke; Milad Nasr; Matthew Jagielski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a scheme for auditing differentially private machine learning systems with a single training run.
823, The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
Agustinus Kristiadi; Felix Dangel; Philipp Hennig;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the invariance of neural nets under reparametrization from the perspective of Riemannian geometry.
824, What Can A Single Attention Layer Learn? A Study Through The Random Features Lens
Hengyu Fu; Tianyu Guo; Yu Bai; Song Mei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a rigorous theoretical study on the learning and generalization of a single multi-head attention layer, with a sequence of key vectors and a separate query vector as input.
825, Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data
Nabeel Seedat; Boris van Breugel; Fergus Imrie; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce 3S Testing, a deep generative modeling framework to facilitate model evaluation by generating synthetic test sets for small subgroups and simulating distributional shifts.
826, Scaling Open-Vocabulary Object Detection
Matthias Minderer; Alexey Gritsenko; Neil Houlsby;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Major challenges in scaling self-training are the choice of label space, pseudo-annotation filtering, and training efficiency. We present the OWLv2 model and OWL-ST self-training recipe, which address these challenges.
827, Unsupervised Semantic Correspondence Using Stable Diffusion
Eric Hedlin; Gopal Sharma; Shweta Mahajan; Hossam Isack; Abhishek Kar; Andrea Tagliasacchi; Kwang Moo Yi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To generate such images, these models must understand the semantics of the objects they are asked to generate. In this work we show that, without any training, one can leverage this semantic knowledge within diffusion models to find semantic correspondences – locations in multiple images that have the same semantic meaning.
828, Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
Muhammad Faaiz Taufiq; Arnaud Doucet; Rob Cornish; Jean-Francois Ton;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a new OPE estimator for contextual bandits, the Marginal Ratio (MR) estimator, which focuses on the shift in the marginal distribution of outcomes $Y$ instead of the policies themselves.
829, Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
Jinwoo Kim; Dat Nguyen; Ayhan Suleymanzade; Hyeokjun An; Seunghoon Hong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries.
830, Mechanic: A Learning Rate Tuner
Ashok Cutkosky; Aaron Defazio; Harsh Mehta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a technique for tuning the learning rate scale factor of any base optimization algorithm and schedule automatically, which we call Mechanic.
831, State-space Models with Layer-wise Nonlinearity Are Universal Approximators with Exponential Decaying Memory
Shida Wang; Beichen Xue;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we prove that stacking state space models with layer-wise nonlinear activation is sufficient to approximate any continuous sequence-to-sequence relationship.
832, Beyond NTK with Vanilla Gradient Descent: A Mean-field Analysis of Neural Networks with Polynomial Width, Samples, and Time
Arvind Mahankali; Jeff Z. HaoChen; Kefan Dong; Margalit Glasgow; Tengyu Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper provides a clean mean-field analysis of projected gradient flow on polynomial-width two-layer neural networks.
833, Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective
Zhiding Liu; Mingyue Cheng; Zhi Li; Zhenya Huang; Qi Liu; Yanhu Xie; Enhong Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel slice-level adaptive normalization, referred to \textbf{SAN}, which is a novel scheme for empowering time series forecasting with more flexible normalization and denormalization.
834, FairLISA: Fair User Modeling with Limited Sensitive Attributes Information
zheng zhang; Qi Liu; Hao Jiang; Fei Wang; Yan Zhuang; Le Wu; Weibo Gao; Enhong Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we focus on a practical situation with limited sensitive data and propose a novel FairLISA framework, which can efficiently utilize data with known and unknown sensitive attributes to facilitate fair model training.
835, BRAM: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training
Hanyang Peng; Shuang Qin; Yue Yu; Jin Wang; Hui Wang; Ge Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: More importantly, recent studies suggest that these algorithms actually offer no speed advantages over SGDM/Adam when used with common distributed DNN training frameworks ( *e.g.*, *{DistributedDataParallel (DDP)*) in the typical settings, due to heavy compression/decompression computation or incompatibility with the efficient \emph{All-Reduce} or the requirement of uncompressed warmup at the early stage. For these reasons, we propose a novel 1-bit adaptive optimizer, dubbed Binary Randomization adaptive optimizer ( BRAM).
836, Predicting Global Label Relationship Matrix for Graph Neural Networks Under Heterophily
Langzhang Liang; Xiangjing Hu; Zenglin Xu; Zixing Song; Irwin King;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent studies have demonstrated that GNNs may struggle to model heterophilous graphs where nodes with different labels are more likely connected. To address this issue, we propose a generic GNN applicable to both homophilous and heterophilous graphs, namely Low-Rank Graph Neural Network (LRGNN).
837, Task-aware World Model Learning with Meta Weighting Via Bi-level Optimization
Huining Yuan; Hongkun Dou; Xingyu Jiang; Yue Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To combine the benefits of both types of models, we propose Task-aware Environment Modeling Pipeline with Bi-level Optimization (TEMPO), a bi-level model learning framework that introduces an additional level of optimization on top of a maximum-likelihood model by incorporating a meta weighter network that weights each training sample.
838, Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning
Zixing Song; Yifei Zhang; Irwin King;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present an optimal asymmetric graph structure for the label inference phase with theoretical motivations.
839, No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning
Zixing Song; Yifei Zhang; Irwin King;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel active learning (AL) method for GNNs, extending the Expected Model Change Maximization (EMCM) principle to improve prediction performance on unlabeled data.
840, Mitigating The Popularity Bias in Graph-based Collaborative Filtering
Yifei Zhang; Hao Zhu; yankai Chen; Zixing Song; Piotr Koniusz; Irwin King;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This enhances the so-called Matthew effect of the popularity bias where popular items are highly recommend whereas remaining items are ignored. In this paper, we analyze the above effect in GCF and reveal that the simplified graph convolution operation (typically used in GCF) shrinks the singular space of the feature matrix.
841, Hierarchically Gated Recurrent Neural Network for Sequence Modeling
Zhen Qin; Songlin Yang; Yiran Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we show that the RNN can not only achieve efficient parallel training but also better long-sequence modeling than transformers.
842, Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
Woojin Cho; Kookjin Lee; Donsub Rim; Noseong Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In various engineering and applied science applications, repetitive numerical simulations of partial differential equations (PDEs) for varying input parameters are often required (e.g., aircraft shape optimization over many design parameters) and solvers are required to perform rapid execution. In this study, we suggest a path that potentially opens up a possibility for physics-informed neural networks (PINNs), emerging deep-learning-based solvers, to be considered as one such solver.
843, Volume Feature Rendering for Fast Neural Radiance Field Reconstruction
Kang Han; Wei Xiang; Lu Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead of rendering yielded color after neural network evaluation, we propose to render the queried feature vectors of a ray first and then transform the rendered feature vector to the final pixel color by a neural network.
844, SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
Di Wang; Jing Zhang; Bo Du; Minqiang Xu; Lin Liu; Dacheng Tao; Liangpei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS.
845, Scissorhands: Exploiting The Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
Zichang Liu; Aditya Desai; Fangshuo Liao; Weitao Wang; Victor Xie; Zhaozhuo Xu; Anastasios Kyrillidis; Anshumali Shrivastava;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by an interesting observation of the attention scores, we hypothesize the persistence of importance: only pivotal tokens, which had a substantial influence at one step, will significantly influence future generations. Based on our empirical verification and theoretical analysis around this hypothesis, we propose scissorhands, a system that maintains the memory usage of the KV cache at a fixed budget without finetuning the model.
846, One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning
Zichang Liu; Zhaozhuo Xu; Benjamin Coleman; Anshumali Shrivastava;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a one-pass distribution sketch to represent the client data distribution.
847, Complexity Matters: Rethinking The Latent Space for Generative Modeling
Tianyang Hu; Fei Chen; Haonan Wang; Jiawei Li; Wenjia Wang; Jiacheng Sun; Zhenguo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although the selection of the latent space is empirically pivotal, determining the optimal choice and the process of identifying it remain unclear. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
848, Achieving Near-optimal Complexity in Hessian-free Stochastic Bilevel Optimization
Yifan Yang; Peiyao Xiao; Kaiyi Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we revisit the bilevel optimization problem, in which the upper-level objective function is generally nonconvex and the lower-level objective function is strongly convex.
849, SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning
Yifan Yang; Peiyao Xiao; Kaiyi Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple and flexible FBO framework named SimFBO, which is easy to implement without sub-loops, and includes a generalized server-side aggregation and update for improving communication efficiency.
850, Binary Radiance Fields
Seungjoo Shin; Jaesik Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose binary radiance fields (BiRF), a storage-efficient radiance field representation employing binary feature encoding that encodes local features using binary encoding parameters in a format of either $+1$ or $-1$.
851, C-Disentanglement: Discovering Causally-Independent Generative Factors Under An Inductive Bias of Confounder
Xiaoyu Liu; Jiaxin Yuan; Bang An; Yuancheng Xu; Yifan Yang; Furong Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we recognize the importance of modeling confounders in discovering causal generative factors.
852, Towards Standardised Evaluation of Systematic Literature Review Automation
Wojciech Kusa; Oscar E. Mendoza; Matthias Samwald; Petr Knoth; Allan Hanbury;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we conduct a deep analysis of the citation screening evaluation datasets, revealing that many of the available datasets are either too small sets, suffer from data leakage and have limited applicability to systems treating automated literature screening as a classification task, as opposed to, for example, a retrieval or question-answering task.
853, Trajdata: A Unified Interface to Multiple Human Trajectory Datasets
Boris Ivanovic; Guanyu Song; Igor Gilitschenski; Marco Pavone;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While such datasets have been a boon for the community, they each use custom and unique data formats and APIs, making it cumbersome for researchers to train and evaluate methods across multiple datasets. To remedy this, we present trajdata: a unified interface to multiple human trajectory datasets.
854, $\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
Ruijie Zheng; Xiyao Wang; Yanchao Sun; Shuang Ma; Jieyu Zhao; Huazhe Xu; Hal Daumé III; Furong Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce $\texttt{TACO}$: $\textbf{T}$emporal $\textbf{A}$ction-driven $\textbf{CO}$ntrastive Learning, a simple yet powerful temporal contrastive learning approach that facilitates the concurrent acquisition of latent state and action representations for agents.
855, Large-Scale Distributed Learning Via Private On-Device LSH
Tahseen Rabbani; Marco Bornstein; Furong Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Using a new family of hash functions, we develop the first private, personalized, and memory-efficient on-device LSH framework.
856, Why Does Sharpness-Aware Minimization Generalize Better Than SGD?
Zixiang Chen; Junkai Zhang; Yiwen Kou; Xiangning Chen; Cho-Jui Hsieh; Quanquan Gu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, a deep understanding of how SAM works, especially in the setting of nonlinear neural networks and classification tasks, remains largely missing. In this paper, we fill this gap by demonstrating why SAM generalize better than Stochastic Gradient Descent (SGD) for the certain data model and two-layer convolutional ReLU networks.
857, Deep Non-line-of-sight Imaging from Under-scanning Measurements
Yue Li; Yueyi Zhang; Juntian Ye; Feihu Xu; Zhiwei Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose the first deep-learning-based approach to NLOS imaging from USM.
858, TradeMaster: A Holistic Quantitative Trading Platform Empowered By Reinforcement Learning
Shuo Sun; Molei Qin; Wentao Zhang; Haochong Xia; Chuqiao Zong; Jie Ying; Yonggang Xie; Lingxuan Zhao; Xinrun Wang; Bo An;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, orchestrating an RLFT project lifecycle poses challenges in engineering (i.e. hard to build), benchmarking (i.e. hard to compare) and usability (i.e. hard to optimize, maintain and use). To overcome these challenges, we introduce TradeMaster, a holistic open-source RLFT platform that serves as a i) software toolkit, ii) empirical benchmark, and iii) user interface.
859, Mind2Web: Towards A Generalist Agent for The Web
Xiang Deng; Yu Gu; Boyuan Zheng; Shijie Chen; Sam Stevens; Boshi Wang; Huan Sun; Yu Su;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Mind2Web, the first dataset for developing and evaluating generalist agents for the web that can follow language instructions to complete complex tasks on any website.
860, Data-Informed Geometric Space Selection
Shuai Zhang; Wenqi Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods heavily rely on heuristic assumptions on the data structure to decide the type of geometry to be adopted, which often leads to suboptimal performance. This work aims to automate the alignment process via a data-informed strategy such that we optimize model performance with minimal overhead.
861, Zero-Shot Batch-Level Anomaly Detection
Aodong Li; Chen Qiu; Marius Kloft; Padhraic Smyth; Maja Rudolph; Stephan Mandt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple yet effective method called Adaptive Centered Representations (ACR) for zero-shot batch-level AD.
862, Sparse Parameterization for Epitomic Dataset Distillation
Xing Wei; Anjia Cao; Funing Yang; Zhiheng Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a Sparse Parameterization for Epitomic datasEt Distillation (SPEED) framework, which leverages the concept of dictionary learning and sparse coding to distill epitomes that represent pivotal information of the data.
863, When Can Regression-Adjusted Control Variate Help? Rare Events, Sobolev Embedding and Minimax Optimality
Jose Blanchet; Haoxuan Chen; Yiping Lu; Lexing Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We examine a prototype estimation problem that involves simulating the moments of a Sobolev function based on observations obtained from (random) quadrature nodes.
864, A Comparative Study of Graph Structure Learning: Benchmark and Analysis
Zhixun Li; Liang Wang; Xin Sun; Yifan Luo; Yanqiao Zhu; Dingshuo Chen; Yingtao Luo; Xiangxin Zhou; Qiang Liu; Shu Wu; Liang Wang; Jeffrey Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from diverse datasets and GSL algorithms.
865, Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games
Yang Cai; Haipeng Luo; Chen-Yu Wei; Weiqiang Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We revisit the problem of learning in two-player zero-sum Markov games, focusing on developing an algorithm that is *uncoupled*, *convergent*, and *rational*, with non-asymptotic convergence rates to Nash equilibrium.
866, Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations
Hammaad Adam; Fan Yin; Huibin Hu; Neil Tenenholtz; Lorin Crawford; Lester Mackey; Allison Koenecke;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we study the early stopping of experiments for harm on heterogeneous populations.
867, Conditional 3D Shape Generation with Shape-Image-Text Aligned Representation
Zibo Zhao; Wen Liu; Xin Chen; Xianfang Zeng; Rui Wang; Pei Cheng; BIN FU; Tao Chen; Gang Yu; Shenghua Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts.
868, Test Time Adaptation with Diffusion Models
Mihir Prabhudesai; Tsung-Wei Ke; Alex Li; Deepak Pathak; Katerina Fragkiadaki;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a method to adapt large-scale pre-trained classifiers and CLIP models to individual unlabelled images by modulating the text conditioning of a text-conditional pretrained image diffusion model and maximizing the image likelihood using end-to-end backpropagation to the classifier parameters.
869, Reinforcement Learning with Simple Sequence Priors
Tankred Saanum; Noemi Elteto; Peter Dayan; Marcel Binz; Eric Schulz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In reinforcement learning (RL), simplicity is typically quantified on an action-by-action basis -- but this timescale ignores temporal regularities, like repetitions, often present in sequential strategies. We therefore propose an RL algorithm that learns to solve tasks with sequences of actions that are compressible.
870, Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance
Lisha Chen; Heshan Fernando; Yiming Ying; Tianyi Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Albeit its appealing intuition, these dynamic weighting methods may not always outperform static ones empirically. To better understand this theory-practical gap, we focus on a stochastic variant of MGDA, and study the generalization performance of dynamic weighting-based methods and its interplay with optimization through the lens of algorithm stability.
871, An Alternating Optimization Method for Bilevel Problems Under The Polyak-Łojasiewicz Condition
Quan Xiao; Songtao Lu; Tianyi Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a \textsf{G}eneralized \textsf{AL}ternating m\textsf{E}thod for bilevel op\textsf{T}imization (\textsf{GALET}) with a nonconvex lower-level objective that satisfies the Polyak-Łojasiewicz (PL) condition.
872, Enhancing Robotic Program Synthesis Through Environmental Context
Tianyi Chen; Qidi Wang; Zhen Dong; Liwei Shen; Xin Peng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a framework that learns to synthesize a program by rectifying potentially erroneous code segments, with the aid of partially observed environments.
873, An Iterative Self-Learning Framework for Medical Domain Generalization
Zhenbang Wu; Huaxiu Yao; David Liebovitz; Jimeng Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, each patient domain exhibits distinct clinical characteristics, making it sub-optimal to train a single model for all domains. To overcome these limitations, we propose SLGD, a self-learning framework that iteratively discovers decoupled domains and trains personalized classifiers for each decoupled domain.
874, CoDrug: Conformal Drug Property Prediction with Density Estimation Under Covariate Shift
Siddhartha Laghuvarapu; Zhen Lin; Jimeng Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the exchangeability assumption of CP is often challenged with covariate shift in drug discovery tasks: Most datasets contain limited labeled data, which may not be representative of the vast chemical space from which molecules are drawn. To address this limitation, we propose a method called CoDrug that employs an energy-based model leveraging both training data and unlabelled data, and Kernel Density Estimation (KDE) to assess the densities of a molecule set.
875, CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation
Chaoqi Chen; Luyao Tang; Yue Huang; Xiaoguang Han; Yizhou Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we delve into a more general but difficult problem termed Open Test-Time DG (OTDG), where both domain shift and open class may occur on the unseen test data.
876, Learning List-Level Domain-Invariant Representations for Ranking
Ruicheng Xian; Honglei Zhuang; Zhen Qin; Hamed Zamani; Jing Lu; Ji Ma; Kai Hui; Han Zhao; Xuanhui Wang; Michael Bendersky;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we revisit invariant representation learning on ranking problem.
877, Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
Pengfei Li; Jianyi Yang; Adam Wierman; Shaolei Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel machine learning (ML) augmented online algorithm, Robustness-Constrained Learning (RCL), which combines untrusted ML predictions with a trusted expert online algorithm via constrained projection to robustify the ML prediction.
878, Anytime-Constrained Reinforcement Learning with Policy Prior
Jianyi Yang; Pengfei Li; Tongxin Li; Adam Wierman; Shaolei Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new algorithm, called Anytime-Constrained Reinforcement Learning (ACRL), which provably guarantees the anytime cost constraints.
879, Newton–Cotes Graph Neural Networks: On The Time Evolution of Dynamic Systems
Lingbing Guo; Weiqing Wang; Zhuo Chen; Ningyu Zhang; Zequn Sun; Yixuan Lai; Qiang Zhang; Huajun Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, their integrand is constant w.r.t. time. Inspired by this observation, we propose a new approach to predict the integration based on several velocity estimations with Newton–Cotes formulas and prove its effectiveness theoretically.
880, Scalable Transformer for PDE Surrogate Modeling
Zijie Li; Dule Shu; Amir Barati Farimani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Factorized Transformer (FactFormer), which is based on an axial factorized kernel integral.
881, TexQ: Zero-shot Network Quantization with Texture Feature Distribution Calibration
Xinrui Chen; Yizhi Wang; Renao YAN; Yiqing Liu; Tian Guan; Yonghong He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the conventional synthetic samples fail to retain the detailed texture feature distributions, which severely limits the knowledge transfer and performance of the quantized model. In this paper, a novel ZSQ method, TexQ is proposed to address this issue.
882, Learning Invariant Molecular Representation in Latent Discrete Space
Xiang Zhuang; Qiang Zhang; Keyan Ding; Yatao Bian; Xiao Wang; Jingsong Lv; Hongyang Chen; Huajun Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing methods suffer from poor out-of-distribution (OOD) generalization, particularly when data for training and testing originate from different environments. To address this issue, we propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts.
883, CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss
Rakshith Sharma Srinivasa; Jaejin Cho; Chouchang Yang; Yashas Malur Saidutta; Ching-Hua Lee; Yilin Shen; Hongxia Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, similarity amongst training examples has a more continuous nature, thus calling for a more `non-binary' treatment. To address this, we propose a new contrastive loss function called Continuously Weighted Contrastive Loss (CWCL) that employs a continuous measure of similarity.
884, CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes
Yulei Qin; Xingyu Chen; Yunhang Shen; Chaoyou Fu; Yun Gu; Ke Li; Xing Sun; Rongrong Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Cross-modality Aligned Prototypes (CAPro), a unified prototypical contrastive learning framework to learn visual representations with correct semantics.
885, Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models
Qiong Wu; Wei Yu; Yiyi Zhou; Shubin Huang; Xiaoshuai Sun; Rongrong Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we aim at parameter and computation efficient transfer learning (PCETL) for VLP models.
886, Improving Adversarial Robustness Via Information Bottleneck Distillation
Huafeng Kuang; Hong Liu; Shin'ichi Satoh; Yongjian Wu; Rongrong Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we further take a closer look at the information bottleneck principle and show that specially designed robust distillation can boost information bottleneck, benefiting from the prior knowledge of a robust pre-trained model. Therefore, we present the Information Bottleneck Distillation (IBD) approach.
887, Better with Less: A Data-Centric Prespective on Pre-Training Graph Neural Networks
Jiarong Xu; Renhong Huang; XIN JIANG; Yuxuan Cao; Carl Yang; Chunping Wang; YANG YANG;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, however, we identify the curse of big data phenomenon in graph pre-training: more training data do not necessarily lead to better performance. Motivated by this observation, we propose a better-with-less framework for graph pre-training: fewer, but carefully choosen data are fed into a GNN model to enhance pre-training.
888, DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting
Salva Rühling Cachay; Bo Zhao; Hailey Joren; Rose Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose an approach for training diffusion models for dynamics forecasting that leverages the temporal dynamics encoded in the data, directly coupling it with the diffusion steps in the network.
889, Diffusion Schrödinger Bridge Matching
Yuyang Shi; Valentin De Bortoli; Andrew Campbell; Arnaud Doucet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce Iterative Markovian Fitting (IMF), a new methodology for solving SB problems, and Diffusion Schrödinger Bridge Matching (DSBM), a novel numerical algorithm for computing IMF iterates.
890, Convolutional Visual Prompts for Self-Supervised Adaptation on Out-of-Distribution Data
Yun-Yun Tsai; Chengzhi Mao; Junfeng Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel approach, convolutional visual prompts (\textit{CVP}), for test-time adaptation without labels.
891, FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation
Yuanxin Liu; Lei Li; Shuhuai Ren; Rundong Gao; Shicheng Li; Sishuo Chen; Xu Sun; Lu Hou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although some benchmarks have categorized the prompts, their categorization either only focuses on a single aspect or fails to consider the temporal information in video generation. Secondly, it is unclear whether the automatic evaluation metrics are consistent with human standards. To address these problems, we propose \textbf{FETV}, a benchmark for \textbf{F}ine-grained \textbf{E}valuation of \textbf{T}ext-to-\textbf{V}ideo generation.
892, Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation
Jaemin Cho; Abhay Zala; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While existing work focuses on equipping LMs with visual understanding, we propose two novel interpretable/explainable visual programming frameworks for T2I generation and evaluation.
893, PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation
Jialu Li; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One main challenge in Vision-and-Language Navigation is the limited availability of photorealistic training environments, which makes it hard to generalize to new and unseen environments. To address this problem, we propose PanoGen, a generation method that can potentially create an infinite number of diverse panoramic environments conditioned on text.
894, Effective Human-AI Teams Via Learned Natural Language Rules and Onboarding
Hussein Mozannar; Jimin Lee; Dennis Wei; Prasanna Sattigeri; Subhro Das; David Sontag;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose to learn rules grounded in data regions and described in natural language that illustrate how the human should collaborate with the AI agent.
895, DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization
Haoran Ye; Jiarui Wang; Zhiguang Cao; Helan Liang; Yong Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose DeepACO, a generic framework leveraging deep reinforcement learning to automate heuristic designs.
896, Kiki or Bouba? Sound Symbolism in Vision-and-Language Models
Morris Alper; Hadar Averbuch-Elor;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address the question of whether sound symbolism is reflected in vision-and-language models such as CLIP and Stable Diffusion.
897, Dynamic Personalized Federated Learning with Adaptive Differential Privacy
Xiyuan Yang; Wenke Huang; Mang Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Considering that Fisher information values can serve as an effective measure for estimating the information content of parameters by reflecting the model sensitivity to parameters, we aim to leverage this property to address the aforementioned challenges. In this paper, we propose a novel adaptive method for DP-PFL to handle these challenges.
898, SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
Mengyu Wang; Henghui Ding; Jun Hao Liew; Jiajun Liu; Yao Zhao; Yunchao Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore a principal way to enhance the quality of object masks generated by different segmentation models.
899, Automatic Integration for Spatiotemporal Neural Point Processes
Zihao Zhou; Rose Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel paradigm: `AutoSTPP` (Automatic Integration for Spatiotemporal Neural Point Processes) that extends the AutoInt approach to 3D STPP.
900, Using Causal Context to Select Algorithmic Fairness Metrics
Jacy Anthis; Victor Veitch;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: On the other hand, counterfactual fairness is a widely intuitive and appealing standard, such as in the U.S. legal system, but its use is limited because, by definition, the counterfactuals it is based on cannot be directly observed in real-world data. In this project, we bridge the conceptual gap between these two paradigms.
901, Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects
Zhuofan Ying; Peter Hase; Mohit Bansal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we investigate how vision models adaptively use context for out-of-distribution (OOD) generalization and leverage our analysis results to improve model OOD generalization.
902, Adversarially Robust Distributed Count Tracking Via Partial Differential Privacy
Zhongzheng Xiong; Xiaoyi Zhu; zengfeng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the distributed tracking model, also known as distributed functional monitoring.
903, Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees
Sharan Vaswani; Amirreza Kazemi; Reza Babanezhad Harikandeh; Nicolas Le Roux;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The critic is usually trained by minimizing the TD error, an objective that is potentially decorrelated with the true goal of achieving a high reward with the actor. We address this mismatch by designing a joint objective for training the actor and critic in a decision-aware fashion.
904, RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments
Mengxue Qu; Yu Wu; Wu Liu; Xiaodan Liang; Jingkuan Song; Yao Zhao; Yunchao Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Previous work in this area is limited either by the number of intention descriptions or by the affordance vocabulary available for intention objects. These limitations make it challenging to handle intentions in open environments effectively. To facilitate this research, we construct a comprehensive dataset called Reasoning Intention-Oriented Objects (RIO).
905, Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach
Haoxuan Li; Kunhan Wu; Chunyuan Zheng; Yanghao Xiao; Hao Wang; Fuli Feng; Xiangnan He; Zhi Geng; Peng Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we first perform theoretical analysis to reveal the possible failure of previous approaches, including propensity-based, multi-task learning, and bi-level optimization methods, in achieving unbiased learning when hidden confounding is present. Then, we propose a unified multi-task learning approach to remove hidden confounding, which uses a few unbiased ratings to calibrate the learned nominal propensities and nominal error imputations from biased data.
906, Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
Divin Yan; Gengchen Wei; Chen Yang; Shengzhong Zhang; zengfeng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data.
907, Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching Via Unsupervised Functional Map Regularized Reconstruction
Souhaib Attaiki; Maks Ovsjanikov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Shape Non-rigid Kinematics (SNK), a novel zero-shot method for non-rigid shape matching that eliminates the need for extensive training or ground truth data.
908, Uncovering Meanings of Embeddings Via Markov Boundaries
Yibo Jiang; Bryon Aragam; Victor Veitch;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the role of partial orthogonality in encoding meanings by searching for ``meaningful'' subspaces of an embedding spanned by other embeddings, which generalizes the notion of Markov boundaries in Euclidean space.
909, SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data
BANG AN; Xun Zhou; YONGJIAN ZHONG; Tianbao Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we bridge the gap by proposing a novel spatial event ranking approach named SpatialRank.
910, Disentangling Voice and Content with Self-Supervision for Speaker Recognition
TIANCHI LIU; Kong Aik Lee; Qiongqiong Wang; Haizhou Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech.
911, Multi-modal Queried Object Detection in The Wild
Yifan Xu; Mengdan Zhang; Chaoyou Fu; Peixian Chen; Xiaoshan Yang; Ke Li; Changsheng Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce MQ-Det, an efficient architecture and pre-training strategy design to utilize both textual description with open-set generalization and visual exemplars with rich description granularity as category queries, namely, Multi-modal Queried object Detection, for real-world detection with both open-vocabulary categories and various granularity.
912, InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion
Ziming Zhang; Fangzhou Lin; Yun Yue; Songlin Hou; Kazunori Yamada; Vijaya Kolachalama; Venkatesh Saligrama;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Chamfer distance (CD) is a popular metric and training loss to measure the distances between point clouds, but also well known to be sensitive to outliers. To address this issue, in this paper we propose InfoCD, a novel contrastive Chamfer distance loss to learn to spread the matched points for better distribution alignments between point clouds as well as accounting for a surface similarity estimator.
913, Mitigating Over-smoothing in Transformers Via Regularized Nonlocal Functionals
Tam Nguyen; Tan Nguyen; Richard Baraniuk;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that self-attention layers in transformers minimize a functional which promotes smoothness, thereby causing token uniformity.
914, Offline Reinforcement Learning with Differential Privacy
Dan Qiao; Yu-Xiang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the learned policy could retain sensitive information of individuals in the training data (e.g., treatment and outcome of patients), thus susceptible to various privacy risks. We design offline RL algorithms with differential privacy guarantees which provably prevent such risks.
915, On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds
David Woodruff; Fred Zhang; Samson Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study robust algorithms for the experts problem under memory constraints.
916, Near-Optimal $k$-Clustering in The Sliding Window Model
David Woodruff; Peilin Zhong; Samson Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we give the first algorithm that achieves near-optimal $(1+\varepsilon)$-approximation to $(k,z)$-clustering in the sliding window model.
917, Injecting Multimodal Information Into Rigid Protein Docking Via Bi-level Optimization
Ruijia Wang; YiWu Sun; Yujie Luo; Cheng Yang; Shaochuan Li; Xingyi Cheng; Hui Li; Chuan Shi; Le Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose BiDock, a novel rigid docking model that effectively integrates sequence- and structure-modal information through bi-level optimization.
918, Neural Polarizer: A Lightweight and Effective Backdoor Defense Via Purifying Poisoned Features
Mingli Zhu; Shaokui Wei; Baoyuan Wu; Hongyuan Zha;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the mechanism of the optical polarizer that a polarizer could pass light waves with particular polarizations while filtering light waves with other polarizations, we propose a novel backdoor defense method by inserting a learnable neural polarizer into the backdoored model as an intermediate layer, in order to purify the poisoned sample via filtering trigger information while maintaining benign information.
919, HAIDNet: Encoding Human Behavior in Automated Information Design
Guanghui Yu; Wei Tang; Saumik Narayanan; Chien-Ju Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose HAIDNet, a neural-network-based optimization framework for information design that can adjust to multiple representations of human behavior.
920, REx: Data-Free Residual Quantization Error Expansion
Edouard YVINEC; Arnaud Dapogny; Matthieu Cord; Kevin Bailly;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, to adapt to a variety of devices, a quantization method shall be flexible enough to find good accuracy v.s. speed trade-offs for every bit width and target device. To achieve this, we propose REx, a quantization method that leverages residual error expansion, along with group sparsity.
921, GEO-Bench: Toward Foundation Models for Earth Monitoring
Alexandre Lacoste; Nils Lehmann; Pau Rodriguez; Evan Sherwin; Hannah Kerner; Björn Lütjens; Jeremy Irvin; David Dao; Hamed Alemohammad; Alexandre Drouin; Mehmet Gunturkun; Gabriel Huang; David Vazquez; Dava Newman; Yoshua Bengio; Stefano Ermon; Xiaoxiang Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To stimulate the development of foundation models for Earth monitoring, we propose a benchmark comprised of six classification and six segmentation tasks, which were carefully curated and adapted to be both relevant to the field and well-suited for model evaluation.
922, MedSat: A Public Health Dataset Featuring Satellite Imagery and Medical Prescriptions
Sanja Scepanovic; Ivica Obadic; Sagar Joglekar; Laura GIUSTARINI; Cristiano Nattero; Daniele Quercia; Xiaoxiang Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For the years 2019 (pre-COVID) and 2020 (COVID), we collected spatio-temporal indices for all Lower Layer Super Output Areas in England.
923, HeadSculpt: Crafting 3D Head Avatars with Text
Xiao Han; Yukang Cao; Kai Han; Xiatian Zhu; Jiankang Deng; Yi-Zhe Song; Tao Xiang; Kwan-Yee K. Wong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is primarily due to the inherited limitations from the pre-trained 2D image diffusion models, which become more pronounced when it comes to 3D head avatars. In this work, we address these challenges by introducing a versatile coarse-to-fine pipeline dubbed HeadSculpt for crafting (i.e., generating and editing) 3D head avatars from textual prompts.
924, SPRING: Studying Papers and Reasoning to Play Games
Yue Wu; So Yeon Min; Shrimai Prabhumoye; Yonatan Bisk; Russ Salakhutdinov; Amos Azaria; Tom Mitchell; Yuanzhi Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM).
925, Learning to Tokenize for Generative Retrieval
Weiwei Sun; Lingyong Yan; Zheng Chen; Shuaiqiang Wang; Haichao Zhu; Pengjie Ren; Zhumin Chen; Dawei Yin; Maarten Rijke; Zhaochun Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, this paper proposes a novel document tokenization learning method--GenRet, which learns to encode the complete document semantics into docids.
926, Evaluating Self-Supervised Learning for Molecular Graph Embeddings
Hanchen Wang; Jean Kaddour; Shengchao Liu; Jian Tang; Joan Lasenby; Qi Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This broad applicability complicates their evaluation. Addressing this challenge, we present Molecular Graph Representation Evaluation (MOLGRAPHEVAL), generating detailed profiles of molecular graph embeddings with interpretable and diversified attributes.
927, Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning
Yihua Zhang; Yimeng Zhang; Aochuan Chen; jinghan jia; Jiancheng Liu; Gaowen Liu; Mingyi Hong; Shiyu Chang; Sijia Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we aim to address the problem of DP for transfer learning, i.e., how to prune a source dataset for improved pretraining efficiency and lossless finetuning accuracy on downstream target tasks.
928, Model Sparsity Can Simplify Machine Unlearning
jinghan jia; Jiancheng Liu; Parikshit Ram; Yuguang Yao; Gaowen Liu; Yang Liu; PRANAY SHARMA; Sijia Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Moving beyond data-centric MU approaches, our study introduces a novel model-based perspective: model sparsification via weight pruning, which is capable of reducing the gap between exact unlearning and approximate unlearning.
929, YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis
Andy Zhou; Samuel Li; Pranav Sriram; Xiang Li; Jiahua Dong; Ansh Sharma; Yuanyi Zhong; Shirui Luo; Volodymyr Kindratenko; George Heintz; Christopher Zallek; Yu-Xiong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on our benchmark, we propose three challenging and complementary tasks encompassing both discriminative and generative tasks, along with a comprehensive set of corresponding baselines.
930, On The Robustness of Removal-Based Feature Attributions
Chris Lin; Ian Covert; Su-In Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we prove upper bounds for the difference between intact and perturbed removal-based attributions, under both settings of input and model perturbation.
931, Feature Selection in The Contrastive Analysis Setting
Ethan Weinberger; Ian Covert; Su-In Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we present CFS (Contrastive Feature Selection), a method for performing feature selection in the CA setting.
932, Robust Lipschitz Bandits to Adversarial Corruptions
Yue Kang; Cho-Jui Hsieh; Thomas Chun Man Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a new problem of Lipschitz bandits in the presence of adversarial corruptions where an adaptive adversary corrupts the stochastic rewards up to a total budget $C$.
933, ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling
Quanyi Li; Zhenghao Peng; Lan Feng; Zhizheng Liu; Chenda Duan; Wenjie Mo; Bolei Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present ScenarioNet, an open-source platform for large-scale traffic scenario modeling and simulation.
934, A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories
Kai Yan; Alex Schwing; Yu-Xiong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the issue, in this paper, we propose Trajectory-Aware Imitation Learning from Observations (TAILO).
935, Learning from Active Human Involvement Through Proxy Value Propagation
Zhenghao Peng; Wenjie Mo; Chenda Duan; Quanyi Li; Bolei Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a new reward-free active human involvement method called Proxy Value Propagation for policy optimization.
936, HASSOD: Hierarchical Adaptive Self-Supervised Object Detection
Shengcao Cao; Dhiraj Joshi; Liangyan Gui; Yu-Xiong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The human visual perception system demonstrates exceptional capabilities in learning without explicit supervision and understanding the part-to-whole composition of objects. Drawing inspiration from these two abilities, we propose Hierarchical Adaptive Self-Supervised Object Detection (HASSOD), an innovative approach that learns to detect objects and understand their compositions without human supervision.
937, RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks
Haonan Yan; Wenjing Zhang; Qian Chen; Xiaoguang Li; Wenhai Sun; HUI LI; Xiaodong Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel defense including detection and aggregation, named RECESS, to serve as a “vaccine” for FL against model poisoning attacks.
938, Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization Across Threat Models
Naman Deep Singh; Francesco Croce; Matthias Hein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Given the recent debate about whether transformers are more robust than convnets, we revisit adversarial training on ImageNet comparing ViTs and ConvNeXts.
939, PreDiff: Precipitation Nowcasting with Latent Diffusion Models
Zhihan Gao; Xingjian Shi; Boran Han; Hao Wang; Xiaoyong Jin; Danielle Maddix; Yi Zhu; Yuyang (Bernie) Wang; Mu Li; Dit-Yan Yeung;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, most state-of-the-art DL approaches for Earth system forecasting lack the ability to handle uncertainty or are intrinsically deterministic. To address these limitations and enhance operational applicability, we propose *PreDiff*, a conditional latent diffusion model for probabilistic spatiotemporal forecasting.
940, XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information
Zitao Liu; Qiongqiong Liu; Teng Guo; Jiahao Chen; Shuyan Huang; Xiangyu Zhao; Jiliang Tang; Weiqi Luo; Jian Weng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, although the educational contexts contain various factors that may have an influence on student learning outcomes, existing public KT datasets mainly consist of anonymized ID-like features, which may hinder the research advances towards this field. Therefore, in this work, we present, \emph{XES3G5M}, a large-scale dataset with rich auxiliary information about questions and their associated knowledge components (KCs)\footnote{\label{ft:kc}A KC is a generalization of everyday terms like concept, principle, fact, or skill.}
941, MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
Jianfei Yang; He Huang; Yunjiao Zhou; Xinyan Chen; Yuecong Xu; Shenghai Yuan; Han Zou; Chris Xiaoxuan Lu; Lihua Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose MM-Fi, the first multi-modal non-intrusive 4D human dataset with 27 daily or rehabilitation action categories, to bridge the gap between wireless sensing and high-level human perception tasks.
942, Normalization Layers Are All That Sharpness-Aware Minimization Needs
Maximilian Mueller; Tiffany Vlaar; David Rolnick; Matthias Hein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we show that perturbing only the affine normalization parameters (comprising less than 0.1% of the total parameters) in the adversarial step of SAM outperforms perturbing all of the parameters.
943, Seeing Is Not Always Believing: Benchmarking Human and Model Perception of AI-Generated Images
Zeyu Lu; Di Huang; LEI BAI; Jingjing Qu; Chengyue Wu; Xihui Liu; Wanli Ouyang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This study aims to comprehensively evaluate agents for distinguishing state-of-the-art AI-generated visual content.
944, Model-enhanced Vector Index
Hailin Zhang; Yujing Wang; Qi Chen; Ruiheng Chang; Ting Zhang; Ziming Miao; Yingyan Hou; Yang Ding; Xupeng Miao; Haonan Wang; Bochen Pang; Yuefeng Zhan; Hao Sun; Weiwei Deng; Qi Zhang; Fan Yang; Xing Xie; Mao Yang; Bin CUI;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we aim to enhance the vector index with end-to-end deep neural networks, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency.
945, Improving Diffusion-Based Image Synthesis with Context Prediction
Ling Yang; Jingwei Liu; Shenda Hong; Zhilong Zhang; Zhilin Huang; Zheming Cai; Wentao Zhang; Bin CUI;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a powerful source of automatic supervisory signal, context has been well studied for learning representations. Inspired by this, we for the first time propose ConPreDiff to improve diffusion-based image synthesis with context prediction.
946, Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
Hao Li; Jingkuan Song; Lianli Gao; Xiaosu Zhu; Hengtao Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
947, Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
Sai Aparna Aketi; Abolfazl Hashemi; Kaushik Roy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we focus on designing a decentralized learning algorithm that is less susceptible to variations in data distribution across devices.
948, Contextual Stochastic Bilevel Optimization
Yifan Hu; Jie Wang; Yao Xie; Andreas Krause; Daniel Kuhn;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Due to the presence of contextual information, existing single-loop methods for classical stochastic bilevel optimization are unable to converge. To overcome this challenge, we introduce an efficient double-loop gradient method based on the Multilevel Monte-Carlo (MLMC) technique and establish its sample and computational complexities.
949, Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
Changyu CHEN; Ramesha Karunasena; Thanh Nguyen; Arunesh Sinha; Pradeep Varakantham;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Also, these problems require validity of the realized action (allocation); this validity constraint is often difficult to express compactly in a closed mathematical form. In this work, we address these issues by (1) using a (state) conditional normalizing flow to compactly represent the stochastic policy; the compactness arises due to the network only producing one sampled action and log probability of the action, which is then used by an actor-critic method.
950, Low Tensor Rank Learning of Neural Dynamics
Arthur Pellegrino; N Alex Cayco Gajic; Angus Chadwick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By fitting RNNs of varying rank to large-scale neural recordings during a motor learning task, we find that the inferred weights are low-tensor-rank and therefore evolve over a fixed low-dimensional subspace throughout the entire course of learning. We next validate the observation of low-tensor-rank learning on an RNN trained to solve the same task by performing a low-tensor-rank decomposition directly on the ground truth weights, and by showing that the method we applied to the data faithfully recovers this low rank structure.
951, Prompt-augmented Temporal Point Process for Streaming Event Sequence
Siqiao Xue; Yan Wang; Zhixuan Chu; Xiaoming Shi; Caigao JIANG; Hongyan Hao; Gangwei Jiang; Xiaoyun Feng; James Zhang; Jun Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Under the privacy and memory constraints commonly seen in real scenarios, how to continuously monitor a TPP to learn the streaming event sequence is an important yet under-investigated problem. In this work, we approach this problem by adopting Continual Learning (CL), which aims to enable a model to continuously learn a sequence of tasks without catastrophic forgetting.
952, Improved Frequency Estimation Algorithms with and Without Predictions
Anders Aamand; Justin Chen; Huy Nguyen; Sandeep Silwal; Ali Vakilian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The work of Hsu et al.~(2019) introduced the idea of using machine learning to tailor sketching algorithms to the specific data distribution they are being run on. In particular, their learning-augmented frequency estimation algorithm uses a learned heavy-hitter oracle which predicts which elements will appear many times in the stream. We give a novel algorithm, which in some parameter regimes, already theoretically outperforms the learning based algorithm of Hsu et al. *without* the use of any predictions.
953, A Constant-Factor Approximation for Individual Preference Stable Clustering
Anders Aamand; Justin Chen; Allen Liu; Sandeep Silwal; Pattara Sukprasert; Ali Vakilian; Fred Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, before this work, it was unknown if an $o(n)$-IP stable clustering always exists, as the prior state of the art only guaranteed an $O(n)$-IP stable clustering. We close this gap in understanding and show that an $O(1)$-IP stable clustering always exists for general metrics, and we give an efficient algorithm which outputs such a clustering.
954, DiffUTE: Universal Text Editing Diffusion Model
Haoxing Chen; Zhuoer Xu; Zhangxuan Gu; jun lan; 行 郑; Yaohui Li; Changhua Meng; Huijia Zhu; Weiqiang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing state-of-the-art diffusion models struggle with rendering correct text and text style during generation. To tackle this problem, we propose a universal self-supervised text editing diffusion model (DiffUTE), which aims to replace or modify words in the source image with another one while maintaining its realistic appearance.
955, Brain Encoding Models Based on Multimodal Transformers Can Transfer Across Language and Vision
Jerry Tang; Meng Du; Vy Vo; VASUDEV LAL; Alexander Huth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we used representations from multimodal transformers to train encoding models that can transfer across fMRI responses to stories and movies.
956, Near-Linear Time Algorithm for The Chamfer Distance
Ainesh Bakshi; Piotr Indyk; Rajesh Jayaram; Sandeep Silwal; Erik Waingarten;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the \emph{quadratic} dependence on $n$ in the running time makes the naive approach intractable for large datasets. We overcome this bottleneck and present the first $(1+\epsilon)$-approximate algorithm for estimating Chamfer distance with a near-linear running time.
957, Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing
Nived Rajaraman; Fnu Devvrit; Aryan Mokhtari; Kannan Ramchandran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although the above pipeline, which we refer to as pruning + fine-tuning, has been extremely successful in lowering the complexity of trained models, there is very little known about the theory behind this success. In this paper we address this issue by investigating the pruning + fine-tuning framework on the overparameterized matrix sensing problem with the ground truth denoted $U_\star \in \mathbb{R}^{d \times r}$ and the overparameterized model $U \in \mathbb{R}^{d \times k}$ with $k \gg r$.
958, GlyphControl: Glyph Conditional Controllable Visual Text Generation
Yukang Yang; Dongnan Gui; YUHUI YUAN;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, instead of relying on character-aware text encoders like ByT5 and retraining text-to-image models, we propose a more efficient and powerful approach called GlyphControl.
959, Probabilistic Invariant Learning with Randomized Linear Classifiers
Leonardo Cotta; Gal Yehuda; Assaf Schuster; Chris Maddison;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show how to leverage randomness and design models that are both expressive and invariant but use less resources.
960, Greatness in Simplicity: Unified Self-Cycle Consistency for Parser-Free Virtual Try-On
Chenghu Du; junyin Wang; Shuqing Liu; Shengwu Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Additionally, current garment deformation methods are unable to mimic the natural interaction between the garment and the human body in the real world, resulting in unrealistic alignment effects. To tackle these limitations, we present a new Unified Self-Cycle Consistency for Parser-Free virtual try-on Network (USC-PFN), which enables the robust translation between various garment domains using only a single generator and realistically mimics non-rigid geometric deformation of garments in real-life scenarios.
961, On The Minimax Regret for Online Learning with Feedback Graphs
Khaled Eldowa; Emmanuel Esposito; Tom Cesari; Nicolò Cesa-Bianchi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we improve on the upper and lower bounds for the regret of online learning with strongly observable undirected feedback graphs.
962, Faster Relative Entropy Coding with Greedy Rejection Coding
Gergely Flamich; Efstratios Markou; José Miguel Hernández-Lobato;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, despite their practical benefits, REC algorithms have not seen widespread application, due to their prohibitively slow runtimes or restrictive assumptions. In this paper, we make progress towards addressing these issues.
963, Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks
Tolga Ergen; Mert Pilanci;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we study the training problem of deep neural networks and introduce an analytic approach to unveil hidden convexity in the optimization landscape.
964, EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding
Shuhan Tan; Tushar Nagarajan; Kristen Grauman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent advances in egocentric video understanding models are promising, but their heavy computational expense is a barrier for many real-world applications. To address this challenge, we propose EgoDistill, a distillation-based approach that learns to reconstruct heavy ego-centric video clip features by combining the semantics from a sparse set of video frames with head motion from lightweight IMU readings.
965, Joint Training of Deep Ensembles Fails Due to Learner Collusion
Alan Jeffares; Tennison Liu; Jonathan Crabbé; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead, most previous research trains individual models independently with ensembling performed post hoc. In this work, we show that this is for good reason - joint optimization of ensemble loss results in degenerate behavior.
966, Online Learning of Long-range Dependencies
Nicolas Zucchet; Robert Meier; Simon Schug; Asier Mujika; Joao Sacramento;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we present a high-performance online learning algorithm that merely doubles the memory and computational requirements of a single inference pass.
967, Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
Samuel Hurault; Ulugbek Kamilov; Arthur Leclaire; Nicolas Papadakis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose two PnP algorithms based on the Bregman Score Denoiser for solving Poisson inverse problems.
968, Enhancing Generalization and Plasticity for Sample Efficient Reinforcement Learning
Hojoon Lee; Hanseul Cho; HYUNSEUNG KIM; DAEHOON GWAK; Joonkee Kim; Jaegul Choo; Se-Young Yun; Chulhee Yun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In response, we propose a combined usage of Sharpness-Aware Minimization (SAM) and a reset mechanism.
969, GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Haiteng Zhao; Shengchao Liu; Ma Chang; Hannan Xu; Jie Fu; Zhihong Deng; Lingpeng Kong; Qi Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We discover that existing molecule-text models perform poorly in this setting due to inadequate treatment of instructions and limited capacity for graphs. To overcome these issues, we propose GIMLET, which unifies language models for both graph and text data.
970, Dynamics of Temporal Difference Reinforcement Learning
Blake Bordelon; Paul Masset; Henry Kuo; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we use concepts from statistical physics, to study the typical case learning curves for temporal difference learning of a value function with linear function approximators.
971, Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
Junghyun Lee; Hanseul Cho; Se-Young Yun; Chulhee Yun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: On the theoretical side, we rigorously formulate fair PCA using a new notion called probably approximately fair and optimal (PAFO) learnability. On the practical side, motivated by recent advances in streaming algorithms for addressing memory limitation, we propose a new setting called fair streaming PCA along with a memory-efficient algorithm, fair noisy power method (FNPM).
972, Trajectory Alignment: Understanding The Edge of Stability Phenomenon Via Bifurcation Theory
Minhak Song; Chulhee Yun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we start by demonstrating through empirical studies that when the EoS phenomenon occurs, different GD trajectories (after a proper reparameterization) align on a specific bifurcation diagram determined solely by the loss function, independent of the network architecture, training data, and step size.
973, An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions
Mohammad Jalali; Cheuk Ting Li; Farzan Farnia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an information-theoretic diversity evaluation method for multi-modal underlying distributions.
974, KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs
Lujun Li; Peijie Dong; Anggeng Li; Zimian Wei; Ya Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel framework, KD-Zero, which utilizes evolutionary search to automatically discover promising distiller from scratch for any teacher-student architectures.
975, Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Jannik Kossen; Mark Collier; Basil Mustafa; Xiao Wang; Xiaohua Zhai; Lucas Beyer; Andreas Steiner; Jesse Berent; Rodolphe Jenatton; Effrosyni Kokiopoulou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Three Towers (3T), a flexible method to improve the contrastive learning of vision-language models by incorporating pretrained image classifiers.
976, Learning Environment-Aware Affordance for 3D Articulated Object Manipulation Under Occlusions
Ruihai Wu; Kai Cheng; Yan Zhao; Chuanruo Ning; Guanqi Zhan; Hao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an environment-aware affordance framework that incorporates both object-level actionable priors and environment constraints.
977, Towards Consistent Video Editing with Text-to-Image Diffusion Models
Zicheng Zhang; Bonan Li; Xuecheng Nie; Congying Han; Tiande Guo; Luoqi Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite of their low requirements of data and computation, these methods always generate editing results of unsatisfied consistency with text prompt as well as temporal sequence, limiting their applications in the real world. In this paper, we propose to address the above issue with a novel EI$^2$ model towards \textbf{E}nhancing v\textbf{I}deo \textbf{E}diting cons\textbf{I}stency of TTI-based frameworks.
978, Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
Masatoshi Uehara; Haruka Kiyohara; Andrew Bennett; Victor Chernozhukov; Nan Jiang; Nathan Kallus; Chengchun Shi; Wen Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods such as sequential importance sampling estimators and fitted-Q evaluation suffer from the curse of horizon in POMDPs. To circumvent this problem, we develop a novel model-free OPE method by introducing future-dependent value functions that take future proxies as inputs.
979, Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
Tianhe Wu; Shuwei Shi; Haoming Cai; Mingdeng Cao; Jing Xiao; Yinqiang Zheng; Yujiu Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we propose a generalized Recursive Probability Sampling (RPS) method for the BOIQA task, combining content and detailed information to generate multiple pseudo viewport sequences from a given starting point.
980, Gradient-Based Feature Learning Under Structured Data
Alireza Mousavi-Hosseini; Denny Wu; Taiji Suzuki; Murat Erdogdu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate the effect of a spiked covariance structure and reveal several interesting phenomena.
981, Payoff-based Learning with Matrix Multiplicative Weights in Quantum Games
Kyriakos Lotidis; Panayotis Mertikopoulos; Nicholas Bambos; Jose Blanchet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the problem of learning in quantum games with scalar, payoff-based feedback.
982, Fantastic Robustness Measures: The Secrets of Robust Generalization
Hoki Kim; Jinseong Park; Yujin Choi; Jaewook Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address this issue, various measures have been developed, including margin, smoothness, and flatness-based measures, to understand and improve robust generalization. In this study, we present a large-scale analysis of robust generalization to empirically verify whether the relationship between these measures and robust generalization remains valid in diverse settings.
983, Stable Backdoor Purification with Feature Shift Tuning
Rui Min; Zeyu Qin; Li Shen; Minhao Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although a line of defense methods is proposed to mitigate this threat, they either require complicated modifications to the training process or heavily rely on the specific model architecture, which makes them hard to be deployed into real-world applications. Therefore, in this paper, we instead start with fine-tuning, one of the most common and easy-to-deploy backdoor defenses, through comprehensive evaluations against diverse attack scenarios.
984, Better Private Linear Regression Through Better Private Feature Selection
Travis Dick; Jennifer Gillenwater; Matthew Joseph;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent work has attempted to develop solutions that shift these burdens from users to algorithms, but they struggle to provide utility as the feature dimension grows. This work extends these algorithms to higher-dimensional problems by introducing a differentially private feature selection method based on Kendall rank correlation.
985, Replicable Clustering
Hossein Esfandiari; Amin Karbasi; Vahab Mirrokni; Grigoris Velegkas; Felix Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: According to this definition, a clustering algorithm is replicable if, with high probability, its output induces the exact same partition of the sample space after two executions on different inputs drawn from the same distribution, when its internal randomness is shared across the executions. We propose such algorithms for the statistical $k$-medians, statistical $k$-means, and statistical $k$-centers problems by utilizing approximation routines for their combinatorial counterparts in a black-box manner.
986, Benchmarking Foundation Models with Language-Model-as-an-Examiner
Yushi Bai; Jiahao Ying; Yixin Cao; Xin Lv; Yuze He; Xiaozhi Wang; Jifan Yu; Kaisheng Zeng; Yijia Xiao; Haozhe Lyu; Jiayin Zhang; Juanzi Li; Lei Hou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Most of these works focus on proposing new datasets, however, we see two main issues within previous benchmarking pipelines, namely testing leakage and evaluation automation. In this paper, we propose a novel benchmarking framework, Language-Model-as-an-Examiner, where the LM serves as a knowledgeable examiner that formulates questions based on its knowledge and evaluates responses in a reference-free manner.
987, DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning
kangyang Luo; Shuai Wang; Yexuan Fu; Xiang Li; Yunshi Lan; Ming Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, how to learn a robust global model in the data-heterogeneous and model-heterogeneous FL scenarios is challenging. To address it, we resort to data-free knowledge distillation to propose a new FL method (namely DFRD).
988, A Rigorous Link Between Deep Ensembles and (Variational) Bayesian Methods
Veit David Wild; Sahra Ghalebikesabi; Dino Sejdinovic; Jeremias Knoblauch;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: On a technical level, our contribution amounts to studying generalised variational inference through the lense of Wasserstein gradient flows.
989, An Empirical Investigation of The Role of Pre-training in Lifelong Learning
Sanket Vaibhav Mehta; Darshan Patil; Sarath Chandar; Emma Strubell;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We investigate existing methods in the context of large, pre-trained models and evaluate their performance on a variety of text and image classification tasks, including a large-scale study using a novel data set of 15 diverse NLP tasks.
990, Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks
Blake Bordelon; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We analyze the dynamics of finite width effects in wide but finite feature learning neural networks.
991, On The (Non-)Convergence of Sharpness-Aware Minimization
Dongkuk Si; Chulhee Yun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing studies prove convergence of SAM for smooth functions, but they do so by assuming decaying perturbation size $\rho$ and/or no gradient normalization in $y_t$, which is detached from practice. To address this gap, we study deterministic/stochastic versions of SAM with practical configurations (i.e., constant $\rho$ and gradient normalization in $y_t$ and explore their convergence properties on smooth functions with (non)convexity assumptions.
992, Learning DAGs from Data with Few Root Causes
Panagiotis Misiakos; Chris Wendler; Markus Püschel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel perspective and algorithm for learning directed acyclic graphs (DAGs) from data generated by a linear structural equation model (SEM).
993, Add and Thin: Diffusion for Temporal Point Processes
David Lüdke; Marin Biloš; Oleksandr Shchur; Marten Lienen; Stephan Günnemann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By deriving a probabilistic diffusion model for TPPs, we propose ADD-THIN, a new framework that naturally handles the continuous and discrete nature of point processes and directly models whole event sequences.
994, Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage
Masatoshi Uehara; Nathan Kallus; Jason Lee; Wen Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast to numerous offline RL algorithms that necessitate the uniform coverage of the offline data over state and action space, we propose value-based algorithms with PAC guarantees under partial coverage, specifically, coverage of offline data against a single policy, and realizability of soft Q-function (a.k.a., entropy-regularized Q-function) and another function, which is defined as a solution to a saddle point of certain minimax optimization problem).
995, Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions
Abhineet Agarwal; Anish Agarwal; Suhas Vijaykumar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We consider a setting where there are $N$ heterogeneous units and $p$ interventions. Our goal is to learn unit-specific potential outcomes for any combination of these $p$ interventions, i.e., $N \times 2^p$ causal parameters.
996, Regret Matching$^+$: (In)Stability and Fast Convergence in Games
Gabriele Farina; Julien Grand-Clément; Christian Kroer; Chung-Wei Lee; Haipeng Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We then provide two fixes: restarting and chopping off the positive orthant that RM$^+$ works in. We show that these fixes are sufficient to get $O(T^{1/4})$ individual regret and $O(1)$ social regret in normal-form games via RM$^+$ with predictions.
997, Let The Flows Tell: Solving Graph Combinatorial Problems with GFlowNets
Dinghuai Zhang; Hanjun Dai; Nikolay Malkin; Aaron Courville; Yoshua Bengio; Ling Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space.
998, Papt: A Pairwise GUI Dataset Between Android Phones and Tablets
han hu; Haolan Zhan; Yujin Huang; Di Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This poses a significant barrier to the employment of deep learning in automated GUI development. In this paper, we introduce the Papt dataset, a pioneering pairwise GUI dataset tailored for Android phones and tablets, encompassing 10,035 phone-tablet GUI page pairs sourced from 5,593 unique app pairs.we propose novel pairwise GUI collection approaches for constructing this dataset and delineate its advantages over currently prevailing datasets in the field.
999, Joint Data-Task Generation for Auxiliary Learning
Hong Chen; Xin Wang; Yuwei Zhou; Yijian Qin; Chaoyu Guan; Wenwu Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To tackle the problem, we propose a joint data-task generation framework for auxiliary learning (DTG-AuxL), which can bring benefits to the primary task by generating the new auxiliary data and task in a joint manner.
1000, Spectral Invariant Learning for Dynamic Graphs Under Distribution Shifts
Zeyang Zhang; Xin Wang; Ziwei Zhang; Zhou Qin; Weigao Wen; Hui Xue'; Haoyang Li; Wenwu Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we discover that there exist cases with distribution shifts unobservable in the time domain while observable in the spectral domain, and propose to study distribution shifts on dynamic graphs in the spectral domain for the first time.
1001, Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum
Yijian Qin; Xin Wang; Ziwei Zhang; Hong Chen; Wenwu Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, multi-task GraphNAS capable of handling multiple tasks simultaneously has been largely unexplored in literature, posing great challenges to capture the complex relations and influences among different tasks. To tackle this problem, we propose a novel multi-task graph neural architecture search with task-aware collaboration and curriculum (MTGC3), which is able to simultaneously discover optimal architectures for different tasks and learn the collaborative relationships among different tasks in a joint manner.
1002, Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision
Zeyang Zhang; Xin Wang; Ziwei Zhang; Guangyao Shen; Shiqi Shen; Wenwu Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the problem of unsupervised graph neural architecture search, which remains unexplored in the literature.
1003, Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
Xinyu Ma; Xu Chu; Yasha Wang; Yang Lin; Junfeng Zhao; Liantao Ma; Wenwu Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals.
1004, A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
Junyi Zhang; Charles Herrmann; Junhwa Hur; Luisa Polania Cabrera; Varun Jampani; Deqing Sun; Ming-Hsuan Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we exploit Stable Diffusion (SD) features for semantic and dense correspondence and discover that with simple post-processing, SD features can perform quantitatively similar to SOTA representations.
1005, Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits
Evelyn Xiao-Yue Gong; Mark Sellke;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study pure exploration with infinitely many bandit arms generated \iid from an unknown distribution. Our goal is to efficiently select a single high quality arm whose average reward is, with probability $1-\delta$, within $\varepsilon$ of being with the top $\eta$-fraction of arms; this is a natural adaptation of the classical PAC guarantee for infinite action sets.
1006, Mean-field Langevin Dynamics: Time-space Discretization, Stochastic Gradient, and Variance Reduction
Taiji Suzuki; Denny Wu; Atsushi Nitanda;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide an extensively general framework to prove a uniform-in-time propagation of chaos for MFLD which takes into account the errors due to finite-particle approximation, time-discretization, and stochastic gradient approximation.
1007, Optimal Dynamic Treatment Allocation for Efficient Policy Evaluation
Ting Li; Chengchun Shi; Jianing Wang; Fan Zhou; hongtu zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose three optimal allocation strategies in a dynamic setting where treatments are sequentially assigned over time.
1008, Feature Learning Via Mean-field Langevin Dynamics: Classifying Sparse Parities and Beyond
Taiji Suzuki; Denny Wu; Kazusato Oko; Atsushi Nitanda;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, all existing guarantees for MFLD only considered the \textit{optimization} efficiency, and it is unclear if this algorithm leads to improved \textit{generalization} performance and sample complexity due to the presence of feature learning. To fill this important gap, in this work we study the sample complexity of MFLD in learning a class of binary classification problems.
1009, BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing
DONGXU LI; Junnan Li; Steven Hoi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts.
1010, Point Cloud Completion with Pretrained Text-to-Image Diffusion Models
Yoni Kasten; Ohad Rahamim; Gal Chechik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We describe an approach called SDS-Complete that uses a pre-trained text-to-image diffusion model and leverages the text semantic of a given incomplete point cloud of an object, to obtain a complete surface representation.
1011, Bridging Semantic Gaps for Language-Supervised Semantic Segmentation
Yun Xing; Jian Kang; Aoran Xiao; Jiahao Nie; Ling Shao; Shijian Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Such semantic misalignment circulates in pre-training, leading to inferior zero-shot performance in dense predictions due to insufficient visual concepts captured in textual representations. To close such semantic gap, we propose Concept Curation (CoCu), a pipeline that leverages CLIP to compensate for the missing semantics.
1012, Content-based Unrestricted Adversarial Attack
Zhaoyu Chen; Bo Li; Shuang Wu; Kaixun Jiang; Shouhong Ding; Wenqiang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To ensure the photorealism of adversarial examples and boost attack performance, we propose a novel unrestricted attack framework called Content-based Unrestricted Adversarial Attack.
1013, Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
Emanuele Marconato; Stefano Teso; Antonio Vergari; Andrea Passerini;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work fills this gap by characterizing them as unintended optima of the learning objective and identifying four key conditions behind their occurrence. Based on this, we derive several natural mitigation strategies, and analyze their efficacy both theoretically and empirically.
1014, Shared Adversarial Unlearning: Backdoor Mitigation By Unlearning Shared Adversarial Examples
Shaokui Wei; Mingda Zhang; Hongyuan Zha; Baoyuan Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore the task of purifying a backdoored model using a small clean dataset.
1015, Cross-Episodic Curriculum for Transformer Agents
Lucy Xiaoyang Shi; Yunfan Jiang; Jake Grigsby; Linxi Fan; Yuke Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new algorithm, Cross-Episodic Curriculum (CEC), to boost the learning efficiency and generalization of Transformer agents.
1016, Black-box Backdoor Defense Via Zero-shot Image Purification
Yucheng Shi; Mengnan Du; Xuansheng Wu; Zihan Guan; Jin Sun; Ninghao Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel backdoor defense framework to defend against backdoor attacks through zero-shot image purification (ZIP).
1017, RADAR: Robust AI-Text Detection Via Adversarial Learning
Xiaomeng Hu; Pin-Yu Chen; Tsung-Yi Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While existing works show that current AI-text detectors are not robust to LLM-based paraphrasing, this paper aims to bridge this gap by proposing a new framework called RADAR, which jointly trains a \underline{r}obust \underline{A}I-text \underline{d}etector via \underline{a}dversarial lea\underline{r}ning.
1018, DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
Zhiyuan Yan; Yong Zhang; Xinhang Yuan; Siwei Lyu; Baoyuan Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Additionally, there are noticeable differences in experimental settings, and evaluation strategies and metrics lack standardization. To fill this gap, we present the first comprehensive benchmark for deepfake detection, called \textit{DeepfakeBench}, which offers three key contributions: 1) a unified data management system to ensure consistent input across all detectors, 2) an integrated framework for state-of-the-art methods implementation, and 3) standardized evaluation metrics and protocols to promote transparency and reproducibility.
1019, Robust Matrix Sensing in The Semi-Random Model
Xing Gao; Yu Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study new approaches for matrix sensing in a semi-random model where an adversary can add any number of arbitrary sensing matrices.
1020, PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation
Yuhan Ding; Fukun Yin; Jiayuan Fan; Hui Li; Xin Chen; Wen Liu; Chongshan Lu; Gang Yu; Tao Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To alleviate the dilemma of using individual points to perceive the entire colossal space, we explore learning the surface distribution of the scene to provide structural priors and reduce the samplable space and propose a Point Diffusion implicit Function, PDF, for large-scale scene neural representation.
1021, Learning Unseen Modality Interaction
Yunhua Zhang; Hazel Doughty; Cees Snoek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive for generalization to unseen modality combinations during inference.
1022, One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds Without Per-Shape Optimization
Minghua Liu; Chao Xu; Haian Jin; Linghao Chen; Mukund Varma T; Zexiang Xu; Hao Su;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a novel method that takes a single image of any object as input and generates a full 360-degree 3D textured mesh in a single feed-forward pass.
1023, OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding
Minghua Liu; Ruoxi Shi; Kaiming Kuang; Yinhao Zhu; Xuanlin Li; Shizhong Han; Hong Cai; Fatih Porikli; Hao Su;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds.
1024, OpenIllumination: A Multi-Illumination Dateset for Inverse Rendering Evaluation on Real Objects
Isabella Liu; Linghao Chen; Ziyang Fu; Liwen Wu; Haian Jin; Zhong Li; Chin Ming Ryan Wong; Yi Xu; Ravi Ramamoorthi; Zexiang Xu; Hao Su;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations.
1025, Deductive Verification of Chain-of-Thought Reasoning
Zhan Ling; Yunhao Fang; Xuanlin Li; Zhiao Huang; Mingu Lee; Roland Memisevic; Hao Su;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, directly verifying the validity of an entire deductive reasoning process is challenging, even with advanced models like ChatGPT. In light of this, we propose to decompose a reasoning verification process into a series of step-by-step subprocesses, each only receiving their necessary context and premises.
1026, Percentile Criterion Optimization in Offline Reinforcement Learning
Cyrus Cousins; Elita Lobo; Marek Petrik; Yair Zick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing works use Bayesian credible regions as uncertainty sets, but they are often unnecessarily large and result in learning overly conservative policies. To overcome these shortcomings, we propose a novel Value-at-Risk based dynamic programming algorithm to optimize the percentile criterion without explicitly constructing any uncertainty sets.
1027, Enhancing Adaptive History Reserving By Spiking Convolutional Block Attention Module in Recurrent Neural Networks
Qi Xu; Yuyuan Gao; Jiangrong Shen; Yaxin Li; Xuming Ran; Huajin Tang; Gang Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop a recurrent spiking neural network (RSNN) model embedded with an advanced spiking convolutional block attention module (SCBAM) component to combine both spatial and temporal features of spatio-temporal patterns.
1028, Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning
HuiYang Shao; Qianqian Xu; Zhiyong Yang; Peisong Wen; Gao Peifeng; Qingming Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to tackle flexible cost requirements for long-tail datasets, where we need to construct a (a) cost-sensitive and (b) class-distribution robust learning framework.
1029, A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning
Zitai Wang; Qianqian Xu; Zhiyong Yang; Yuan He; Xiaochun Cao; Qingming Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing generalization analysis of such losses is still coarse-grained and fragmented, failing to explain some empirical results. To bridge this gap between theory and practice, we propose a novel technique named data-dependent contraction to capture how these modified losses handle different classes.
1030, DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework
Siran Dai; Qianqian Xu; Zhiyong Yang; Xiaochun Cao; Qingming Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem. To tackle this challenge, methodically we propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it.
1031, DesCo: Learning Object Recognition with Rich Language Descriptions
Liunian Li; Zi-Yi Dou; Nanyun Peng; Kai-Wei Chang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To tackle the challenges, we propose a new description-conditioned (DesCo) paradigm of learning object recognition models with rich language descriptions consisting of two major innovations: 1) to collect rich language descriptions of objects, we use a large language model as a commonsense knowledge engine to generate rich language descriptions based on object names and the raw image-text caption; 2) to improve the ability of models to accurately interpret intricate nuances embedded within descriptions, we create context-sensitive queries, where the model is forced to focus on context and not just object names.
1032, VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Sihan Chen; Handong Li; Qunbo Wang; Zijia Zhao; Mingzhen Sun; Xinxin Zhu; Jing Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we resort to establish connections between multi-modality video tracks, including Vision, Audio, and Subtitle, and Text by exploring an automatically generated large-scale omni-modality video caption dataset called VAST-27M.
1033, Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning
Yangru Huang; Peixi Peng; Yifan Zhao; Haoran Xu; Mengyue Geng; Yonghong Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, such a feature-level fusion paradigm with a single critic may fall short in policy learning as it tends to overlook the distinct values of each modality. To remedy this, this paper proposes a Local modality-customized Value Estimation (LVE) paradigm, which dynamically estimates the contribution and adjusts the importance weight of each modality from a value-level perspective.
1034, Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
Wei Fang; Zhaofei Yu; Zhaokun Zhou; Ding Chen; Yanqi Chen; Zhengyu Ma; Timothée Masquelier; Yonghong Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: By rewriting neuronal dynamics without reset to a general formulation, we propose the Parallel Spiking Neuron (PSN), which generates hidden states that are independent of their predecessors, resulting in parallelizable neuronal dynamics and extremely high simulation speed.
1035, Stability-penalty-adaptive Follow-the-regularized-leader: Sparsity, Game-dependency, and Best-of-both-worlds
Taira Tsuchiya; Shinji Ito; Junya Honda;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This learning rate yields a regret bound jointly depending on stability and penalty of the algorithm, into which the regret of FTRL is typically decomposed. With this result, we establish several algorithms with three types of adaptivity: sparsity, game-dependency, and Best-of-Both-Worlds (BOBW).
1036, Prefix-tree Decoding for Predicting Mass Spectra from Molecules
Samuel Goldman; John Bradshaw; Jiayi Xin; Connor Coley;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce a new intermediate strategy for predicting mass spectra from molecules by treating mass spectra as sets of chemical formulae, which are themselves multisets of atoms.
1037, Effective Robustness Against Natural Distribution Shifts for Models with Different Training Data
Zhouxing Shi; Nicholas Carlini; Ananth Balashankar; Ludwig Schmidt; Cho-Jui Hsieh; Alex Beutel; Yao Qin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new effective robustness evaluation metric to compare the effective robustness of models trained on different data distributions.
1038, LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
Hongwu Peng; Ran Ran; Yukui Luo; Jiahui Zhao; Shaoyi Huang; Kiran Thorat; Tong Geng; Chenghong Wang; Xiaolin Xu; Wujie Wen; Caiwen Ding;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To tackle those challenges, we present LinGCN, a framework designed to reduce multiplication depth and optimize the performance of HE based GCN inference.
1039, Facing-off World Model Backbones: RNN, Transformer, and S4
Fei Deng; Junyeong Park; Sungjin Ahn;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we seek to explore alternative world model backbones to improve long-term memory.
1040, Bayesian Optimisation of Functions on Graphs
Xingchen Wan; Pierre Osselin; Henry Kenlay; Binxin Ru; Michael A Osborne; Xiaowen Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Traditional graph search algorithms can be applied in this case, but they may be sample-inefficient and do not make use of information about the function values; on the other hand, Bayesian optimisation is a class of promising black-box solvers with superior sample efficiency, but it has been scarcely been applied to such novel setups. To fill this gap, we propose a novel Bayesian optimisation framework that optimises over functions defined on generic, large-scale and potentially unknown graphs.
1041, Expressive Sign Equivariant Networks for Spectral Geometric Learning
Derek Lim; Joshua Robinson; Stefanie Jegelka; Haggai Maron;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we show that sign invariance is theoretically limited for tasks such as building orthogonally equivariant models and learning node positional encodings for link prediction in graphs. In this work, we demonstrate the benefits of sign equivariance for these tasks.
1042, Alignment with Human Representations Supports Robust Few-shot Learning
Ilia Sucholutsky; Tom Griffiths;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide an information-theoretic analysis that suggests that there should be a U-shaped relationship between the degree of representational alignment with humans and performance on few-shot learning tasks.
1043, Neural Priming for Sample-Efficient Adaptation
Matthew Wallingford; Vivek Ramanujan; Alex Fang; Aditya Kusupati; Roozbeh Mottaghi; Aniruddha Kembhavi; Ludwig Schmidt; Ali Farhadi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose Neural Priming, a technique for adapting large pretrained models to distribution shifts and downstream tasks given few or no labeled examples.
1044, Cognitive Steering in Deep Neural Networks Via Long-Range Modulatory Feedback Connections
Talia Konkle; George Alvarez;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by biological and cognitive science evidence, we introduce long-range modulatory feedback connections to deep convolutional neural network models to enable cognitive steering.
1045, Beyond Lipschitz Smoothness: A New Approach to Convex and Non-Convex Optimization
Haochuan Li; Jian Qian; Yi Tian; Ali Jadbabaie; Alexander Rakhlin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we further generalize this non-uniform smoothness condition and develop a simple, yet powerful analysis technique that bounds the gradients along the trajectory, thereby leading to stronger results for both convex and non-convex optimization problems. In particular, we obtain the classical convergence rates for (stochastic) gradient descent and Nesterov's accelerated gradient method in the convex and/or non-convex setting under this general smoothness condition.
1046, Geometry-Informed Neural Operator for Large-Scale 3D PDEs
Zongyi Li; Nikola Kovachki; Chris Choy; Boyi Li; Jean Kossaifi; Shourya Otta; Mohammad Amin Nabian; Maximilian Stadler; Christian Hundt; Kamyar Azizzadenesheli; Animashree Anandkumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the geometry-informed neural operator (GINO), a highly efficient approach to learning the solution operator of large-scale partial differential equations with varying geometries.
1047, Imagine The Unseen World: A Systematic Visual Imagination Benchmark
Yeongbin Kim; Gautam Singh; Junyeong Park; Caglar Gulcehre; Sungjin Ahn;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While there has been considerable progress in the language domain, efforts towards systematic visual imagination, or envisioning the dynamical implications of a visual observation, are in their infancy. We introduce the Systematic Visual Imagination Benchmark (SVIB), the first benchmark designed to address this problem head-on.
1048, Gaussian Process Probes (GPP) for Uncertainty-Aware Probing
Alexander Ku; Zi Wang; Jason Baldridge; Tom Griffiths; Been Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce a unified yet simple framework for probing and measuring uncertainty about concepts represented by models--Gaussian process probes (GPP).
1049, Finite Population Regression Adjustment and Non-asymptotic Guarantees for Treatment Effect Estimation
Mehrdad Ghadiri; David Arbour; Tung Mai; Cameron Musco; Anup Rao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the problems of estimating the sample mean, individual treatment effects, and average treatment effect with regression adjustment.
1050, Convergence of Adam Under Relaxed Assumptions
Haochuan Li; Ali Jadbabaie; Alexander Rakhlin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives.
1051, Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio
Xudong XU; Dejan Markovic; Jacob Sandakly; Todd Keebler; Steven Krenn; Alexander Richard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While 3D human body modeling has received much attention in computer vision, modeling the acoustic equivalent, i.e. modeling 3D spatial audio produced by body motion and speech, has fallen short in the community. To close this gap, we present a model that can generate accurate 3D spatial audio for full human bodies.
1052, State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding
Devleena Das; Sonia Chernova; Been Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we contribute a unified framework, State2Explanation (S2E), that involves learning a joint embedding model between state-action pairs and concept-based explanations, and leveraging such learned model to both (1) inform reward shaping during an agent's training, and (2) provide explanations to end-users at deployment for improved task performance.
1053, The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions
Jonathan Schmidt; Philipp Hennig; Jörg Nick; Filip Tronarp;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel approximate Gaussian filtering and smoothing methodwhich propagates low-rank approximations of the covariance matrices.
1054, Can Semi-supervised Learning Use All The Data Effectively? A Lower Bound Perspective
Gizem Yüce; Alexandru Tifrea; Amartya Sanyal; Fanny Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we derive tight lower bounds for 2-Gaussian mixture model distributions which exhibit an explicit dependence on both the labeled and the unlabeled dataset sizes.
1055, On The Learning Curves of Kernel Ridge Regression
Yicheng Li; haobo Zhang; Qian Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, under mild and more realistic assumptions, we rigorously provide a full characterization of the learning curve:elaborating the effect of and the interplay between the choice of the regularization parameter, the source condition and the noise.
1056, Dynamic Sparsity Is Channel-Level Sparsity Learner
Lu Yin; Gen Li; Meng Fang; Li Shen; Tianjin Huang; Zhangyang Atlas Wang; Vlado Menkovski; Xiaolong Ma; Mykola Pechenizkiy; Shiwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Channel-aware dynamic sparse (Chase), that for the first time seamlessly translates the promise of unstructured dynamic sparsity to GPU-friendly channel-level sparsity (not fine-grained N:M or group sparsity) during one end-to-end training process, without any ad-hoc operations.
1057, Federated Compositional Deep AUC Maximization
Xinwen Zhang; Yihan Zhang; Tianbao Yang; Richard Souvenir; Hongchang Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most existing approaches focus on problems with balanced data, and prediction performance is far from satisfactory for many real-world applications where the number of samples in different classes is highly imbalanced. To address this challenging problem, we developed a novel federated learning method for imbalanced data by directly optimizing the area under curve (AUC) score.
1058, Predicting Mutational Effects on Protein-protein Binding Via A Side-chain Diffusion Probabilistic Model
Shiwei Liu; Tian Zhu; Milong Ren; Chungong Yu; Dongbo Bu; Haicang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose SidechainDiff, a novel representation learning-based approach that leverages unlabelled experimental protein structures.
1059, Robust Model Reasoning and Fitting Via Dual Sparsity Pursuit
Xingyu Jiang; Jiayi Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we contribute to solving a threefold problem: outlier rejection, true model reasoning and parameter estimation in a unified optimization modeling.
1060, Practical Contextual Bandits with Feedback Graphs
Mengxiao Zhang; Yuheng Zhang; Olga Vrousgou; Haipeng Luo; Paul Mineiro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose and analyze an approach to contextual bandits with feedback graphs based upon reduction to regression.
1061, Densely Annotated Synthetic Images Make Stronger Semantic Segmentation Models
Lihe Yang; Xiaogang Xu; Bingyi Kang; Yinghuan Shi; Hengshuang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, they are extremely hungry for delicate annotations to train, and the acquisition is laborious and unaffordable. Therefore, in this work, we resort to synthetic images generated from generative models to ease the burden of both data collection and annotation procedures.
1062, TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
Rongkun Zheng; Lu Qi; Xi Chen; Yi Wang; Kun Wang; Yu Qiao; Hengshuang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, increasing the data scale and enriching taxonomy space while improving classification precision is important. In this work, we analyze that providing extra taxonomy information can help models concentrate on specific taxonomy, and propose our model named Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation (TMT-VIS) to address this vital challenge.
1063, CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
Yixing Lao; Xiaogang Xu; Xihui Liu; Hengshuang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present CorresNeRF, a method to leverage image correspondence priors computed by off-the-shelf methods to supervise the training of NeRF.
1064, Equivariant Neural Operator Learning with Graphon Convolution
Chaoran Cheng; Jian Peng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space.
1065, Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels
Zhen Liu; ma peitian; Dongliang Chen; Wenbin Pei; Qianli Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This results in training losses of some time series samples that do not meet the small-loss criterion. Therefore, this paper proposes a deep learning paradigm called Scale-teaching to cope with time series noisy labels.
1066, Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
Yubin Shi; Yixuan Chen; Mingzhi Dong; Xiaochen Yang; Dongsheng Li; Yujiang Wang; Robert Dick; Qin Lv; Yingying Zhao; Fan Yang; Tun Lu; Ning Gu; Li Shang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $\lambda_{\max}$.
1067, Diversifying Spatial-Temporal Perception for Video Domain Generalization
Kun-Yu Lin; Jia-Run Du; Yipeng Gao; Jiaming Zhou; Wei-Shi Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we propose to perceive diverse spatial-temporal cues in videos, aiming to discover potential domain-invariant cues in addition to domain-specific cues.
1068, Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction
Yu-Kun Qiu; Guo-Hao Xu; Wei-Shi Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By contrast, it is relatively easy for the classifier to distinguish inner-surface and outer-surface voxels due to the intrinsic gap. Inspired by this, we propose the inner-outer aware reconstruction (IOAR) model.
1069, Temporal Continual Learning with Prior Compensation for Human Motion Prediction
Jianwei Tang; Jiangxin Sun; Xiaotong Lin; lifang zhang; Jian-Fang Hu; Wei-Shi Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Previous approaches have treated the prediction of various moments equally, resulting in two main limitations: the learning of short-term predictions is hindered by the focus on long-term predictions, and the incorporation of prior information from past predictions into subsequent predictions is limited. In this paper, we introduce a novel multi-stage training framework called Temporal Continual Learning (TCL) to address the above challenges.
1070, PTADisc: A Diverse, Immense, Student-Centered and Cross-Course Dataset for Personalized Learning
Liya Hu; Zhiang Dong; Jingyuan Chen; Guifeng Wang; Zhihua Wang; Zhou Zhao; Fei Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing research has been limited to single-course scenarios; cross-course studies have not been explored due to a lack of dataset. We address this issue by constructing PTADisc, a Diverse, Immense, Student-centered dataset that emphasizes its sufficient Cross-course information for personalized learning.
1071, BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization
Chen Fan; Gaspard Choné-Ducasse; Mark Schmidt; Christos Thrampoulidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing algorithms involve two coupled learning rates that can be affected by approximation errors when computing hypergradients, making careful fine-tuning necessary to ensure fast convergence. To alleviate this issue, we investigate the use of recently proposed adaptive step-size methods, namely stochastic line search (SLS) and stochastic Polyak step size (SPS), for computing both the upper and lower-level learning rates.
1072, Building Socio-culturally Inclusive Stereotype Resources with Community Engagement
Sunipa Dev; Jaya Goyal; Dinesh Tewari; Shachi Dave; Vinodkumar Prabhakaran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we demonstrate a socio-culturally aware expansion of evaluation resources in the Indian societal context, specifically for the harm of stereotyping.
1073, AdaPlanner: Adaptive Planning from Feedback with Language Models
Haotian Sun; Yuchen Zhuang; Lingkai Kong; Bo Dai; Chao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Consequently, the sequential decision-making performance of LLM agents degenerates with problem complexity and plan horizons increase. We propose a closed-loop approach, AdaPlanner, which allows the LLM agent to refine its self-generated plan adaptively in response to environmental feedback.
1074, Stability Guarantees for Feature Attributions with Multiplicative Smoothing
Anton Xue; Rajeev Alur; Eric Wong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we analyze stability as a property for reliable feature attribution methods.
1075, PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction
Apoorva Sharma; Sushant Veer; Asher Hancock; Heng Yang; Marco Pavone; Anirudha Majumdar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we use PAC-Bayes theory to obtain generalization bounds on both the coverage and the efficiency of set-valued predictors which can be directly optimized to maximize efficiency while satisfying a desired test coverage.
1076, Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
Xiaojun Guo; Yifei Wang; Zeming Wei; Yisen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, through a systematic study of various graph contrastive learning (GCL) methods, we observe that some common phenomena among existing GCL methods that are quite different from the original VCL methods, including 1) positive samples are not a must for GCL; 2) negative samples are not necessary for graph classification, neither for node classification when adopting specific normalization modules; 3) data augmentations have much less influence on GCL, as simple domain-agnostic augmentations (e.g., Gaussian noise) can also attain fairly good performance. By uncovering the implicit mechanism of the architecture to contrastive learning, we theoretically give explanations for the above intriguing properties of GCL.
1077, A Simple Yet Effective Strategy to Robustify The Meta Learning Paradigm
Qi Wang; yanghe feng; Yiqin Lv; Zheng Xie; Jincai Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We take the two-stage strategy as heuristics to solve the robust meta learning problem, controlling the worst fast adaptation cases at a certain probabilistic level.
1078, On The Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training
Jieyu Zhang; Bohan Wang; Zhengyu Hu; Pang Wei Koh; Alexander Ratner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the impact of the trade-off between the intra-class diversity (the number of samples per class) and the inter-class diversity (the number of classes) of a supervised pre-training dataset.
1079, Refined Mechanism Design for Approximately Structured Priors Via Active Regression
Christos Boutsikas; Petros Drineas; Marios Mertzanidis; Alexandros Psomas; Paritosh Verma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, following a model introduced recently by Cai and Daskalakis [CD22], we consider the case that bidders' prior distributions can be well-approximated by a topic model.
1080, Hypervolume Maximization: A Geometric View of Pareto Set Learning
Xiaoyuan Zhang; Yifan Chen; Bo Xue; Xi Lin; Qingfu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a novel approach to multiobjective algorithms aimed at modeling the Pareto set using neural networks.
1081, Approximately Equivariant Graph Networks
Ningyuan Huang; Ron Levie; Soledad Villar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we focus on the active symmetries of GNNs, by considering a learning setting where signals are supported on a fixed graph.
1082, Tri-contrastive Learning: Identifiable Representation Learning with Automatic Discovery of Feature Importance
Qi Zhang; Yifei Wang; Yisen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study a new method named tri-contrastive learning (triCL) that involves a 3-factor contrast in the form of $z_x^\top S z_{x'}$, where $S={\rm diag}(s_1,\dots,s_k)$ is a learnable diagonal matrix that automatically captures the importance of each feature.
1083, CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data
Taiki Miyanishi; Fumiya Kitamori; Shuhei Kurita; Jungdae Lee; Motoaki Kawanabe; Nakamasa Inoue;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, compared to the extensive text annotations available for images and indoor scenes, the scarcity of text annotations for outdoor scenes poses a significant challenge for achieving these applications. To tackle this problem, we introduce the CityRefer dataset for city-level visual grounding.
1084, ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
Jungwoo Oh; Seongsu Bae; Gyubok Lee; Joon-myoung Kwon; Edward Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This leaves the vast potential of combining electrocardiogram (ECG) data with these systems largely untapped. To address this gap, we present ECG-QA, the first QA dataset specifically designed for ECG analysis.
1085, Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
George Ma; Yifei Wang; Yisen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we explore a minimal approach that resolves the ambiguity issues by directly finding canonical directions for the eigenvectors, named Laplacian Canonization (LC).
1086, DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models
Ge Zheng; Bin Yang; Jiajin Tang; Hong-Yu Zhou; Sibei Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To evoke CoT reasoning in multimodality, this work first conducts an in-depth analysis of these challenges posed by multimodality and presents two key insights: �keeping critical thinking� and �letting everyone do their jobs� in multimodal CoT reasoning.
1087, Schema-learning and Rebinding As Mechanisms of In-context Learning and Emergence
Sivaramakrishnan Swaminathan; Antoine Dedieu; Rajkumar Vasudeva Raju; Murray Shanahan; Miguel Lazaro-Gredilla; Dileep George;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we demonstrate that comparable ICL capabilities can be acquired by an alternative sequence prediction learning method using clone-structured causal graphs (CSCGs).
1088, Adversarial Examples Are Not Real Features
Ang Li; Yifei Wang; Yiwen Guo; Yisen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: A classical theory explaining the existence of adversarial examples is the non-robust features. We examine deeper into the essence of non-robust features.
1089, Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from A Minimax Game Perspective
Yifei Wang; Liangchen Li; Jiansheng Yang; Zhouchen Lin; Yisen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, researchers recently notice that AT suffers from severe robust overfitting problems, particularly after the learning rate (LR) decay. In this paper, we explain this phenomenon by viewing adversarial training as a dynamic minimax game between the model trainer and the attacker.
1090, Adversarial Robustness in Graph Neural Networks: A Hamiltonian Energy Conservation Approach
Kai Zhao; Yang Song; Qiyu Kang; Rui She; Sijie Wang; Wee Peng Tay;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by physics principles, we advocate for the use of conservative Hamiltonian neural flows to construct GNNs that are robust to adversarial attacks.
1091, A Logic for Expressing Log-Precision Transformers
William Merrill; Ashish Sabharwal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we analyze transformers whose forward pass is computed in $\log n$ precision on contexts of length $n$.
1092, Wasserstein Quantum Monte Carlo: A Novel Approach for Solving The Quantum Many-Body Schrödinger Equation
Kirill Neklyudov; Jannes Nys; Luca Thiede; Juan Carrasquilla; Qiang Liu; Max Welling; Alireza Makhzani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: More specifically, we propose ``Wasserstein Quantum Monte Carlo'' (WQMC), which uses the gradient flow induced by the Wasserstein metrics, rather than Fisher--Rao metric, and corresponds to *transporting* the probability mass, rather than *teleporting* it.
1093, LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting
Xu Liu; Yutong Xia; Yuxuan Liang; Junfeng Hu; Yiwei Wang; LEI BAI; Chao Huang; Zhenguang Liu; Bryan Hooi; Roger Zimmermann;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the promising results achieved on current public datasets may not be applicable to practical scenarios due to limitations within these datasets. First, the limited sizes of them may not reflect the real-world scale of traffic networks. Second, the temporal coverage of these datasets is typically short, posing hurdles in studying long-term patterns and acquiring sufficient samples for training deep models. Third, these datasets often lack adequate metadata for sensors, which compromises the reliability and interpretability of the data. To mitigate these limitations, we introduce the LargeST benchmark dataset.
1094, SLM: A Smoothed First-order Lagrangian Method for Structured Constrained Nonconvex Minimization
Songtao Lu; Jiawei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we focus on a class of structured nonconvex FCO problems, where the two optimization variables are nonlinearly coupled in the inequality constraint.
1095, Open-Vocabulary Semantic Segmentation Via Attribute Decomposition-Aggregation
Chaofan Ma; Yang Yuhuan; Chen Ju; Fei Zhang; Ya Zhang; Yanfeng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, exceptions often happen when meet with ambiguity for brief or incomplete names, new words that are not present in the pre-trained lexicons, and difficult-to-describe categories for users. To address these issues, this work proposes a novel decomposition-aggregation framework, inspired by human cognition in understanding new concepts.
1096, Federated Learning with Bilateral Curation for Partially Class-Disjoint Data
Ziqing Fan; ruipeng zhang; Jiangchao Yao; Bo Han; Ya Zhang; Yanfeng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As far as we know, none of the existing methods can intrinsically mitigate PCDD challenges to achieve holistic improvement in the bilateral views (both global view and local view) of federated learning. To address this dilemma, we are inspired by the strong generalization of simplex Equiangular Tight Frame (ETF) on the imbalanced data, and propose a novel approach called FedGELA where the classifier is globally fixed as a simplex ETF while locally adapted to the personal distributions.
1097, Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
Haotian Zheng; Qizhou Wang; Zhen Fang; Xiaobo Xia; Feng Liu; Tongliang Liu; Bo Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Accordingly, we propose a powerful data generation-based learning method named *Auxiliary Task-based OOD Learning* (ATOL) that can relieve the mistaken OOD generation.
1098, DreamWaltz: Make A Scene with Complex 3D Animatable Avatars
Yukun Huang; Jianan Wang; Ailing Zeng; He CAO; Xianbiao Qi; Yukai Shi; Zheng-Jun Zha; Lei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present DreamWaltz, a novel framework for generating and animating complex avatars given text guidance and parametric human body prior.
1099, Designing Robust Transformers Using Robust Kernel Density Estimation
Xing Han; Tongzheng Ren; Tan Nguyen; Khai Nguyen; Joydeep Ghosh; Nhat Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, by re-interpreting the self-attention mechanism as a non-parametric kernel density estimator, we adapt classical robust kernel density estimation methods to develop novel classes of transformers that are resistant to adversarial attacks and data contamination.
1100, Demystifying Softmax Gating in Gaussian Mixture of Experts
Huy Nguyen; TrungTin Nguyen; Nhat Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It is mainly due to three fundamental theoretical challenges associated with the softmax gating: (i) the identifiability only up to the translation of the parameters; (ii) the intrinsic interaction via partial differential equation between the softmax gating and the expert functions in Gaussian distribution; (iii) the complex dependence between the numerator and denominator of the conditional density of softmax gating Gaussian mixture of experts. We resolve these challenges by proposing novel Vononoi loss functions among parameters and establishing the convergence rates of the maximum likelihood estimator (MLE) for solving parameter estimation in these models.
1101, Diffusion Model Is An Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
Haoran He; Chenjia Bai; Kang Xu; Zhuoran Yang; Weinan Zhang; Dong Wang; Bin Zhao; Xuelong Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we aim to investigate the effectiveness of a single diffusion model in modeling large-scale multi-task offline data, which can be challenging due to diverse and multimodal data distribution.
1102, Joint Feature and Differentiable $ K $-NN Graph Learning Using Dirichlet Energy
Lei Xu; Lei Chen; Rong Wang; Feiping Nie; Xuelong Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a deep FS method that simultaneously conducts feature selection and differentiable $ k $-NN graph learning based on the Dirichlet Energy.
1103, Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models
Dat Do; Huy Nguyen; Khai Nguyen; Nhat Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the maximum likelihood estimation (MLE) in the multivariate deviated model where the data are generated from the density function $(1-\lambda^{\ast})h_{0}(x)+\lambda^{\ast}f(x|\mu^{\ast}, \Sigma^{\ast})$ in which $h_{0}$ is a known function, $\lambda^{\ast} \in [0,1]$ and $(\mu^{\ast}, \Sigma^{\ast})$ are unknown parameters to estimate.
1104, Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing
kai wang; Fei Yang; Shiqi Yang; Muhammad Atif Butt; Joost van de Weijer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: According to our experimental findings, inaccurate cross-attention maps are at the root of this problem. Based on this observation, we propose $\textit{Dynamic Prompt Learning}$ ($DPL$) to force cross-attention maps to focus on correct $\textit{noun}$ words in the text prompt.
1105, On The Generalization Properties of Diffusion Models
Puheng Li; Zhong Li; Huishuai Zhang; Jiang Bian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work embarks on a comprehensive theoretical exploration of the generalization attributes of diffusion models.
1106, PLANNER: Generating Diversified Paragraph Via Latent Language Diffusion Model
Yizhe Zhang; Jiatao Gu; Zhuofeng Wu; Shuangfei Zhai; Joshua Susskind; Navdeep Jaitly;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose PLANNER, a model that combines latent semantic diffusion with autoregressive generation, to generate fluent text while exercising global control over paragraphs.
1107, Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty Via Attributes
Minyang Hu; Hong Chang; Zong Guo; Bingpeng MA; Shiguang Shan; Xilin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we try to understand FSL by exploring two key questions:(1) How to quantify the relationship between training and novel tasks?
1108, Primal-Attention: Self-attention Through Asymmetric Kernel SVD in Primal Representation
YINGYI CHEN; Qinghua Tao; Francesco Tonin; Johan Suykens;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide a new perspective to represent and optimize self-attention through asymmetric Kernel Singular Value Decomposition (KSVD), which is also motivated by the low-rank property of self-attention normally observed in deep layers.
1109, Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates
Sarath Sreedharan; Michael Katz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most of these works are inherently limited by their assumption of having an access to a symbolic approximation of the underlying problem. To address this issue, we introduce a new method for learning optimistic symbolic approximations of the underlying world model.
1110, Convergence Analysis of ODE Models for Accelerated First-order Methods Via Positive Semidefinite Kernels
Jungbin Kim; Insoon Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel methodology that systematically analyzes ordinary differential equation (ODE) models for first-order optimization methods by converting the task of proving convergence rates into verifying the positive semidefiniteness of specific Hilbert-Schmidt integral operators.
1111, Group Fairness in Peer Review
Haris Aziz; Evi Micha; Nisarg Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study a simple peer review model, prove that it always admits a reviewing assignment in the core, and design an efficient algorithm to find one such assignment.
1112, Theoretical Analysis of The Inductive Biases in Deep Convolutional Networks
Zihao Wang; Lei Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the inductive biases in convolutional neural networks (CNNs), which are believed to be vital drivers behind CNNs' exceptional performance on vision-like tasks.
1113, Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes
Cai Zhou; Xiyuan Wang; Muhan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on spectral analysis of Hodge $1$-Laplcians, we propose Hodge1Lap, a permutation equivariant and expressive edge-level positional encoding.
1114, MAG-GNN: Reinforcement Learning Boosted Graph Neural Network
Lecheng Kong; Jiarui Feng; Hao Liu; Dacheng Tao; Yixin Chen; Muhan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we analyze the necessity of complete subgraph enumeration and show that a model can achieve a comparable level of expressivity by considering a small subset of the subgraphs.
1115, Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
Ziyi Bai; Ruiping Wang; Xilin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, humans can easily tackle it by using a series of episode memory as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model.
1116, Generalized Semi-Supervised Learning Via Self-Supervised Feature Adaptation
Jiachen Liang; RuiBing Hou; Hong Chang; Bingpeng MA; Shiguang Shan; Xilin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a novel setting to formalize the feature distribution mismatch between the labeled and unlabeled samples.
1117, Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions
Dongjie Wang; Meng Xiao; Min Wu; pengfei wang; Yuanchun Zhou; Yanjie Fu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Overly emphasizing efficiency in algorithm design usually sacrifice stability or robustness. To fundamentally fill this gap, we reformulate discrete feature transformation as a continuous space optimization task and develop an embedding-optimization-reconstruction framework.
1118, Distance-Restricted Folklore Weisfeiler-Lehman GNNs with Provable Cycle Counting Power
Junru Zhou; Jiarui Feng; Xiyuan Wang; Muhan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we overcome the aforementioned limitations of subgraph GNNs by proposing a novel class of GNNs---$d$-Distance-Restricted FWL(2) GNNs, or $d$-DRFWL(2) GNNs.
1119, Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions
Xiang Cheng; Bohan Wang; Jingzhao Zhang; Yusong Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, on the theory side, MCMC algorithms suffer from slow mixing rate when $\pi(x)$ is non-log-concave. Our work examines this gap and shows that when Poincar\'e-style inequality holds on a subset $\mathcal{X}$ of the state space, the conditional distribution of MCMC iterates over $\mathcal{X}$ mixes fast to the true conditional distribution.
1120, A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing
Junren Chen; Jonathan Scarlett; Michael Ng; Zhaoqiang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we build a unified framework to derive uniform recovery guarantees for nonlinear GCS where the observation model is nonlinear and possibly discontinuous or unknown.
1121, Blurred-Dilated Net for Adversarial Attacks
Yang Deng; Weibin Wu; Jianping Zhang; Zibin Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a model optimization attack: Blurred-Dilated method (BD), which achieves greater black-box transferability by reducing downsampling, using BlurPools and dilated convolutions on the source model.
1122, DAW: Exploring The Better Weighting Function for Semi-supervised Semantic Segmentation
Rui Sun; Huayu Mai; Tianzhu Zhang; Feng Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we systematically analyze the trade-off in previous methods when dealing with pseudo-labels.
1123, Kernel-Based Tests for Likelihood-Free Hypothesis Testing
Patrik R Gerber; Tianze Jiang; Yury Polyanskiy; Rui Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we (a) introduce a generalization where unlabeled samples come from a mixture of the two classes -- a case often encountered in practice; (b) study the minimax sample complexity for non-parametric classes of densities under maximum meandiscrepancy (MMD) separation; and (c) investigate the empirical performance of kernels parameterized by neural networks on two tasks: detectionof the Higgs boson and detection of planted DDPM generated images amidstCIFAR-10 images.
1124, Optimal Transport for Counterfactual Regression: A New Perspective
Hao Wang; Quanyu Dai; Jiajun Fan; Zhichao Chen; Haoxuan Li; Weiming Liu; Tianqiao Liu; Yichao Wang; Zhenhua Dong; Ruiming Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, based on the canonical optimal transport framework, we propose a relaxed mass-preserving regularizer to address the MSE issue and design a proximal factual outcome regularizer to handle the UCE issue.
1125, DPM-Solver-v3: Improved Diffusion ODE Solvers with Empirical Model Statistics
Kaiwen Zheng; Cheng Lu; Jianfei Chen; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel formulation towards the optimal parameterization during sampling that minimizes the first-order discretization error of the ODE solution.
1126, Learning Sample Difficulty from Pre-trained Models for Reliable Prediction
Peng Cui; Dan Zhang; Zhijie Deng; Yinpeng Dong; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, modern neural networks have been found to be poorly calibrated and make overconfident predictions regardless of inherent sample difficulty and data uncertainty. To address this issue, we propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization.
1127, Towards Accelerated Model Training Via Bayesian Data Selection
Zhijie Deng; Peng Cui; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, its practical adoption relies on less principled approximations and additional clean holdout data. This work solves these problems by leveraging a lightweight Bayesian treatment and incorporating off-the-shelf zero-shot predictors built on large-scale pre-trained models.
1128, Memory Efficient Optimizers with 4-bit States
Bingrui Li; Jianfei Chen; Jun Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we push optimizer states bitwidth down to 4-bit through a detailed empirical analysis of first and second order momentums.
1129, Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?
Xiaoxiao Sun; Nidham Gazagnadou; Vivek Sharma; Lingjuan Lyu; Hongdong Li; Liang Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, there is no guarantee that these metrics well reflect human opinions, which, as a judgement for model privacy leakage, are more trustworthy. In this paper, we comprehensively study the faithfulness of these hand-crafted metrics to human perception of privacy information from the reconstructed images.
1130, Divide, Evaluate, and Conquer: A Decompositional Perspective on Evaluating and Improving Text-to-Image Alignment
Jaskirat Singh; Liang Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, such misalignments are often left undetected by pretrained multi-modal models such as CLIP. To address these problems, in this paper, we explore a simple yet effective decompositional approach towards both evaluation and improvement of text-to-image alignment.
1131, Idempotent Learned Image Compression with Right-Inverse
Yanghao Li; Tongda Xu; Yan Wang; Jingjing Liu; Ya-Qin Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of idempotent learned image compression (LIC).
1132, A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
Zhaocheng Zhu; Xinyu Yuan; Michael Galkin; Louis-Pascal Xhonneux; Ming Zhang; Maxime Gazeau; Jian Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here we present A\*Net, a scalable path-based method for knowledge graph reasoning.
1133, DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing
Yangtian Zhang; Zuobai Zhang; Bozitao Zhong; Sanchit Misra; Jian Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present DiffPack, a torsional diffusion model that learns the joint distribution of side-chain torsional angles, the only degrees of freedom in side-chain packing, by diffusing and denoising on the torsional space.
1134, Score-based Data Assimilation
François Rozet; Gilles Louppe;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce score-based data assimilation for trajectory inference.
1135, Agnostic Multi-Group Active Learning
Nicholas Rittler; Kamalika Chaudhuri;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the problem of improving classification accuracy on rare or hard subsets of a population, there has been recent interest in models of learning where the goal is to generalize to a collection of distributions, each representing a ``group''. We consider a variant of this problem from the perspective of active learning, where the learner is endowed with the power to decide which examples are labeled from each distribution in the collection, and the goal is to minimize the number of label queries while maintaining PAC-learning guarantees.
1136, Augmentation-Aware Self-Supervision for Data-Efficient GAN Training
Liang Hou; Qi Cao; Yige Yuan; Songtao Zhao; Chongyang Ma; Siyuan Pan; Pengfei Wan; Zhongyuan Wang; Huawei Shen; Xueqi Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data.
1137, Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis
Yuanshao Zhu; Yongchao Ye; Ying Wu; Xiangyu Zhao; James Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite its significant value, the availability of such datasets often faces limitations due to privacy concerns, proprietary barriers, and quality inconsistencies. To address these challenges, this paper presents a synthetic trajectory dataset with high fidelity, offering a general solution to these data accessibility issues.
1138, An Active Learning Framework for Multi-group Mean Estimation
Abdellah Aznag; Rachel Cummings; Adam N. Elmachtoub;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an algorithm, Variance-UCB, that selects groups according to a an upper bound on the variance estimate adjusted to the $p$-norm chosen.
1139, Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation
Myong Chol Jung; He Zhao; Joanna Dipnall; Lan Du;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While NPs hold significant potential for multimodal uncertainty estimation, the adaptation of NPs for multimodal data has not been carefully studied. To bridge this gap, we propose Multimodal Neural Processes (MNPs) by generalising NPs for multimodal uncertainty estimation.
1140, $SE(3)$ Equivariant Convolution and Transformer in Ray Space
Yinshuang Xu; Jiahui Lei; Kostas Daniilidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We model the ray space as a homogeneous space of $SE(3)$ and introduce the $SE(3)$-equivariant convolution in ray space.
1141, DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model
Yuanshao Zhu; Yongchao Ye; Shiyao Zhang; Xiangyu Zhao; James Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a spatial-temporal diffusion probabilistic model for trajectory generation (DiffTraj).
1142, Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
Haotian Xue; Alexandre Araujo; Bin Hu; Yongxin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel framework dubbed Diffusion-Based Projected Gradient Descent (Diff-PGD) for generating realistic adversarial samples.
1143, The Curious Role of Normalization in Sharpness-Aware Minimization
Yan Dai; Kwangjun Ahn; Suvrit Sra;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We focus, in particular, on understanding ***the role played by normalization***, a key component of the SAM updates.
1144, Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise
Ilias Diakonikolas; Jelena Diakonikolas; Daniel Kane; Puqian Wang; Nikos Zarifis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of learning general (i.e., not necessarily homogeneous) halfspaces with Random Classification Noise under the Gaussian distribution.
1145, SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions
Ilias Diakonikolas; Daniel Kane; Lisheng Ren; Yuxin Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we establish that the latter condition is indeed not necessary.
1146, A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm
Ilias Diakonikolas; Daniel Kane; Jasper Lee; Ankit Pensia; Thanasis Pittas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of list-decodable Gaussian covariance estimation.
1147, First Order Stochastic Optimization with Oblivious Noise
Ilias Diakonikolas; Sushrut Karmalkar; Jong Ho Park; Christos Tzamos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Along the way, we develop a rejection-sampling-based algorithm to perform noisy location estimation, which may be of independent interest.
1148, Efficient Testable Learning of Halfspaces with Adversarial Label Noise
Ilias Diakonikolas; Daniel Kane; Vasilis Kontonis; Sihan Liu; Nikos Zarifis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We give the first polynomial-time algorithm for the testable learning of halfspaces in the presence of adversarial label noise under the Gaussian distribution.
1149, Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression
Ilias Diakonikolas; Daniel Kane; Ankit Pensia; Thanasis Pittas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the fundamental problems of Gaussian mean estimation and linear regression with Gaussian covariates in the presence of Huber contamination.
1150, SQ Lower Bounds for Learning Mixtures of Linear Classifiers
Ilias Diakonikolas; Daniel Kane; Yuxin Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of learning mixtures of linear classifiers under Gaussian covariates.
1151, Training Your Image Restoration Network Better with Random Weight Network As Optimization Function
man zhou; Naishan Zheng; Yuan Xu; Chun-Le Guo; Chongyi Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we propose to investigate new optimization functions to improve image restoration performance.
1152, WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts
Nianyun Li; Naman Goel; Peiyao Sun; Claudia Marangon; Elliott Ash;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we contribute WCLD, a curated large dataset of 1.5 million criminal cases from circuit courts in the U.S. state of Wisconsin.
1153, Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?
Fan Yao; Chuanhao Li; Karthik Abinav Sankararaman; Yiming Liao; Yan Zhu; Qifan Wang; Hongning Wang; Haifeng Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work makes two major contributions in this regard: first, we uncover a fundamental limit about a class of widely adopted mechanisms, coined Merit-based Monotone Mechanisms, by showing that they inevitably lead to a constant fraction loss of the welfare. To circumvent this limitation, we introduce Backward Rewarding Mechanisms (BRMs) and show that the competition games resulting from BRM possess a potential game structure, which naturally induces the strategic creators' behavior dynamics to optimize any given welfare metric.
1154, Hierarchical Planning with Foundation Models
Anurag Ajay; Seungwook Han; Yilun Du; Shuang Li; Abhi Gupta; Tommi Jaakkola; Josh Tenenbaum; Leslie Kaelbling; Akash Srivastava; Pulkit Agrawal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Hierarchical Planning with Foundation Models (HiP), a framework that leverages different modalities of knowledge to capture information supporting the different levels of decision-making.
1155, Time Series As Images: Vision Transformer for Irregularly Sampled Time Series
Zekun Li; Shiyang Li; Xifeng Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper studies the problem from a whole new perspective by transforming irregularly sampled time series into line graph images and leveraging powerful vision transformers for time series classification in the same way as image classification.
1156, DropPos: Pre-Training Vision Transformers By Reconstructing Dropped Positions
Haochen Wang; Junsong Fan; Yuxi Wang; Kaiyou Song; Tong Wang; ZHAO-XIANG ZHANG;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident. To address this, we present DropPos, a novel pretext task designed to reconstruct Dropped Positions.
1157, Guiding Large Language Models Via Directional Stimulus Prompting
Zekun Li; Baolin Peng; Pengcheng He; Michel Galley; Jianfeng Gao; Xifeng Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a novel prompting framework called Directional Stimulus Prompting for guiding black-box large language models (LLMs) toward desired outputs.
1158, Lossy Image Compression with Conditional Diffusion Models
Ruihan Yang; Stephan Mandt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional content latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image.
1159, $\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties
Shihang Feng; Hanchen Wang; Chengyuan Deng; Yinan Feng; Yanhua Liu; Min Zhu; Peng Jin; Yinpeng Chen; Youzuo Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce $\mathbf{\mathbb{E}^{FWI}}$, a comprehensive benchmark dataset that is specifically designed for elastic FWI.
1160, Neuro-symbolic Learning Yielding Logical Constraints
Zenan Li; Yunpeng Huang; Zhaoyu Li; Yuan Yao; Jingwei Xu; Taolue Chen; Xiaoxing Ma; Jian Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a natural framework that fuses neural network training, symbol grounding, and logical constraint synthesis into a coherent and efficient end-to-end learning process.
1161, Does Graph Distillation See Like Vision Dataset Counterpart?
Beining Yang; Kai Wang; Qingyun Sun; Cheng Ji; Xingcheng Fu; Hao Tang; Yang You; Jianxin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel Structure-braodcasting Graph Dataset Distillation (\textbf{SGDD}) scheme for broadcasting the original structure information to the generation of the synthetic one, which explicitly prevents overlooking the original structure information.
1162, Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
Haonan Yuan; Qingyun Sun; Xingcheng Fu; Ziwei Zhang; Cheng Ji; Hao Peng; Jianxin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: But it remains unexplored with the following two challenges: 1) How to properly model and infer the complex environments on dynamic graphs with distribution shifts? 2) How to discover invariant patterns given inferred spatio-temporal environments? To solve these challenges, we propose a novel Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex coupled environments and exploiting spatial-temporal invariant patterns.
1163, STORM: Efficient Stochastic Transformer Based World Models for Reinforcement Learning
Weipu Zhang; Gang Wang; Jian Sun; Yetian Yuan; Gao Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce Stochastic Transformer-based wORld Model (STORM), an efficient world model architecture that combines the strong sequence modeling and generation capabilities of Transformers with the stochastic nature of variational autoencoders.
1164, Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL
Yang Yue; Rui Lu; Bingyi Kang; Shiji Song; Gao Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Though this issue can be alleviated with policy constraints or conservative Q estimation, a theoretical understanding of the underlying mechanism causing the divergence has been absent. In this work, we aim to thoroughly comprehend this mechanism and attain an improved solution.
1165, Train Once, Get A Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning
Shenzhi Wang; Qisen Yang; Jiawei Gao; Matthieu Lin; HAO CHEN; Liwei Wu; Ning Jia; Shiji Song; Gao Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we introduce Family Offline-to-Online RL (FamO2O), a simple yet effective framework that empowers existing algorithms to determine state-adaptive improvement-constraint balances.
1166, Geometric Transformer with Interatomic Positional Encoding
Yusong Wang; Shaoning Li; Tong Wang; Bin Shao; Nanning Zheng; Tie-Yan Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, by designing Interatomic Positional Encoding (IPE) thatparameterizes atomic environments as Transformer's positional encodings,we propose Geoformer, a novel geometric Transformer to effectively model molecular structures for various molecular property prediction.
1167, Exploring Question Decomposition for Zero-Shot VQA
Zaid Khan; Vijay Kumar B G; Samuel Schulter; Manmohan Chandraker; Yun Fu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we show that naive application of model-written decompositions can hurt performance. We introduce a model-driven _selective decomposition_ approach for second-guessing predictions and correcting errors, and validate its effectiveness on eight VQA tasks across three domains, showing consistent improvements in accuracy, including improvements of >20% on medical VQA datasets and boosting the zero-shot performance of BLIP-2 significantly above chance (+18%) on the challenging Winoground task.
1168, Latent Graph Inference with Limited Supervision
Jianglin Lu; Yi Xu; Huan Wang; Yue Bai; Yun Fu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Consequently, these supervision-starved weights, which determine the predictions of testing samples, cannot be semantically optimal, resulting in poor generalization. In this paper, we observe that this issue is actually caused by the graph sparsification operation, which severely destroys the important connections established between pivotal nodes and labeled ones.
1169, XAGen: 3D Expressive Human Avatars Generation
Zhongcong XU; Jianfeng Zhang; Jun Hao Liew; Jiashi Feng; Mike Zheng Shou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To enhance the fidelity of small-scale regions like face and hands, we devise a multi-scale and multi-part 3D representation that models fine details. Based on this representation, we propose a multi-part rendering technique that disentangles the synthesis of body, face, and hands to ease model training and enhance geometric quality.
1170, Learning Visual Prior Via Generative Pre-Training
Jinheng Xie; Kai Ye; Yudong Li; Yuexiang Li; Kevin Qinghong Lin; Yefeng Zheng; Linlin Shen; Mike Zheng Shou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work aims to explicitly learn the visual prior and enable the customization of sampling.
1171, On The Pareto Front of Multilingual Neural Machine Translation
Liang Chen; Shuming Ma; Dongdong Zhang; Furu Wei; Baobao Chang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we study how the performance of a given direction changes with its sampling ratio in Multilingual Neural Machine Translation (MNMT).
1172, DropCompute: Simple and More Robust Distributed Synchronous Training Via Compute Variance Reduction
Niv Giladi; Shahar Gottlieb; moran shkolnik; Asaf Karnieli; Ron Banner; Elad Hoffer; Kfir Y. Levy; Daniel Soudry;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We find an analytical relation between compute time properties and scalability limitations, caused by such straggling workers. With these findings, we propose a simple yet effective decentralized method to reduce the variation among workers and thus improve the robustness of synchronous training.
1173, Doubly Smoothed GDA for Constrained Nonconvex-Nonconcave Minimax Optimization
Taoli Zheng; Linglingzhi Zhu; Anthony Man-Cho So; Jose Blanchet; Jiajin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, most existing algorithms cannot be guaranteed to converge globally and even suffer from *limit cycles*. To address this issue, we propose a novel single-loop algorithm called doubly smoothed gradient descent ascent method (DSGDA), which naturally balances the primal and dual updates.
1174, How Do Minimum-Norm Shallow Denoisers Look in Function Space?
Chen Zeno; Greg Ongie; Yaniv Blumenfeld; Nir Weinberger; Daniel Soudry;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to characterize the functions realized by shallow ReLU NN denoisers --- in the common theoretical setting of interpolation (i.e., zero training loss) with a minimal representation cost (i.e., minimal $\ell^2$ norm weights).
1175, Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee
Yuanshi Liu; Cong Fang; Tong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop a double randomization technique, which leads to a fast underdamped Langevin algorithm with a dimension-independent convergence guarantee.
1176, Corruption-Robust Offline Reinforcement Learning with General Function Approximation
Chenlu Ye; Rui Yang; Quanquan Gu; Tong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Drawing inspiration from the uncertainty-weighting technique from the robust online RL setting \citep{he2022nearly,ye2022corruptionrobust}, we design a new uncertainty weight iteration procedure to efficiently compute on batched samples and propose a corruption-robust algorithm for offline RL.
1177, Posterior Sampling for Competitive RL: Function Approximation and Partial Observation
Shuang Qiu; Ziyu Dai; Han Zhong; Zhaoran Wang; Zhuoran Yang; Tong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on self-play GEC, we propose a model-based self-play posterior sampling method to control both players to learn Nash equilibrium, which can successfully handle the partial observability of states.
1178, Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training
Rie Johnson; Tong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Focusing on the stochastic nature of training, we first present a theoretical analysis in which the bound of generalization gap depends on what we call inconsistency and instability of model outputs, which can be estimated on unlabeled data.
1179, A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes
Han Zhong; Tong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, it is unclear whether PPO or its optimistic variants can effectively solve linear Markov decision processes (MDPs), which are arguably the simplest models in RL with function approximation. To bridge this gap, we propose an optimistic variant of PPO for episodic adversarial linear MDPs with full-information feedback, and establish a $\tilde{\mathcal{O}}(d^{3/4}H^2K^{3/4})$ regret for it.
1180, Smooth Flipping Probability for Differential Private Sign Random Projection Methods
Ping Li; Xiaoyun Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop a series of differential privacy (DP) algorithms from a family of random projections (RP) and sign random projections (SignRP).
1181, K-Median Clustering Via Metric Embedding: Towards Better Initialization with Differential Privacy
Chenglin Fan; Ping Li; Xiaoyun Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel and efficient search algorithm, for good initial centers that can be used subsequently for the local search algorithm.
1182, On Separate Normalization in Self-supervised Transformers
Xiaohui Chen; Yinkai Wang; Yuanqi Du; Soha Hassoun; Liping Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose in this paper a simple modification that employs separate normalization layers for the tokens and the [CLS] symbol to better capture their distinct characteristics and enhance downstream task performance.
1183, Smoothed Online Learning for Prediction in Piecewise Affine Systems
Adam Block; Max Simchowitz; Russ Tedrake;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper builds on the recently developed smoothed online learning framework and provides the first algorithms for prediction and simulation in PWA systems whose regret is polynomial in all relevant problem parameters under a weak smoothness assumption; moreover, our algorithms are efficient in the number of calls to an optimization oracle.
1184, PromptRestorer: A Prompting Image Restoration Method with Degradation Perception
Cong Wang; Jinshan Pan; Wei Wang; Jiangxin Dong; Mengzhu Wang; Yakun Ju; Junyang Chen; Xiao-Ming Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While networks that do not consider them for restoration forget gradually degradation during the learning process, model capacity is severely hindered. To address this, we propose a \textbf{Prompt}ing image \textbf{Restorer}, termed as \textbf{PromptRestorer}.
1185, PRED: Pre-training Via Semantic Rendering on LiDAR Point Clouds
Hao Yang; Haiyang Wang; Di Dai; Liwei Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose PRED, a novel image-assisted pre-training framework for outdoor point clouds in an occlusion-aware manner.
1186, CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
Chuofan Ma; Yi Jiang; Xin Wen; Zehuan Yuan; Xiaojuan Qi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem.
1187, CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation
Xiuzhe Wu; Peng Dai; Weipeng DENG; Handi Chen; Yang Wu; Yan-Pei Cao; Ying Shan; Xiaojuan Qi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we tackle the challenge of efficiently adapting NeRFs to real-world scene changes over time using a few new images while retaining the memory of unaltered areas, focusing on the continual learning aspect of NeRFs.
1188, Data Pruning Via Moving-one-Sample-out
Haoru Tan; Sitong Wu; Fei Du; Yukang Chen; Zhibin Wang; Fan Wang; Xiaojuan Qi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel data-pruning approach called moving-one-sample-out (MoSo), which aims to identify and remove the least informative samples from the training set.
1189, Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability
Hanlin Zhu; Amy Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide a rigorous theoretical analysis of an existing empirically successful offline GCRL algorithm.
1190, F-Policy Gradients: A General Framework for Goal-Conditioned RL Using F-Divergences
Siddhant Agarwal; Ishan Durugkar; Peter Stone; Amy Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our work ($f$-PG or $f$-Policy Gradients) shows that minimizing f-divergence between the agent's state visitation distribution and the goal can give us an optimal policy. We derive gradients for various f-divergences to optimize this objective.
1191, Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
Zeyuan Yin; Eric Xing; Zhiqiang Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a new dataset condensation framework termed Squeeze, Recover and Relabel (SRe$^2$L) that decouples the bilevel optimization of model and synthetic data during training, to handle varying scales of datasets, model architectures and image resolutions for effective dataset condensation.
1192, Aligning Language Models with Human Preferences Via A Bayesian Approach
Jiashuo WANG; Haozhao Wang; Shichao Sun; Wenjie Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Although straightforward to understand and execute, such methods suffer from an inability to capture the nuanced degrees of disaggregation among humans and may only represent a specialized subset of individuals, thereby lacking the ability to quantitatively disclose the universality of human preferences. To address this challenge, this paper proposes a novel approach, which employs a Bayesian framework to account for the distribution of disagreements among human preferences as training a preference model, and names it as $\textbf{d-PM}$.
1193, DISCO-10M: A Large-Scale Music Dataset
Luca Lanzendörfer; Florian Grötschla; Emil Funke; Roger Wattenhofer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Music datasets play a crucial role in advancing research in machine learning for music. However, existing music datasets suffer from limited size, accessibility, and lack of audio resources. To address these shortcomings, we present DISCO-10M, a novel and extensive music dataset that surpasses the largest previously available music dataset by an order of magnitude.
1194, Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective
Yuzheng Hu; Ruicheng Xian; Qilong Wu; Qiuling Fan; Lang Yin; Han Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In fact, heated debates exist in the community comparing these two types of algorithms, mostly from an empirical perspective. To approach the above question, in this paper, we revisit scalarization from a theoretical perspective.
1195, Fundamental Limits and Tradeoffs in Invariant Representation Learning
Han Zhao; Chen Dan; Bryon Aragam; Tommi Jaakkola; Geoffrey Gordon; Pradeep Ravikumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite their wide applicability, theoretical understanding of the optimal tradeoffs --- with respect to accuracy, and invariance --- achievable by invariant representations is still severely lacking. In this paper, we provide an information theoretic analysis of such tradeoffs under both classification and regression settings.
1196, Efficient Learning of Linear Graph Neural Networks Via Node Subsampling
Seiyun Shin; Ilan Shomorony; Han Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present empirical results for regression problems on two real-world graphs and show that our algorithm significantly outperforms other baseline sampling strategies that exploit the same number of observations.
1197, A Bounded Ability Estimation for Computerized Adaptive Testing
Yan Zhuang; Qi Liu; Guanhao Zhao; Zhenya Huang; Weizhe Huang; Zachary Pardos; Enhong Chen; Jinze Wu; Xin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we analyze the statistical properties of estimation and find a theoretical approximation of the true ability: the ability estimated by full responses to question bank.
1198, Towards More Stable Training of Diffusion Model Via Scaling Network Long Skip Connection
Zhongzhan Huang; Pan Zhou; Shuicheng Yan; Liang Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, theoretical understandings of the instability of UNet in diffusion models and also the performance improvement of LSC scaling remain absent yet. To solve this issue, we theoretically show that the coefficients of LSCs in UNet have big effects on the stableness of the forward and backward propagation and robustness of UNet.
1199, Finding Local Minima Efficiently in Decentralized Optimization
Wenhan Xian; Heng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we study the second-order optimality of decentralized stochastic algorithm that escapes saddle point efficiently for nonconvex optimization problems.
1200, Optimization and Bayes: A Trade-off for Overparameterized Neural Networks
Zhengmian Hu; Heng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel algorithm, Transformative Bayesian Learning (TansBL), which bridges the gap between empirical risk minimization (ERM) and Bayesian learning for neural networks.
1201, Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
Junyi Li; Feihu Huang; Heng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate Federated Bilevel Optimization problems and propose a communication-efficient algorithm, named FedBiOAcc.
1202, Resolving The Tug-of-War: A Separation of Communication and Learning in Federated Learning
Junyi Li; Heng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we find that learning and communication have fundamentally divergent requirements for parameter selection, akin to two opposite teams in a tug-of-war game. To mitigate this discrepancy, we introduce FedSep, a novel two-layer federated learning framework.
1203, Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork
Qiang Gao; Xiaojun Shan; Yuchen Zhang; Fan Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As there exist competitive subnetworks within a dense network in concert with Lottery Ticket Hypothesis, we introduce a novel neuron-wise task incremental learning method, namely Data-free Subnetworks (DSN), which attempts to enhance the elastic knowledge transfer across the tasks that sequentially arrive.
1204, Minimax-Optimal Location Estimation
Shivam Gupta; Jasper Lee; Eric Price; Paul Valiant;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The maximum likelihood estimator (MLE) is known to be asymptotically optimal as $n \to \infty$, but what is possible for finite $n$? In this paper, we give two location estimators that are optimal under different criteria: 1) an estimator that has minimax-optimal estimation error subject to succeeding with probability $1-\delta$ and 2) a confidence interval estimator which, subject to its output interval containing $\mu$ with probability at least $1-\delta$, has the minimum expected squared interval width among all shift-invariant estimators.
1205, Compact Neural Volumetric Video Representations with Dynamic Codebooks
Haoyu Guo; Sida Peng; Yunzhi Yan; Linzhan Mou; Yujun Shen; Hujun Bao; Xiaowei Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, such explicit representations easily lead to large model sizes when modeling dynamic scenes. To solve this problem, our key idea is reducing the spatial and temporal redundancy of feature grids, which intrinsically exist due to the self-similarity of scenes.
1206, Non-autoregressive Machine Translation with Probabilistic Context-free Grammar
Shangtong Gui; Chenze Shao; Zhengrui Ma; xishan zhang; Yunji Chen; Yang Feng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, conventional NAT models suffer from limited-expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens.
1207, Beyond MLE: Convex Loss for Text Generation
Chenze Shao; Zhengrui Ma; Min Zhang; Yang Feng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution.
1208, Act As You Wish: Fine-grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs
Peng Jin; Yang Wu; Yanbo Fan; Zhongqian Sun; Wei Yang; Li Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose hierarchical semantic graphs for fine-grained control over motion generation.
1209, A Riemannian Exponential Augmented Lagrangian Method for Computing The Projection Robust Wasserstein Distance
Bo Jiang; Ya-Feng Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Projection robust Wasserstein (PRW) distance is recently proposed to efficiently mitigate the curse of dimensionality in the classical Wasserstein distance. In this paper, by equivalently reformulating the computation of the PRW distance as an optimization problem over the Cartesian product of the Stiefel manifold and the Euclidean space with additional nonlinear inequality constraints, we propose a Riemannian exponential augmented Lagrangian method (REALM) for solving this problem.
1210, Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks
Andong Wang; Chao Li; Mingyuan Bai; Zhong Jin; Guoxu Zhou; Qibin Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our analysis highlights the potential of transformed low-rank parameterization in enhancing the robust generalization of t-NNs, offering valuable insights for further research and development.
1211, Cal-DETR: Calibrated Detection Transformer
Muhammad Akhtar Munir; Salman Khan; Muhammad Haris Khan; Mohsen Ali; Fahad Shahbaz Khan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address the problem by proposing a mechanism for calibrated detection transformers (Cal-DETR), particularly for Deformable-DETR and UP-DETR.
1212, StoryBench: A Multifaceted Benchmark for Continuous Story Visualization
Emanuele Bugliarello; H. Hernan Moraldo; Ruben Villegas; Mohammad Babaeizadeh; Mohammad Taghi Saffar; Han Zhang; Dumitru Erhan; Vittorio Ferrari; Pieter-Jan Kindermans; Paul Voigtlaender;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Creating a benchmark for video generation requires data annotated over time, which contrasts with the single caption used often in video datasets. To fill this gap, we collect comprehensive human annotations on three existing datasets, and introduce StoryBench: a new, challenging multi-task benchmark to reliably evaluate forthcoming text-to-video models.
1213, A Reduction-based Framework for Sequential Decision Making with Delayed Feedback
Yunchang Yang; Han Zhong; Tianhao Wu; Bin Liu; Liwei Wang; Simon Du;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel reduction-based framework, which turns any multi-batched algorithm for sequential decision making with instantaneous feedback into a sample-efficient algorithm that can handle stochastic delays in sequential decision making.
1214, Learning to Influence Human Behavior with Offline Reinforcement Learning
Joey Hong; Sergey Levine; Anca Dragan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead, we focus on influence in settings where there is a need to capture human suboptimality.
1215, Bandit Task Assignment with Unknown Processing Time
Shinji Ito; Daisuke Hatano; Hanna Sumita; Kei Takemura; Takuro Fukunaga; Naonori Kakimura; Ken-Ichi Kawarabayashi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The problem generalizes the stochastic combinatorial semi-bandit problem and the budget-constrained bandit problem. For this problem setting, we propose an algorithm based on upper confidence bounds~(UCB) combined with a phased-update approach.
1216, An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits
Shinji Ito; Kei Takemura;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider how to construct best-of-both-worlds linear bandit algorithms that achieve nearly optimal performance for both stochastic and adversarial environments.
1217, Laying The Foundation for An Instruction-Following Generalist Agent in Minecraft
Shalev Lifshitz; Keiran Paster; Harris Chan; Jimmy Ba; Sheila McIlraith;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study introduces an instruction-tuned Video Pretraining (VPT) model for Minecraft called STEVE-1, demonstrating that the unCLIP approach, utilized in DALL•E 2, is also effective for creating instruction-following sequential decision-making agents.
1218, DICES Dataset: Diversity in Conversational AI Evaluation for Safety
Lora Aroyo; Alex Taylor; Mark Diaz; Christopher Homan; Alicia Parrish; Gregory Serapio-García; Vinodkumar Prabhakaran; Ding Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This is especially troubling when building safety datasets for conversational AI systems, as safety is socio-culturally situated in this context. To demonstrate this crucial aspect of conversational AI safety, and to facilitate in-depth model performance analyses, we introduce the DICES (Diversity In Conversational AI Evaluation for Safety) dataset that contains fine-grained demographics information about raters, high replication of ratings per item to ensure statistical power for analyses, and encodes rater votes as distributions across different demographics to allow for in-depth explorations of different aggregation strategies.
1219, Vocabulary-free Image Classification
Alessandro Conti; Enrico Fini; Massimiliano Mancini; Paolo Rota; Yiming Wang; Elisa Ricci;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We thus formalize a novel task, termed as Vocabulary-free Image Classification (VIC), where we aim to assign to an input image a class that resides in an unconstrained language-induced semantic space, without the prerequisite of a known vocabulary.
1220, Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
ABHRA CHAUDHURI; Massimiliano Mancini; Zeynep Akata; Anjan Dutta;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The relational representations relied upon by such methods, however, are abstract. We aim to deconstruct this abstraction by expressing such relationships as interpretable graphs over image views.
1221, SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multiple Explanations
Ziyuan Ye; Rihan Huang; Qilin Wu; Quanying Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose $\underline{\text{S}}$tructure-$\underline{\text{A}}$ware Shapley-based $\underline{\text{M}}$ulti-$\underline{\text{E}}$xplanation (SAME) method to address the structure-aware feature interactions challenges for GNNs explanation with a theoretical foundation.
1222, Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization
Ruichen Jiang; Aryan Mokhtari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an accelerated quasi-Newton proximal extragradient method for solving unconstrained smooth convex optimization problems.
1223, RECKONING: Reasoning Through Dynamic Knowledge Encoding
Zeming Chen; Gail Weiss; Eric Mitchell; Asli Celikyilmaz; Antoine Bosselut;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This reasoning failure contrasts with the model’s apparent ability to distinguish its contextual knowledge from all the knowledge it has memorized during pre-training. Following this observation, we propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model’s parameters before presenting it with a question.
1224, HyP-NeRF: Learning Improved NeRF Priors Using A HyperNetwork
Bipasha Sen; Gaurav Singh; Aditya Agarwal; Rohith Agaram; Madhava Krishna; Srinath Sridhar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks.
1225, Towards Higher Ranks Via Adversarial Weight Pruning
Yuchuan Tian; Hanting Chen; Tianyu Guo; Chao Xu; Yunhe Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a Rank-based PruninG (RPG) method to maintain the ranks of sparse weights in an adversarial manner.
1226, Temporal Dynamic Quantization for Diffusion Model
Junhyuk So; Jungwon Lee; Daehyun Ahn; Hyungjun Kim; Eunhyeok Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel quantization method that dynamically adjusts the quantization interval based on time step information, significantly improving output quality.
1227, ARTree: A Deep Autoregressive Model for Phylogenetic Inference
Tianyu Xie; Cheng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a deep autoregressive model for phylogenetic inference based on graph neural networks (GNNs), called ARTree.
1228, StyleGAN Knows Normal, Depth, Albedo, and More
Anand Bhattad; Daniel McKee; Derek Hoiem; David Forsyth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper demonstrates that StyleGAN can easily be induced to produce intrinsic images.
1229, Towards Free Data Selection with General-Purpose Models
Yichen Xie; Mingyu Ding; Masayoshi TOMIZUKA; Wei Zhan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, current approaches typically follow a cumbersome pipeline that iterative the time-consuming model training and batch data selection repeatedly. In this paper, we challenge this status quo by proposing a novel free data selection (FreeSel) method following our designed new pipeline with existing general-purpose models hence a negligible extra time cost.
1230, On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond
Thanh Nguyen-Tang; Raman Arora;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We seek to understand what empowers sample-efficient learning from historical datasets for sequential decision-making, typically known as offline reinforcement learning (RL), in the context of (value) function approximation and which algorithms guarantee sample efficiency. In this paper, we extend our understanding of these important questions by (i) proposing a notion of data diversity that subsumes the previous notions of coverage measures in offline RL and (ii) using this notion to study three \emph{distinct} classes of offline RL algorithms that are based on version spaces (VS), regularized optimization (RO), and posterior sampling (PS).
1231, Generalizing Nonlinear ICA Beyond Structural Sparsity
Yujia Zheng; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the sparsity constraint may not hold universally for all sources in practice. Furthermore, the assumptions of bijectivity of the mixing process and independence among all sources, which arise from the setting of ICA, may also be violated in many real-world scenarios. To address these limitations and generalize nonlinear ICA, we propose a set of new identifiability results in the general settings of undercompleteness, partial sparsity and source dependence, and flexible grouping structures.
1232, Learning to Separate in Branch-and-Cut
Sirui Li; Wenbin Ouyang; Max Paulus; Cathy Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work identifies that MILP solvers can be drastically accelerated by appropriately selecting separators to activate.
1233, Asymmetric Certified Robustness Via Feature-Convex Neural Networks
Samuel Pfrommer; Brendon Anderson; Julien Piet; Somayeh Sojoudi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We formalize the asymmetric robustness certification problem and correspondingly present the feature-convex neural network architecture, which composes an input-convex neural network (ICNN) with a Lipschitz continuous feature map in order to achieve asymmetric adversarial robustness.
1234, Contrast Everything: Multi-Granularity Representation Learning for Medical Time-Series
Yihe Wang; Yu Han; Haishuai Wang; Xiang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the complex nature of heterogeneous data structures still presents significant challenges in medical time series analysis. To tackle these issues, we propose COMET, a multi-granularity framework that leverages data consistencies at different levels inherent in medical time series data.
1235, When Does Optimizing A Proper Loss Yield Calibration?
Jarosław Błasiok; Parikshit Gopalan; Lunjia Hu; Preetum Nakkiran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: What precise calibration guarantees does it give? In this work, we provide a rigorous answer to these questions.
1236, Universality and Limitations of Prompt Tuning
Yihan Wang; Jatin Chauhan; Wei Wang; Cho-Jui Hsieh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the demonstrated empirical efficacy of prompt-tuning to adapt a pretrained language model for a new task, the theoretical underpinnings of the difference between tuning parameters before the input against the tuning of model weights are limited. We thus take one of the first steps to understand the role of soft-prompt tuning for transformer-based architectures.
1237, Fast Online Changepoint Detection Via Functional Pruning CUSUM Statistics
Gaetano Romano; Idris A. Eckley; Paul Fearnhead; Guillem Rigaill;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Such choices affect which changes the algorithms have most power to detect. We introduce an algorithm, Functional Online CuSUM (FOCuS), which is equivalent to running these earlier methods simultaneously for all sizes of windows, or all possible values for the size of change.
1238, Inserting Anybody in Diffusion Models Via Celeb Basis
Ge Yuan; Xiaodong Cun; Yong Zhang; Maomao Li; Chenyang Qi; Xintao Wang; Ying Shan; Huicheng Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We thus propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just one facial photograph and only 1024 learnable parameters under 3 minutes.
1239, ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation
Chenyang Le; Yao Qian; Long Zhou; Shujie LIU; Yanmin Qian; Michael Zeng; Xuedong Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present ComSL, a speech-language model built atop a composite architecture of public pre-trained speech-only and language-only models and optimized data-efficiently for spoken language tasks.
1240, Fast Optimal Transport Through Sliced Generalized Wasserstein Geodesics
Guillaume Mahey; Laetitia Chapel; Gilles Gasso; Clément Bonet; Nicolas Courty;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new proxy of the squared WD, coined $\textnormal{min-SWGG}$, that is based on the transport map induced by an optimal one-dimensional projection of the two input distributions.
1241, Learning Runtime Decisions for Adaptive Real-Time Perception
Anurag Ghosh; Akshay Nambi; Vaibhav Balloli; Aditya Singh; Tanuja Ganu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Earlier runtime execution frameworks employed rule-based decision algorithms and operated with a fixed algorithm latency budget to balance these concerns, which is sub-optimal and inflexible. We propose Chanakya, a learned approximate execution framework that naturally derives from the streaming perception paradigm, to automatically learn decisions induced by these tradeoffs instead.
1242, Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers
Sotiris Anagnostidis; Dario Pavllo; Luca Biggio; Lorenzo Noci; Aurelien Lucchi; Thomas Hofmann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we present a novel approach that dynamically prunes contextual information while preserving the model's expressiveness, resulting in reduced memory and computational requirements during inference.
1243, Nonparametric Teaching for Multiple Learners
Chen Zhang; Xiaofeng Cao; Weiyang Liu; Ivor Tsang; James Kwok;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of teaching multiple learners simultaneously in the nonparametric iterative teaching setting, where the teacher iteratively provides examples to accelerate the learning of a general target model by the learner.
1244, Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning
Marina Munkhoeva; Ivan Oseledets;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we attempt to provide an understanding from the perspective of a Laplace operator and connect the inductive bias stemming from the augmentation process to a low-rank matrix completion problem.
1245, Defending Against Data-Free Model Extraction By Distributionally Robust Defensive Training
Zhenyi Wang; Li Shen; Tongliang Liu; Tiehang Duan; Yanjun Zhu; Donglin Zhan; DAVID DOERMANN; Mingchen Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a Memory and Computation efficient defense approach, named MeCo, to prevent DFME from happening while maintaining the model utility simultaneously by distributionally robust defensive training on the target victim model.
1246, Generalized Logit Adjustment: Calibrating Fine-tuned Models By Removing Foundation Class Bias
Beier Zhu; Kaihua Tang; QIANRU SUN; Hanwang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we systematically examine the biases in foundation models and demonstrate the efficacy of our proposed Generalized Logit Adjustment (GLA) method.
1247, Towards Data-Agnostic Pruning At Initialization: What Makes A Good Sparse Mask?
Hoang Pham; The Anh Ta; Shiwei Liu; Lichuan Xiang; Dung Le; Hongkai Wen; Long Tran-Thanh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study PaI from a brand-new perspective -- the topology of subnetworks.
1248, Trans-Dimensional Generative Modeling Via Jump Diffusion Models
Andrew Campbell; William Harvey; Christian Weilbach; Valentin De Bortoli; Thomas Rainforth; Arnaud Doucet;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a new class of generative model that naturally handles data of varying dimensionality by jointly modeling the state and dimension of each datapoint.
1249, Unifying GANs and Score-Based Diffusion As Generative Particle Models
Jean-Yves Franceschi; Mike Gartrell; Ludovic Dos Santos; Thibaut Issenhuth; Emmanuel de Bézenac; Mickael Chen; Alain Rakotomamonjy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we challenge this interpretation and propose a novel framework that unifies particle and adversarial generative models by framing generator training as a generalization of particle models.
1250, Flow-Attention-based Spatio-Temporal Aggregation Network for 3D Mask Detection
Yuxin Cao; Yian Li; Yumeng Zhu; Derui Wang; Minhui Xue;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, rPPG-based methods are sensitive to noisy interference and require at least one second (> 25 frames) of observation time, which induces high computational overhead. To address these challenges, we propose a novel 3D mask detection framework, called FASTEN (Flow-Attention-based Spatio-Temporal aggrEgation Network).
1251, Expressivity-Preserving GNN Simulation
Fabian Jogl; Maximilian Thiessen; Thomas Gärtner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our contribution leads to a direct way to translate common operations of non-standard GNNs to graph transformations that allow for strong or weak simulation.
1252, SOAR: Improved Quantization for Nearest Neighbor Search
Philip Sun; David Simcha; Dave Dopson; Ruiqi Guo; Sanjiv Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search.
1253, GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection
Jianheng Tang; Fengrui Hua; Ziqi Gao; Peilin Zhao; Jia Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In response, we present GADBench---a comprehensive benchmark for supervised anomalous node detection on static graphs.
1254, Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning
Hengli Li; Song-Chun Zhu; Zilong Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new benchmark, Diplomat, aiming at a unified paradigm for pragmatic reasoning and situated conversational understanding.
1255, Scale Alone Does Not Improve Mechanistic Interpretability in Vision Models
Roland S. Zimmermann; Thomas Klein; Wieland Brendel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We here use a psychophysical paradigm to quantify mechanistic interpretability for a diverse suite of models and find no scaling effect for interpretability - neither for model nor dataset size.
1256, Margin-based Adversarial Learning for Domain Generalization
Aveen Dayal; Vimal K B; Linga Reddy Cenkeramaddi; C Mohan; Abhinav Kumar; Vineeth N Balasubramanian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, only a few algorithms have been developed based on theoretical frameworks. To mitigate this gap, this work proposes a novel adversarial learning DG algorithm, $\textbf{MADG}$, inspired by a theoretical framework for addressing unseen target error.
1257, Self-Supervised Lagrangian Motion Magnification
Zhaoying Pan; Daniel Geng; Andrew Owens;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we revisit the classic Lagrangian approach in motion magnification and integrate it with modern self-supervised learning techniques.
1258, FlowCam: Training Generalizable 3D Radiance Fields Without Camera Poses Via Pixel-Aligned Scene Flow
Cameron Smith; Yilun Du; Ayush Tewari; Vincent Sitzmann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a method that jointly reconstructs camera poses and 3D neural scene representations online and in a single forward pass.
1259, Emergent Communication for Rules Reasoning
Yuxuan Guo; Yifan Hao; Rui Zhang; Enshuai Zhou; Zidong Du; xishan zhang; Xinkai Song; Xuehai Zhou; Jiaming Guo; Qi Yi; Shaohui Peng; Di Huang; Ruizhi Chen; Qi Guo; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, inspired by the classic human reasoning test (namely Raven's Progressive Matrix), we propose the Reasoning Game, a cognition-oriented environment that encourages agents to reason and communicate high-level rules, rather than perceived low-level contexts.
1260, Efficient Symbolic Policy Learning Via Gradient Descent
Jiaming Guo; Rui Zhang; Shaohui Peng; Qi Yi; Xing Hu; Ruizhi Chen; Zidong Du; xishan zhang; Ling Li; Qi Guo; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an efficient gradient-based learning method named Efficient Symbolic Policy Learning (ESPL) that learns the symbolic policy from scratch in an end-to-end way.
1261, TrojPrompt: A Black-box Trojan Attack on Pre-trained Language Models
Jiaqi Xue; Yepeng Liu; Mengxin Zheng; Ting Hua; Yilin Shen; Ladislau Bölöni; Qian Lou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we undertake a pioneering study on the Trojan susceptibility of prompt-learning PLM APIs.
1262, Recasting Meta-Continual Learning As Sequence Modeling
Soochan Lee; Jaehyeon Son; Gunhee Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we aim to establish a strong connection between two significant bodies of machine learning research: continual learning and sequence modeling.
1263, A Scalable Neural Network for DSIC Affine Maximizer Auction Design
Zhijian Duan; Haoran Sun; Yurong Chen; Xiaotie Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the former cannot strictly ensure dominant strategy incentive compatibility (DSIC), while the latter faces scalability issue due to the large number of allocation candidates. To address these limitations, we propose AMenuNet, a scalable neural network that constructs the AMA parameters (even including the allocation menu) from bidder and item representations.
1264, Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds
Ziqiao Wang; Yongyi Mao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present new information-theoretic generalization guarantees through the a novel construction of the neighboring-hypothesis matrix and a new family of stability notions termed sample-conditioned hypothesis (SCH) stability.
1265, Characterizing Out-of-Distribution Error Via Optimal Transport
Yuzhe Lu; Yilong Qin; Runtian Zhai; Andrew Shen; Ketong Chen; Zhenlin Wang; Soheil Kolouri; Simon Stepputtis; Joseph Campbell; Katia Sycara;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While a number of methods have been proposed by prior work,they often underestimate the actual error, sometimes by a large margin, which greatly impacts their applicability to real tasks. In this work, we identify *pseudo-label shift*, or the difference between the predicted and true OOD label distributions, as a key indicator to this underestimation.
1266, Identification of Nonlinear Latent Hierarchical Models
Lingjing Kong; Biwei Huang; Feng Xie; Eric Xing; Yuejie Chi; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate the identification problem for nonlinear latent hierarchical causal models in which observed variables are generated by a set of causally related latent variables, and some latent variables may not have observed children.
1267, Should Under-parameterized Student Networks Copy or Average Teacher Weights?
Berfin Simsek; Amire Bendjeddou; Wulfram Gerstner; Johanni Brea;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For shallow neural networks with odd activation function, we prove that ``copy-average'' configurations are critical points, and the optimum is reached when $n-1$ student neurons with erf activation each copy one teacher neuron and the $n$-th student neuron averages the remaining $k-n+1$ teacher neurons, if the teacher's incoming weights are orthonormal, it's outgoing weights are unitary and the input is standard Gaussian. For the student network with $n=1$ neuron, we provide additionally a closed-form solution of the unique non-trivial critical point for commonly used activation functions.
1268, RETVec: Resilient and Efficient Text Vectorizer
Elie Bursztein; Marina Zhang; Owen Vallis; XINYU JIA; Alexey Kurakin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper describes RETVec, a resilient, multilingual text vectorizer designed for neural-based text processing, including for small-text classification and large-language models.
1269, Scaling MLPs: A Tale of Inductive Bias
Gregor Bachmann; Sotiris Anagnostidis; Thomas Hofmann;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we revisit the most fundamental building block in deep learning, the multi-layer perceptron (MLP), and study the limits of its performance on vision tasks.
1270, Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities
Donghao Ying; Yunkai Zhang; Yuhao Ding; Alec Koppel; Javad Lavaei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The exponential growth of the state-action space size with the number of agents presents challenges for global observability, further exacerbated by the global coupling arising from agents' safety constraints. To tackle this issue, we propose a primal-dual method utilizing shadow reward and $\kappa$-hop neighbor truncation under a form of correlation decay property, where $\kappa$ is the communication radius.
1271, Memory-Constrained Algorithms for Convex Optimization
Moise Blanchard; Junhui Zhang; Patrick Jaillet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a family of recursive cutting-plane algorithms to solve feasibility problems with constrained memory, which can also be used for first-order convex optimization.
1272, Learning Mixtures of Gaussians Using The DDPM Objective
Kulin Shah; Sitan Chen; Adam Klivans;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we give the first provably efficient results for one of the most fundamental distribution families, Gaussian mixture models.
1273, Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations
Thomas Yerxa; Yilun Kuang; Eero Simoncelli; SueYeon Chung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we outline the simplifying assumptions that allow manifold capacity to be optimized directly, yielding Maximum Manifold Capacity Representations (MMCR).
1274, A Spectral Theory of Neural Prediction and Alignment
Abdulkadir Canatar; Jenelle Feather; Albert Wakhloo; SueYeon Chung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To gain insight into this, we use a recent theoretical framework that relates the generalization error from regression to the spectral bias of the model activations and the alignment of the neural responses onto the learnable subspace of the model. We extend this theory to the case of regression between model activations and neural responses, and define geometrical properties describing the error embedding geometry.
1275, Composable Coresets for Determinant Maximization: Greedy Is Almost Optimal
Siddharth Gollapudi; Sepideh Mahabadi; Varun Sivashankar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that the widely-used Greedy algorithm also provides composable coresets with an almost optimal approximation factor of $O(k)^{3k}$, which improves over the previously known guarantee of $C^{k^2}$, and supports the prior experimental results showing the practicality of the greedy algorithm as a coreset.
1276, Compositional Generalization from First Principles
Thaddäus Wiedemer; Prasanna Mayilvahanan; Matthias Bethge; Wieland Brendel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To get a better handle on compositional generalization, we here approach it from the bottom up: Inspired by identifiable representation learning, we investigate compositionality as a property of the data-generating process rather than the data itself.
1277, SatBird: A Dataset for Bird Species Distribution Modeling Using Remote Sensing and Citizen Science Data
Mélisande Teng; Amna Elmustafa; Benjamin Akera; Hager Radi; Yoshua Bengio; Hugo Larochelle; David Rolnick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel task for mapping bird species to their habitats by predicting species encounter rates from satellite images, and present SatBird, a satellite dataset of locations in the USA with labels derived from presence-absence observation data from the citizen science database eBird, considering summer (breeding) and winter seasons.
1278, Active Learning-Based Species Range Estimation
Christian Lange; Elijah Cole; Grant Horn; Oisin Mac Aodha;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore the task of estimating the geographical range of a species from a limited set of on the ground observations via a new active learning approach.
1279, CORL: Research-oriented Deep Offline Reinforcement Learning Library
Denis Tarasov; Alexander Nikulin; Dmitry Akimov; Vladislav Kurenkov; Sergey Kolesnikov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: CORL is an open-source library that provides thoroughly benchmarked single-file implementations of both deep offline and offline-to-online reinforcement learning algorithms.
1280, Revisiting The Minimalist Approach to Offline Reinforcement Learning
Denis Tarasov; Vladislav Kurenkov; Alexander Nikulin; Sergey Kolesnikov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the effect of these design choices on established baselines remains understudied. In this work, we aim to bridge this gap by conducting a retrospective analysis of recent works in offline RL and propose ReBRAC, a minimalistic algorithm that integrates such design elements built on top of the TD3+BC method.
1281, Don't Be So Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models
Leonardo Galli; Holger Rauhut; Mark Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a POlyak NOnmonotone Stochastic (PoNoS) method, obtained by combining a nonmonotone line search with a Polyak initial step size.
1282, All In One: A Chinese Multi-Modal Dataset for Multi-Affection Detection in Conversations
Yazhou Zhang; Yang Yu; Qing Guo; Benyou Wang; Dongming Zhao; Sagar Uprety; Dawei Song; Jing Qin; Qiuchi Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent advances in this field employed multi-task learning paradigms to render the inter-relatedness across tasks, but the scarcity of publicly available resources sets a limit to the potential of works. To fill this gap, we build the first Chinese Multi-modal Multi-Affection conversation (CMMA) dataset, which contains 3,000 multi-party conversations and 21,795 multi-modal utterances collected from various styles of TV-series.
1283, Phase Diagram of Early Training Dynamics in Deep Neural Networks: Effect of The Learning Rate, Depth, and Width
Dayal Singh Kalra; Maissam Barkeshli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We systematically analyze optimization dynamics in deep neural networks (DNNs) trained with stochastic gradient descent (SGD) and study the effect of learning rate $\eta$, depth $d$, and width $w$ of the neural network.
1284, $S^3$: Increasing GPU Utilization During Generative Inference for Higher Throughput
Yunho Jin; Chun-Feng Wu; David Brooks; Gu-Yeon Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose $S^3$, which predicts the output sequence length, schedules generation queries based on the prediction to increase device resource utilization and throughput, and handle mispredictions.
1285, Connecting Certified and Adversarial Training
Yuhao Mao; Mark Müller; Marc Fischer; Martin Vechev;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose \tool, an (unsound) certified training method that combines IBP and PGD training to optimize more precise, although not necessarily sound, worst-case loss approximations, reducing over-regularization and increasing certified and standard accuracies.
1286, Extremal Domain Translation with Neural Optimal Transport
Milena Gazdieva; Alexander Korotin; Daniil Selikhanovych; Evgeny Burnaev;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the extremal transport (ET) which is a mathematical formalization of the theoretically best possible unpaired translation between a pair of domains w.r.t. the given similarity function.
1287, Entropic Neural Optimal Transport Via Diffusion Processes
Nikita Gushchin; Alexander Kolesov; Alexander Korotin; Dmitry Vetrov; Evgeny Burnaev;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a novel neural algorithm for the fundamental problem of computing the entropic optimal transport (EOT) plan between probability distributions which are accessible by samples.
1288, SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling
Jiaxiang Dong; Haixu Wu; Haoran Zhang; Li Zhang; Jianmin Wang; Mingsheng Long;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We thus present SimMTM, a Simple pre-training framework for Masked Time-series Modeling.
1289, Compression with Bayesian Implicit Neural Representations
Zongyu Guo; Gergely Flamich; Jiajun He; Zhibo Chen; José Miguel Hernández-Lobato;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, most current solutions for this are inefficient, as quantization to low-bit precision substantially degrades the reconstruction quality. To address this issue, we propose overfitting variational Bayesian neural networks to the data and compressing an approximate posterior weight sample using relative entropy coding instead of quantizing and entropy coding it.
1290, Learning Rate Free Bayesian Inference in Constrained Domains
Louis Sharrock; Lester Mackey; Christopher Nemeth;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a suite of new particle-based algorithms for sampling on constrained domains which are entirely learning rate free.
1291, Geodesic Multi-Modal Mixup for Robust Fine-Tuning
Changdae Oh; Junhyuk So; Hoyoon Byun; YongTaek Lim; Minchul Shin; Jong-June Jeon; Kyungwoo Song;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we found that representation learned by CLIP has two separate subspaces for each heterogeneous modality with poor alignment.
1292, Locally Invariant Explanations: Towards Stable and Unidirectional Explanations Through Local Invariant Learning
Amit Dhurandhar; Karthikeyan Natesan Ramamurthy; Kartik Ahuja; Vijay Arya;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although many variants have been proposed, few provide a simple way to produce high fidelity explanations that are also stable and intuitive. In this work, we provide a novel perspective by proposing a model agnostic local explanation method inspired by the invariant risk minimization (IRM) principle -- originally proposed for (global) out-of-distribution generalization -- to provide such high fidelity explanations that are also stable and unidirectional across nearby examples.
1293, Double and Single Descent in Causal Inference with An Application to High-Dimensional Synthetic Control
Jann Spiess; guido imbens; Amar Venugopal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: As our main contribution, we document the performance of high-dimensional synthetic control estimators with many control units.
1294, Black-Box Variational Inference Converges
Kyurae Kim; Kaiwen Wu; Jisu Oh; Yian Ma; Jacob Gardner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide the first convergence guarantee for full black-box variational inference (BBVI), also known as Monte Carlo variational inference.
1295, Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests
Edward Raff; James Holt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, to the best of our knowledge, it has gone unnoticed that almost all deep-MIL models proposed since 2016 do not respect the MIL assumptions and can learn anti-correlated instances (i.e., defaulting to positive labels until seeing a negative counter-example), which puts any down-stream task at risk of learning incorrect models at greater risk of operational failure or spurious over-fitting. We identify and demonstrate this problem via a proposed algorithmic unit test, where we create synthetic datasets that can be solved by a MIL respecting model, for which current methods fail.
1296, Feature Adaptation for Sparse Linear Regression
Jonathan Kelner; Frederic Koehler; Raghu Meka; Dhruv Rohatgi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide a polynomial-time algorithm that, given $\Sigma$, automatically adapts the Lasso to tolerate a small number of approximate dependencies.
1297, Collapsed Inference for Bayesian Deep Learning
Zhe Zeng; Guy Van den Broeck;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We tackle this challenge by revealing a previously unseen connection between inference on BNNs and volume computation problems. With this observation, we introduce a novel collapsed inference scheme that performs Bayesian model averaging using collapsed samples.
1298, On The Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices
Guillaume Wang; Lénaïc Chizat;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that, thanks to partial curvature, conic particle methods -- which optimize over both weights and supports of the mixed strategies -- generically converge faster than fixed-support methods.
1299, On Kernel-based Statistical Learning Theory in The Mean Field Limit
Christian Fiedler; Michael Herty; Sebastian Trimpe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by machine learning of interacting particle systems, we consider the situation when the number of input variables goes to infinity.
1300, Predicting A Protein's Stability Under A Million Mutations
Jeffrey Ouyang-Zhang; Daniel Diaz; Adam Klivans; Philipp Kraehenbuehl;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our main contribution is a simple, parallel decoding algorithm.
1301, Shaped Attention Mechanism in The Infinite Depth-and-Width Limit at Initialization
Lorenzo Noci; Chuning Li; Mufan Li; Bobby He; Thomas Hofmann; Chris Maddison; Dan Roy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by the success of Transformers, we study the covariance matrix of a modified Softmax-based attention modelwith skip connections in the proportional limit of infinite-depth-and-width.
1302, Bringing Regularized Optimal Transport to Lightspeed: A Splitting Method Adapted for GPUs
Jacob Lindbäck; Zesen Wang; Mikael Johansson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present an efficient algorithm for regularized optimal transport.
1303, Which Models Have Perceptually-Aligned Gradients? An Explanation Via Off-Manifold Robustness
Suraj Srinivas; Sebastian Bordt; Himabindu Lakkaraju;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the underlying mechanisms behind these phenomena remain unknown. In this work, we provide a first explanation of PAGs via \emph{off-manifold robustness}, which states that models must be more robust off- the data manifold than they are on-manifold.
1304, Connected Superlevel Set in (Deep) Reinforcement Learning and Its Application to Minimax Theorems
Sihan Zeng; Thinh Doan; Justin Romberg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The aim of this paper is to improve the understanding of the optimization landscape for policy optimization problems in reinforcement learning.
1305, Projection-Free Methods for Solving Nonconvex-Concave Saddle Point Problems
Morteza Boroun; Erfan Yazdandoost Hamedani; Afrooz Jalilzadeh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate a class of constrained saddle point (SP) problems where the objective function is nonconvex-concave and smooth.
1306, Batchnorm Allows Unsupervised Radial Attacks
Amur Ghose; Apurv Gupta; Yaoliang Yu; Pascal Poupart;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that for batch normalized deep image recognition architectures, intermediate latents that are produced after a batch normalization step by themselves suffice to produce adversarial examples using an intermediate loss solely utilizing angular deviations, without relying on any label.
1307, Federated Learning Via Meta-Variational Dropout
Insu Jeon; Minui Hong; Junhyeog Yun; Gunhee Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, traditional FL often encounters challenges in practical applications, including model overfitting and diverging local models due to the limited and non-i.i.d. data among clients. To resolve these issues, we introduce a novel Bayesian meta-learning approach named meta-variational dropout (MetaVD).
1308, Delegated Classification
Eden Saig; Inbal Talgam-Cohen; Nir Rosenfeld;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a theoretical framework for incentive-aware delegation of machine learning tasks.
1309, Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams
Esmaeil Seraj; Jerry Xiong; Mariah Schrum; Matthew Gombolay;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although prior work has shown that enabling communication among agents of a robot team can alleviate such issues, creating inter-agent communication under existing Multi-Agent LfD (MA-LfD) frameworks requires the human expert to provide demonstrations for both environment actions and communication actions, which necessitates an efficient communication strategy on a known message spaces. To address this problem, we propose Mixed-Initiative Multi-Agent Apprenticeship Learning (MixTURE).
1310, Training Neural Networks Is NP-Hard in Fixed Dimension
Vincent Froese; Christoph Hertrich;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the parameterized complexity of training two-layer neural networks with respect to the dimension of the input data and the number of hidden neurons, considering ReLU and linear threshold activation functions.
1311, On The Learnability of Multilabel Ranking
Vinod Raman; UNIQUE SUBEDI; Ambuj Tewari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we characterize the learnability of multilabel ranking problems in both batch and online settings for a large family of ranking losses.
1312, Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space
Saghar Adler; Vijay Subramanian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Algorithmic and learning procedures that have been developed to produce optimal policies mainly focus on finite state settings, and do not directly apply to these models. To overcome this lacuna, in this work we study the problem of optimal control of a family of discrete-time countable state-space Markov Decision Processes (MDPs) governed by an unknown parameter $\theta\in\Theta$, and defined on a countably-infinite state space $\mathcal X=\mathbb{Z}_+^d$, with finite action space $\mathcal A$, and an unbounded cost function.
1313, GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search
Xiao Zang; Miao Yin; Jinqi Xiao; Saman Zonouz; Bo Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, though the state-of-the-art GNN planner can efficiently extract and learn graph information, its inherent mechanism is not well suited for graph search process, hindering its further performance improvement. To address this challenge and fully unleash the potential of GNN in motion planning, this paper proposes GraphMP, a neural motion planner for both low and high-dimensional planning tasks.
1314, Global Structure-Aware Diffusion Process for Low-light Image Enhancement
Jinhui HOU; Zhiyu Zhu; Junhui Hou; Hui LIU; Huanqiang Zeng; Hui Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To additionally promote learning in challenging regions, we introduce an uncertainty-guided regularization technique, which judiciously relaxes constraints on the most extreme portions of the image.
1315, Nonparametric Identifiability of Causal Representations from Unknown Interventions
Julius von Kügelgen; Michel Besserve; Liang Wendong; Luigi Gresele; Armin Kekić; Elias Bareinboim; David Blei; Bernhard Schölkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our goal is to identify both the ground truth latents and their causalgraph up to a set of ambiguities which we show to be irresolvable from interventional data.
1316, SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models
Martin Gonzalez; Nelson Fernandez Pinto; Thuy Tran; elies Gherbi; Hatem Hajri; Nader Masmoudi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose Stochastic Exponential Derivative-free Solvers (SEEDS), improving and generalising Exponential Integrator approaches to the stochastic case on several frameworks.
1317, Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
Tiansheng Huang; Sihao Hu; Ka-Ho Chow; Fatih Ilhan; Selim Tekin; Ling Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents Lockdown, an isolated subspace training method to mitigate the poison-coupling effect.
1318, Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits
Dorian Baudry; Fabien Pesquerel; Rémy Degenne; Odalric-Ambrym Maillard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce several methods to approximate the infimum KL which reduce drastically the computational and memory costs of existing optimal algorithms, while keeping their regret guaranties.
1319, The S-value: Evaluating Stability with Respect to Distributional Shifts
Suyash Gupta; Dominik Rothenhäusler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a measure of instability that quantifies the distributional instability of a statistical parameter with respect to Kullback-Leibler divergence, that is, the sensitivity of the parameter under general distributional perturbations within a Kullback-Leibler divergence ball.
1320, Fast Trainable Projection for Robust Fine-tuning
Junjiao Tian; Yen-Cheng Liu; James S Smith; Zsolt Kira;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new projection-based fine-tuning algorithm, Fast Trainable Projection (FTP) for computationally efficient learning of per-layer projection constraints, resulting in an average 35% speedup on our benchmarks compared to prior works.
1321, Neural Injective Functions for Multisets, Measures and Graphs Via A Finite Witness Theorem
Tal Amir; Steven Gortler; Ilai Avni; Ravina Ravina; Nadav Dym;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, there remains a gap between the provably injective multiset functions considered in theory, which typically rely on polynomial moments, and the multiset functions used in practice which typically rely on $\textit{neural moments}$, whose injectivity on multisets has not been studied to date. In this paper we bridge this gap by showing that moments of neural network do define an injective multiset function, provided that an analytic non-polynomial activation is used.
1322, GEQ: Gaussian Kernel Inspired Equilibrium Models
Mingjie Li; Yisen Wang; Zhouchen Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One key factor responsible for this performance limitation is the use of linear kernels to extract features in these models. To address this issue, we propose a novel approach by replacing linear kernels with a new function that can readily capture nonlinear feature dependencies in the input data.
1323, The Distortion of Binomial Voting Defies Expectation
Yannai A. Gonczarowski; Gregory Kehne; Ariel Procaccia; Ben Schiffer; Shirley Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead, we introduce and study the expected distortion of voting rules with respect to an underlying distribution over voter utilities.
1324, Structured Zeroth-order for Non-smooth Optimization
Marco Rando; Cesare Molinari; Lorenzo Rosasco; Silvia Villa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, only the smooth setting was considered. To close this gap, we introduce and analyze O-ZD, the first structured finite-difference algorithm for non-smooth black-box optimization.
1325, Sampling from Gaussian Process Posteriors Using Stochastic Gradient Descent
Jihao Andreas Lin; Javier Antorán; Shreyas Padhy; David Janz; José Miguel Hernández-Lobato; Alexander Terenin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In general, this has a cubic cost in dataset size and is sensitive to conditioning. We explore stochastic gradient algorithms as a computationally efficient method of approximately solving these linear systems: we develop low-variance optimization objectives for sampling from the posterior and extend these to inducing points.
1326, ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation
Shuyang Sun; Weijun Wang; Andrew Howard; Qihang Yu; Philip Torr; Liang-Chieh Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present ReMaX, that adds relaxation to mask predictions and class predictions for panoptic segmentation.
1327, On Calibrating Diffusion Probabilistic Models
Tianyu Pang; Cheng Lu; Chao Du; Min Lin; Shuicheng Yan; Zhijie Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we observe that the stochastic reverse process of data scores is a martingale, from which concentration bounds and the optional stopping theorem for data scores can be derived.
1328, Advice Querying Under Budget Constraint for Online Algorithms
Ziyad Benomar; Vianney Perchet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, it is assumed in most works that the predictions are provided to the algorithm as input, with no constraint on their size. In this paper, we consider algorithms with access to a limited number of predictions, that they can request at any time during their execution.
1329, DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
Mintong Kang; Dawn Song; Bo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a unified framework DiffAttack to perform effective and efficient attacks against diffusion-based purification defenses, including both DDPM and score-based approaches.
1330, Near-optimal Learning with Average Hölder Smoothness
Guy Kornowski; Aryeh Kontorovich; Steve Hanneke;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Nevertheless, we provide distinct learning algorithms that achieve both (nearly) optimal learning rates.
1331, Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation
Yilin Lyu; Liyuan Wang; Xingxing Zhang; Zicheng Sun; Hang Su; Jun Zhu; Liping Jing;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the normalization layers provide an exception, as they are updated interdependently by the gradient and statistics of currently observed training samples, which require specialized strategies to mitigate recency bias. In this work, we focus on the most popular Batch Normalization (BN) and provide an in-depth theoretical analysis of its sub-optimality in continual learning.
1332, Temporal Robustness Against Data Poisoning
Wenxiao Wang; Soheil Feizi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address this issue, we leverage timestamps denoting the birth dates of data, which are often available but neglected in the past. Benefiting from these timestamps, we propose a temporal threat model of data poisoning with two novel metrics, earliness and duration, which respectively measure how long an attack started in advance and how long an attack lasted.
1333, The Transient Nature of Emergent In-context Learning in Transformers
Aaditya Singh; Stephanie Chan; Ted Moskovitz; Erin Grant; Andrew Saxe; Felix Hill;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we show that the emergence of ICL during transformer training is, in fact, often transient.
1334, Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
Thomas Hartvigsen; Swami Sankaranarayanan; Hamid Palangi; Yoon Kim; Marzyeh Ghassemi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose GRACE, a Lifelong Model Editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs.
1335, First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
Julia Olkhovskaya; Jack Mayo; Tim van Erven; Gergely Neu; Chen-Yu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the adversarial linear contextual bandit setting, whichallows for the loss functions associated with each of $K$ arms to changeover time without restriction.
1336, From Tempered to Benign Overfitting in ReLU Neural Networks
Guy Kornowski; Gilad Yehudai; Ohad Shamir;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, a theoretical justification of this claim for non-linear NNs has been lacking so far. In this work, we provide several results that aim at bridging these complementing views.
1337, What Functions Can Graph Neural Networks Compute on Random Graphs? The Role of Positional Encoding
Nicolas Keriven; Samuel Vaiter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We aim to deepen the theoretical understanding of Graph Neural Networks (GNNs) on large graphs, with a focus on their expressive power.
1338, Training Shallow ReLU Networks on Noisy Data Using Hinge Loss: When Do We Overfit and Is It Benign?
Erin George; Michael Murray; William Swartworth; Deanna Needell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study benign overfitting in two-layer ReLU networks trained using gradient descent and hinge loss on noisy data for binary classification.
1339, When Can We Track Significant Preference Shifts in Dueling Bandits?
Joe Suk; Arpit Agarwal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by concerns that user preferences/tastes can evolve over time, we consider the problem of _dueling bandits with distribution shifts_.
1340, Handling Data Heterogeneity Via Architectural Design for Federated Visual Recognition
Sara Pieri; Jose Restom; Samuel Horváth; Hisham Cholakkal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our study provides an extensive review of federated learning applied to visual recognition.
1341, Tester-Learners for Halfspaces: Universal Algorithms
Aravind Gollakota; Adam Klivans; Konstantinos Stavropoulos; Arsen Vasilyan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We give the first tester-learner for halfspaces that succeeds universally over a wide class of structured distributions.
1342, Do Imperceptible Perturbations Really Prevent Unauthorized Data Usage in Diffusion-based Image Generation Systems?
Bochuan Cao; Changjiang Li; Ting Wang; Jinyuan Jia; Bo Li; Jinghui Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that those existing methods provide a false sense of protection.
1343, Elastic Decision Transformer
Yueh-Hua Wu; Xiaolong Wang; Masashi Hamaya;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces Elastic Decision Transformer (EDT), a significant advancement over the existing Decision Transformer (DT) and its variants.
1344, PROTES: Probabilistic Optimization with Tensor Sampling
Anastasiia Batsheva; Andrei Chertkov; Gleb Ryzhakov; Ivan Oseledets;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We developed a new method PROTES for black-box optimization which is based on probabilistic sampling from a probability density function given in a low-parametric tensor train format.
1345, On The Constrained Time-Series Generation Problem
Andrea Coletta; Sriram Gopalakrishnan; Daniel Borrajo; Svitlana Vyetrenko;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel set of methods to tackle the constrained time series generation problem and provide efficient sampling while ensuring the realism of generated time series.
1346, Conformal Prediction for Time Series with Modern Hopfield Networks
Andreas Auer; Martin Gauch; Daniel Klotz; Sepp Hochreiter;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, they are difficult to apply to time series as the autocorrelative structure of time series violates basic assumptions required by conformal prediction. We propose HopCPT, a novel conformal prediction approach for time series that not only copes with temporal structures but leverages them.
1347, SHAP-IQ: Unified Approximation of Any-order Shapley Interactions
Fabian Fumagalli; Maximilian Muschalik; Patrick Kolpaczki; Eyke Hüllermeier; Barbara Hammer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we propose SHAPley Interaction Quantification (SHAP-IQ), an efficient sampling-based approximator to compute Shapley interactions for arbitrary cardinal interaction indices (CII), i.e. interaction indices that satisfy the linearity, symmetry and dummy axiom.
1348, Domain Adaptive Imitation Learning with Visual Observation
Sungho Choi; Seungyul Han; WOOJUN KIM; Jongseong Chae; Whiyoung Jung; Youngchul Sung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain.
1349, Exact Bayesian Inference on Discrete Models Via Probability Generating Functions: A Probabilistic Programming Approach
Fabian Zaiser; Andrzej Murawski; Luke Ong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present an exact Bayesian inference method for discrete statistical models, which can find exact solutions to many discrete inference problems, even with infinite support and continuous priors.
1350, On The Convergence to A Global Solution of Shuffling-Type Gradient Algorithms
Lam Nguyen; Trang H. Tran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we focus on the shuffling version of SGD which matches the mainstream practical heuristics.
1351, Minimum Description Length and Generalization Guarantees for Representation Learning
Milad Sefidgaran; Abdellatif Zaidi; Piotr Krasnowski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, first, we establish a framework that allows to derive upper bounds on the generalization error of a representation learning algorithm in terms of the Minimum Description Length'' (MDL) of the labels. Rather than the mutual information between the encoder�s input and output, which is often believed to reflect the algorithm�s generalization capability in related literature but in fact, falls short to do so, our new bounds involve the ``multi-letter� relative entropy of the labels of training and test sets and a fixed prior.
1352, Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
Zebang Shen; Zhenfu Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel approach based on the concept of entropy dissipation in the underlying system.
1353, Towards In-context Scene Understanding
Ivana Balazevic; David Steiner; Nikhil Parthasarathy; Relja Arandjelović; Olivier Henaff;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Computer vision, in contrast, has largely stayed in the former regime: specialized decoders and finetuning protocols are generally required to perform dense tasks such as semantic segmentation and depth estimation. In this work we explore a simple mechanism for in-context learning of such scene understanding tasks: nearest neighbor retrieval from a prompt of annotated features.
1354, Curvature Filtrations for Graph Generative Model Evaluation
Joshua Southern; Jeremy Wayland; Michael Bronstein; Bastian Rieck;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We combine graph curvature descriptors with emerging methods from topological data analysis to obtain robust, expressive descriptors for evaluating graph generative models.
1355, Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes
Emmeran Johnson; Ciara Pike-Burke; Patrick Rebeschini;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we bridge the gap between PI and PMD with exact policy evaluation and show that the dimension-free $\gamma$-rate of PI can be achieved by the general family of unregularised PMD algorithms under an adaptive step-size.
1356, Zero-One Laws of Graph Neural Networks
Sam Adam-Day; Iliant; Ismail Ceylan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We offer a novel theoretical perspective on the representation and extrapolation capacity of GNNs, by answering the question: how do GNNs behave as the number of graph nodes become very large? Under mild assumptions, we show that when we draw graphs of increasing size from the Erdős–Rényi model, the probability that such graphs are mapped to a particular output by a class of GNN classifiers tends to either zero or one.
1357, Provably Fast Finite Particle Variants of SVGD Via Virtual Particle Stochastic Approximation
Dheeraj Nagaraj; Aniket Das;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we design two computationally efficient variants of SVGD, namely VP-SVGD (which is conceptually elegant) and GB-SVGD (which is empirically effective), with provably fast finite-particle convergence rates.
1358, Coneheads: Hierarchy Aware Attention
Albert Tseng; Tao Yu; Toni Liu; Christopher De Sa;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the inner product does not explicitly model the complex structural properties of real world datasets, such as hierarchies between data points. To remedy this, we introduce cone attention, a drop-in replacement for dot product attention based on hyperbolic entailment cones.
1359, Diffusion Probabilistic Models for Structured Node Classification
Hyosoon Jang; Seonghyun Park; Sangwoo Mo; Sungsoo Ahn;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In particular, we focus on solving the problem for partially labeled graphs where it is essential to incorporate the information in the known label for predicting the unknown labels. To address this issue, we propose a novel framework leveraging the diffusion probabilistic model for structured node classification (DPM-SNC).
1360, Pointwise Uncertainty Quantification for Sparse Variational Gaussian Process Regression with A Brownian Motion Prior
Luke Travis; Kolyan Ray;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study pointwise estimation and uncertainty quantification for a sparse variational Gaussian process method with eigenvector inducing variables.
1361, Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization
Jui-Nan Yen; Sai Surya Duvvuri; Inderjit Dhillon; Cho-Jui Hsieh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To reduce the time and memory complexity without sacrificing performance, we propose approximating each diagonal block of the second moment matrix by low-rank matrices and enforcing the same basis for the blocks within each layer.
1362, Attentive Transfer Entropy to Exploit Transient Emergence of Coupling Effect
Xiaolei Ru; XINYA ZHANG; Jack Murdoch Moore; Zijia Liu; Gang Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of reconstructing coupled networks (e.g., biological neural networks) connecting large numbers of variables (e.g.,nerve cells), of which state evolution is governed by dissipative dynamics consisting of strong self-drive (dominants the evolution) and weak coupling-drive.
1363, A Unified Approach to Count-Based Weakly Supervised Learning
Vinay Shukla; Zhe Zeng; Kareem Ahmed; Guy Van den Broeck;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In many cases, these weak labels dictate the frequency of each respective class over a set of instances. In this paper, we develop a unified approach to learning from such weak supervision, which we call *count-based weakly supervised learning*.
1364, Accelerating Exploration with Unlabeled Prior Data
Qiyang Li; Jason Zhang; Dibya Ghosh; Amy Zhang; Sergey Levine;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study how prior data without reward labels may be used to guide and accelerate exploration for an agent solving a new sparse reward task.
1365, Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs
Yeyuan Chen; Dingmin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the limitations of R$^2$-GNNs regarding expressiveness, we propose a simple graph transformation technique, akin to a preprocessing step, which can be executed in linear time.
1366, RangePerception: Taming LiDAR Range View for Efficient and Accurate 3D Object Detection
Yeqi BAI; Ben Fei; Youquan Liu; Tao MA; Yuenan Hou; Botian Shi; Yikang LI;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Conversely, RV-based methods demonstrate higher efficiency due to their compactness and compatibility with 2D convolutions, but their performance still trails behind that of BEV-based methods. To eliminate this performance gap while preserving the efficiency of RV-based methods, this study presents an efficient and accurate RV-based 3D object detection framework termed RangePerception.
1367, LLMs for Semi-Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering
Noah Hollmann; Samuel Müller; Frank Hutter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present an approach for doing so by harnessing the power of large language models (LLMs).
1368, Brain Diffusion for Visual Exploration: Cortical Discovery Using Large Scale Generative Models
Andrew Luo; Maggie Henderson; Leila Wehbe; Michael Tarr;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Because the identification of such ROIs has typically relied on manually assembled stimulus sets consisting of isolated objects in non-ecological contexts, exploring functional organization without robust a priori hypotheses has been challenging. To overcome these limitations, we introduce a data-driven approach in which we synthesize images predicted to activate a given brain region using paired natural images and fMRI recordings, bypassing the need for category-specific stimuli.
1369, Amadeus: A Natural Language Interface for Interactive Animal Behavioral Analysis
shaokai ye; Jessy Lauer; Mu Zhou; Alexander Mathis; Mackenzie Mathis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, codifying behavior analysis is often challenging without deep understanding of animal behavior and technical machine learning knowledge. To limit this gap, we introduce Amadeus: a natural language interface that turns natural language descriptions of behaviors into machine-executable code.
1370, Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion
Ethan Pronovost; Meghana Reddy Ganesina; Kai Wang; Nick Roy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Scenario Diffusion, a novel diffusion-based architecture for generating traffic scenarios that enables controllable scenario generation.
1371, Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
Runa Eschenhagen; Alexander Immer; Richard Turner; Frank Schneider; Philipp Hennig;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we identify two different settings of linear weight-sharing layers which motivate two flavours of K-FAC -- \emph{expand} and \emph{reduce}.
1372, Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning
In Huh; changwook jeong; Jae Myung Choe; YOUNGGU KIM; Daesin Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel auto-encoding framework, named isometric quotient VAEs (IQVAEs), that can extract the quotient space from observations and learn the Riemannian isometry of the extracted quotient in an unsupervised manner.
1373, Harnessing The Power of Choices in Decision Tree Learning
Guy Blanc; Jane Lange; Chirag Pabbaraju; Colin Sullivan; Li-Yang Tan; Mo Tiwari;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a simple and natural generalization of standard and empirically successful decision tree learning algorithms such as ID3, C4.5, and CART.
1374, Generative Modeling Through Semi-dual Formulation of Unbalanced Optimal Transport
Jaemoo Choi; Jaewoong Choi; Myungjoo Kang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel generative model based on the semi-dual formulation of Unbalanced Optimal Transport (UOT).
1375, Weitzman's Rule for Pandora's Box with Correlations
Evangelia Gergatsouli; Christos Tzamos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we revisit Pandora’s Box when the value distributions are correlated, first studied in [CGT+20].
1376, An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination
Xue Yan; Jiaxian Guo; Xingzhou Lou; Jun Wang; Haifeng Zhang; Yali Du;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The necessity of such populations severely limits their computational efficiency. To address this issue, we propose E3T, an **E**fficient **E**nd-to-**E**nd **T**raining approach for zero-shot human-AI coordination.
1377, Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games
Minbo Gao; Zhengfeng Ji; Tongyang Li; Qisheng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the first online quantum algorithm for zero-sum games with $\widetilde O(1)$ regret under the game setting.
1378, Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy
Amit Daniely; Nati Srebro; Gal Vardi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, it was previously shown that depth-$2$ networks can be efficiently learned under the assumptions that the input distribution is Gaussian, and the weight matrix is non-degenerate. In this work, we study whether such assumptions may suffice for learning deeper networks and prove negative results.
1379, Cross-Scale MAE: A Tale of Multiscale Exploitation in Remote Sensing
Maofeng Tang; Andrei Cozma; Konstantinos Georgiou; Hairong Qi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper revisits the classical multiscale representation learning problem but under the general framework of self-supervised learning for remote sensing image understanding. We present Cross-Scale MAE, a self-supervised model built upon the Masked Auto-Encoder (MAE), which tackles these challenges by learning relationships between data at different scales during pretraining.
1380, Evolving Standardization for Continual Domain Generalization Over Temporal Drift
Mixue Xie; Shuang Li; Longhui Yuan; Chi Liu; Zehui Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Re-training and updating models with both new and previous domains using existing DG methods can be resource-intensive and inefficient. Therefore, in this paper, we present a problem formulation for Continual Domain Generalization over Temporal Drift (CDGTD).
1381, Computational Guarantees for Doubly Entropic Wasserstein Barycenters
Lénaïc Chizat; Tomas Vaskevicius;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose and analyze an algorithm for computing doubly regularized Wasserstein barycenters.
1382, Common Ground in Cooperative Communication
Yash Jhaveri; Xiaoran Hao; Patrick Shafto;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a general theory of cooperative communication that is mathematically principled and explicitly defines a spectrum of common ground possibilities, going well beyond that of perfect and complete knowledge sharing, on spaces that permit arbitrary representations of data and hypotheses.
1383, On Proper Learnability Between Average- and Worst-case Robustness
Vinod Raman; UNIQUE SUBEDI; Ambuj Tewari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we initiate the study of proper learning under relaxations of the worst-case robust loss.
1384, AllSim: Systematic Simulation and Benchmarking of Repeated Resource Allocation Policies in Multi-User Systems with Varying Resources
Jeroen Berrevoets; Daniel Jarrett; Alex Chan; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, a key limitation has been the absence of good methods and test-beds for benchmarking these policies; almost all resource allocation policies are benchmarked in environments which are either completely synthetic or do not allow _any_ deviation from historical data. In this paper we introduce AllSim, which is a benchmarking environment for realistically simulating the impact and utility of policies for resource allocation in systems in which users compete for such scarce resources.
1385, T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
Kaiyi Huang; Kaiyue Sun; Enze Xie; Zhenguo Li; Xihui Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a new approach, Generative mOdel finetuning with Reward-driven Sample selection (GORS), to boost the compositional text-to-image generation abilities of pretrained text-to-image models.
1386, Platonic Distance: Intrinsic Object-Centric Image Similarity
Klemen Kotar; Stephen Tian; Hong-Xing Yu; Dan Yamins; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose to extend it to general object categories, exploring an image similarity metric based on object intrinsics.
1387, AndroidInTheWild: A Large-Scale Dataset For Android Device Control
Christopher Rawles; Alice Li; Oriana Riva; Daniel Rodriguez; Timothy Lillicrap;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new dataset for mobile device control, AndroidInTheWild, which is orders of magnitude larger than current datasets.
1388, Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images
Pai Chet Ng; Zhixiang Chi; Yannick Verdie; Juwei Lu; Konstantinos N Plataniotis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Hyper-Skin, a hyperspectral dataset covering wide range of wavelengths from visible (VIS) spectrum (400nm - 700nm) to near-infrared (NIR) spectrum (700nm - 1000nm), uniquely designed to facilitate research on facial skin-spectra reconstruction with consumer cameras.
1389, Reimagining Synthetic Data Generation Through Data-Centric AI: A Comprehensive Benchmark
Lasse Hansen; Nabeel Seedat; Mihaela van der Schaar; Andrija Petrovic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Subsequently, we propose a novel framework to evaluate the integration of data profiles to guide the creation of more representative synthetic data.
1390, Differentially Private Statistical Inference Through $\beta$-Divergence One Posterior Sampling
Jack Jewson; Sahra Ghalebikesabi; Chris C Holmes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The application of current approaches has, however, been limited by their strong bounding assumptions which do not hold for basic models, such as simple linear regressors. To ameliorate this, we propose $\beta$D-Bayes, a posterior sampling scheme from a generalised posterior targeting the minimisation of the $\beta$-divergence between the model and the data generating process.
1391, FC-CLIP: Open-Vocabulary Panoptic Segmentation with A Single Frozen Convolutional CLIP
Qihang Yu; Ju He; Xueqing Deng; Xiaohui Shen; Liang-Chieh Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By contrast, we propose to build everything into a single-stage framework using a shared Frozen Convolutional CLIP backbone, which not only significantly simplifies the current two-stage pipeline, but also remarkably yields a better accuracy-cost trade-off.
1392, Energy-Efficient Scheduling with Predictions
Eric Balkanski; Noemie Perivier; Clifford Stein; Hao-Ting Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider a general setting for energy-efficient scheduling and provide a flexible learning-augmented algorithmic framework that takes as input an offline and an online algorithm for the desired energy-efficient scheduling problem.
1393, ClimSim: An Open Large-scale Dataset for Training High-resolution Physics Emulators in Hybrid Multi-scale Climate Models
Sungduk Yu; Walter Hannah; Liran Peng; Jerry Lin; Mohamed Aziz Bhouri; Ritwik Gupta; Björn Lütjens; Justus C. Will; Gunnar Behrens; Nora Loose; Charles Stern; Tom Beucler; Bryce Harrop; Benjamin Hillman; Andrea Jenney; Savannah L. Ferretti; Nana Liu; Animashree Anandkumar; Noah Brenowitz; Veronika Eyring; Nicholas Geneva; Pierre Gentine; Stephan Mandt; Jaideep Pathak; Akshay Subramaniam; Carl Vondrick; Rose Yu; Laure Zanna; Ryan Abernathey; Fiaz Ahmed; David Bader; Pierre Baldi; Elizabeth Barnes; Christopher Bretherton; Julius Busecke; Peter Caldwell; Wayne Chuang; Yilun Han; YU HUANG; Fernando Iglesias-Suarez; Sanket Jantre; Karthik Kashinath; Marat Khairoutdinov; Thorsten Kurth; Nicholas Lutsko; Po-Lun Ma; Griffin Mooers; J. David Neelin; David Randall; Sara Shamekh; Mark Taylor; Nathan Urban; Janni Yuval; Guang Zhang; Tian Zheng; Mike Pritchard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present \dataset{}, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, developed by a consortium of climate scientists and ML researchers.
1394, Objaverse-XL: A Colossal Universe of 3D Objects
Matt Deitke; Ruoshi Liu; Matthew Wallingford; Huong Ngo; Oscar Michel; Aditya Kusupati; Alan Fan; Christian Laforte; Vikram Voleti; Samir Yitzhak Gadre; Eli VanderBilt; Aniruddha Kembhavi; Carl Vondrick; Georgia Gkioxari; Kiana Ehsani; Ludwig Schmidt; Ali Farhadi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present Objaverse-XL, a dataset of over 10 million 3D objects.
1395, YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus
Dave Uthus; Garrett Tanzer; Manfred Georg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present YouTube-ASL, a large-scale, open-domain corpus of American Sign Language (ASL) videos and accompanying English captions drawn from YouTube.
1396, CHAMMI: A Benchmark for Channel-adaptive Models in Microscopy Imaging
Zitong Sam Chen; Chau Pham; Michael Doron; Siqi Wang; Nikita Moshkov; Bryan Plummer; Juan C. Caicedo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a benchmark for investigating channel-adaptive models in microscopy imaging, which consists of 1) a dataset of varied-channel single-cell images, and 2) a biologically relevant evaluation framework.
1397, Saliency Revisited Using RGBD Videos: A Unified Dataset and Benchmark
Jingjing Li; Wei Ji; Size Wang; Wenbo Li; Li cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the unison of two types of crucial information remains largely underexplored due to data constraints. To address this gap, we in this work introduce the DViSal dataset, fueling further research in the emerging field of RGB-D video salient object detection (DVSOD).
1398, ImageNet-Hard: The Hardest Images Remaining from A Study of The Power of Zoom and Spatial Biases in Image Classification
Mohammad Reza Taesiri; Giang Nguyen; Sarra Habchi; Cor-Paul Bezemer; Anh Nguyen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce ImageNet-Hard, a new benchmark that challenges SOTA classifiers including large vision-language models even when optimal zooming is allowed.
1399, EPIC Fields: Marrying 3D Geometry and Video Understanding
Vadim Tschernezki; Ahmad Darkhalil; Zhifan Zhu; David Fouhey; Iro Laina; Diane Larlus; Dima Damen; Andrea Vedaldi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Progress, however, is still hampered by a lack of suitable datasets and benchmarks. To address this gap, we introduce EPIC Fields, an augmentation of EPIC-KITCHENS with 3D camera information.
1400, Structure Preserving Reversible and Irreversible Bracket Dynamics for Deep Graph Neural Networks
Anthony Gruber; Kookjin Lee; Nathaniel Trask;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work presents a series of novel GNN architectures based upon structure-preserving bracket-based dynamical systems, which are provably guaranteed to either conserve energy or generate positive dissipation with increasing depth.
1401, ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence
Ben Dai; Yixuan Qiu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel algorithm, called ReHLine, for minimizing a set of regularized ERMs with convex piecewise linear-quadratic loss functions and optional linear constraints.
1402, Solving Inverse Physics Problems with Score Matching
Benjamin Holzschuh; Simona Vegetti; Nils Thuerey;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose to solve inverse problems involving the temporal evolution of physics systems by leveraging recent advances from diffusion models.
1403, General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence
Lingwei Zhu; Zheng Chen; Matthew Schlegel; Martha White;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Many policy optimization approaches in reinforcement learning incorporate a Kullback-Leilbler (KL) divergence to the previous policy, to prevent the policy from changing too quickly. This idea was initially proposed in a seminal paper on Conservative Policy Iteration, with approximations given by algorithms like TRPO and Munchausen Value Iteration (MVI). We continue this line of work by investigating a generalized KL divergence---called the Tsallis KL divergence.
1404, Explaining V1 Properties with A Biologically Constrained Deep Learning Architecture
Galen Pogoncheff; Jacob Granley; Michael Beyeler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While current state-of-the-art models of the primary visual cortex (V1) have surfaced from training with adversarial examples and extensively augmented data, these models are still unable to explain key neural properties observed in V1 that arise from biological circuitry. To address this gap, we systematically incorporated neuroscience-derived architectural components into CNNs to identify a set of mechanisms and architectures that comprehensively explain neural activity in V1.
1405, Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data
Praveen Venkatesh; Corbett Bennett; Sam Gale; Tamina Ramirez; Greggory Heller; Severine Durand; Shawn Olsen; Stefan Mihalas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new efficient method for computing and estimating a PID definition on multivariate Gaussian distributions.
1406, No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions
William Chang; Tiancheng Jin; Junyan Liu; Haipeng Luo; Chloé Rouyer; Chen-Yu Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is because it has been shown that adversarial transition functions make no-regret learning impossible. Despite such impossibility results, in this work, we develop algorithms that can handle both adversarial losses and adversarial transitions, with regret increasing smoothly in the degree of maliciousness of the adversary.
1407, BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learning
Sheikh Md Shakeel Hassan; Arthur Feeney; Akash Dhruv; Jihoon Kim; Youngjoon Suh; Jaiyoung Ryu; Yoonjin Won; Aparna Chandramowlishwaran;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing experimental datasets are often restricted, with limited availability and sparse ground truth data, impeding our understanding of this complex multi-physics phenomena. To bridge this gap, we present the BubbleML Dataset which leverages physics-driven simulations to provide accurate ground truth information for various boiling scenarios, encompassing nucleate pool boiling, flow boiling, and sub-cooled boiling.
1408, Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval
Xiaoshuai Hao; Wanqian Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we address the challenge task of Unsupervised Domain Adaptation Video-text Retrieval (UDAVR), assuming that training (source) data and testing (target) data are from different domains.
1409, Agnostically Learning Single-Index Models Using Omnipredictors
Aravind Gollakota; Parikshit Gopalan; Adam Klivans; Konstantinos Stavropoulos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We give the first result for agnostically learning Single-Index Models (SIMs) with arbitrary monotone and Lipschitz activations.
1410, Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training
Yefan Zhou; TIANYU PANG; Keqin Liu; charles martin; Michael Mahoney; Yaoqing Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a middle-ground approach for temperature balancing called TempBalance.
1411, Most Neural Networks Are Almost Learnable
Amit Daniely; Nati Srebro; Gal Vardi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a PTAS for learning random constant-depth networks.
1412, Undirected Probabilistic Model for Tensor Decomposition
Zerui Tao; Toshihisa Tanaka; Qibin Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, since such prior knowledge is typically unavailable in real-world applications, picking an appropriate TD model can be challenging. This paper aims to address this issue by introducing a flexible TD framework that discards the structural and distributional assumptions, in order to learn as much information from the data.
1413, Double Auctions with Two-sided Bandit Feedback
Soumya Basu; Abishek Sankararaman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We initiate the study of Double Auction markets under bandit feedback on both buyers' and sellers' side.
1414, Estimating Propensity for Causality-based Recommendation Without Exposure Data
Zhongzhou Liu; Yuan Fang; Min Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we bridge the gap by proposing a new framework, called Propensity Estimation for Causality-based Recommendation (PropCare).
1415, Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
Cristina Menghini; Andrew Delworth; Stephen Bach;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We study the use of pseudolabels, i.e., heuristic labels for unlabeled data, to enhance CLIP via prompt tuning.
1416, Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Approach for Object Detection
Taehyeon Kim; Eric Lin; Junu Lee; Christian Lau; Vaikkunth Mugunthan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data.
1417, Would I Have Gotten That Reward? Long-term Credit Assignment By Counterfactual Contribution Analysis
Alexander Meulemans; Simon Schug; Seijin Kobayashi; nathaniel daw; Gregory Wayne;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Building upon Hindsight Credit Assignment (HCA), we introduce Counterfactual Contribution Analysis (COCOA), a new family of model-based credit assignment algorithms.
1418, Robust Bayesian Satisficing
Artun Saday; Y. Cahit Yıldırım; Cem Tekin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel robust Bayesian satisficing algorithm (RBS) for noisy black-box optimization.
1419, On The Importance of Exploration for Generalization in Reinforcement Learning
Yiding Jiang; J. Zico Kolter; Roberta Raileanu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Through a series of experiments in a tabular contextual MDP, we show that exploration is helpful not only for efficiently finding the optimal policy for the training environments but also for acquiring knowledge that helps decision making in unseen environments. Based on these observations, we propose EDE: Exploration via Distributional Ensemble, a method that encourages exploration of states with high epistemic uncertainty through an ensemble of Q-value distributions.
1420, Exponential Lower Bounds for Fictitious Play in Potential Games
Ioannis Panageas; Nikolas Patris; Stratis Skoulakis; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we focus on the rate of convergence of FP when applied to potential games and more specifically identical payoff games.
1421, GraphPatcher: Mitigating Degree Bias for Graph Neural Networks Via Test-time Node Patching
Mingxuan Ju; Tong Zhao; Wenhao Yu; Neil Shah; Yanfang Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Though effective, these approaches unintentionally create an artificial out-of-distribution scenario, where models mainly or even only observe low-degree nodes during the training, leading to a downgraded performance for high-degree nodes that GNNs originally perform well at. In light of this, we propose a test-time augmentation framework, namely GraphPatcher, to enhance test-time generalization of any GNNs on low-degree nodes.
1422, Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning
Van Cuong Pham; Cuong C Nguyen; Trung Le; Dinh Phung; Gustavo Carneiro; Thanh-Toan Do;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel approach to improve BNNs performance through deep mutual learning.
1423, What Can We Learn from Unlearnable Datasets?
Pedro Sandoval-Segura; Vasu Singla; Jonas Geiping; Micah Goldblum; Tom Goldstein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To emphasize why linearly separable perturbations should not be relied upon, we propose an orthogonal projection attack which allows learning from unlearnable datasets published in ICML 2021 and ICLR 2023.
1424, Multi-Swap K-Means++
Lorenzo Beretta; Vincent Cohen-Addad; Silvio Lattanzi; Nikos Parotsidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To obtain higher quality solutions, Lattanzi and Sohler (ICML 2019) proposed augmenting $k$-means++ with $O(k \log \log k)$ local-search steps obtained through the $k$-means++ sampling distribution to yield a $c$-approximation to the $k$-means clustering problem, where $c$ is a large absolute constant.
1425, Sharp Bounds for Generalized Causal Sensitivity Analysis
Dennis Frauen; Valentyn Melnychuk; Stefan Feuerriegel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a unified framework for causal sensitivity analysis under unobserved confounding in various settings.
1426, Provably Efficient Algorithm for Nonstationary Low-Rank MDPs
Yuan Cheng; Jing Yang; Yingbin Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we make the first effort to investigate nonstationary RL under episodic low-rank MDPs, where both transition kernels and rewards may vary over time, and the low-rank model contains unknown representation in addition to the linear state embedding function.
1427, Stable Diffusion Is Unstable
Chengbin Du; Yanxi Li; Zhongwei Qiu; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, the introduction of small perturbations to the text prompts can result in the blending of primary subjects with other categories or their complete disappearance in the generated images. In this paper, we propose **Auto-attack on Text-to-image Models (ATM)**, a gradient-based approach, to effectively and efficiently generate such perturbations.
1428, Unified Enhancement of Privacy Bounds for Mixture Mechanisms Via $f$-Differential Privacy
Chendi Wang; Buxin Su; Jiayuan Ye; Reza Shokri; Weijie Su;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper focuses on improving privacy bounds for shuffling models and differentially private gradient descent (DP-GD) with random initializations using $f$-DP.
1429, Explore In-Context Learning for 3D Point Cloud Understanding
zhongbin fang; Xiangtai Li; Xia Li; Joachim M Buhmann; Chen Change Loy; Mengyuan Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Moreover, position embedding in the previous works may inadvertently introduce information leakage. To address these challenges, we introduce a novel framework, named Point-In-Context, designed explicitly for in-context learning in 3D point cloud, where both inputs and outputs are modeled as coordinates for each task.
1430, Physics-Informed Bayesian Optimization of Variational Quantum Circuits
Kim Nicoli; Christopher J. Anders; Lena Funcke; Tobias Hartung; Karl Jansen; Stefan Kühn; Klaus-Robert Müller; Paolo Stornati; Pan Kessel; Shinichi Nakajima;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel and powerful method to harness Bayesian optimization for variational quantum eigensolvers (VQEs)---a hybrid quantum-classical protocol used to approximate the ground state of a quantum Hamiltonian.
1431, Arbitrarily Scalable Environment Generators Via Neural Cellular Automata
Yulun Zhang; Matthew Fontaine; Varun Bhatt; Stefanos Nikolaidis; Jiaoyang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, instead of optimizing environments, we propose to optimize Neural Cellular Automata (NCA) environment generators via QD algorithms.
1432, Is Learning in Games Good for The Learners?
William Brown; Jon Schneider; Kiran Vodrahalli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a number of questions related to tradeoffs between reward and regret in repeated gameplay between two agents. To facilitate this, we introduce a notion of {\it generalized equilibrium} which allows for asymmetric regret constraints, and yields polytopes of feasible values for each agent and pair of regret constraints, where we show that any such equilibrium is reachable by a pair of algorithms which maintain their regret guarantees against arbitrary opponents.
1433, Fine-Grained Visual Prompting
Lingfeng Yang; Yueze Wang; Xiang Li; Jian Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we carefully study the visual prompting designs by exploring more fine-grained markings, such as segmentation masks and their variations.
1434, ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion
WEI XING; Yuxin Wang; Zheng Xing;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we first generalize the popular autoregression (AR) to derive a novel linear fidelity differential equation (LiFiDE), paving the way to tractable infinitefidelity fusion.
1435, RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing
Antoine Scardigli; Lukas Cavigelli; Lorenz K. Müller;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Monte-Carlo path tracing is a powerful technique for realistic image synthesis but suffers from high levels of noise at low sample counts, limiting its use in real-time applications. To address this, we propose a framework with end-to-end training of a sampling importance network, a latent space encoder network, and a denoiser network.
1436, Analyzing The Sample Complexity of Self-Supervised Image Reconstruction Methods
Tobit Klug; Dogukan Atik; Reinhard Heckel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: A variety of self-supervised methods enable training based on noisy measurements only, without clean images. In this work, we investigate the cost of self-supervised training by characterizing its sample complexity.
1437, Quasi-Monte Carlo Graph Random Features
Isaac Reid; Adrian Weller; Krzysztof M Choromanski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel mechanism to improve the accuracy of the recently-introduced class of graph random features (GRFs).
1438, A Theoretical Analysis of The Test Error of Finite-Rank Kernel Ridge Regression
Tin Sum Cheng; Aurelien Lucchi; Anastasis Kratsios; Ivan Dokmanić; David Belius;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, finite-rank kernels naturally appear in a number of machine learning problems, e.g. when fine-tuning a pre-trained deep neural network's last layer to adapt it to a novel task when performing transfer learning. We address this gap for finite-rank kernel ridge regression (KRR) by deriving sharp non-asymptotic upper and lower bounds for the KRR test error of any finite-rank KRR.
1439, Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation
Minghui Hu; Jianbin Zheng; Daqing Liu; Chuanxia Zheng; Chaoyue Wang; Dacheng Tao; Tat-Jen Cham;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Cocktail, a pipeline to mix various modalities into one embedding, amalgamated with a generalized ControlNet (gControlNet), a controllable normalisation (ControlNorm), and a spatial guidance sampling method, to actualize multi-modal and spatially-refined control for text-conditional diffusion models.
1440, Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models
Waïss Azizian; Franck Iutzeler; Jérôme Malick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing guarantees either suffer from the curse of dimensionality, are restricted to specific settings, or lead to spurious error terms. In this paper, we show that these generalization guarantees actually hold on general classes of models, do not suffer from the curse of dimensionality, and can even cover distribution shifts at testing.
1441, CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection
Yingjie Wang; Jiajun Deng; Yuenan Hou; Yao Li; Yu Zhang; Jianmin Ji; Wanli Ouyang; Yanyong Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: On the other hand, cluster-based detectors exploit the voting mechanism and aggregate the foreground points into object-centric clusters for further prediction. In this paper, we explore how to effectively combine these two complementary representations into a unified framework.
1442, Reducing Blackwell and Average Optimality to Discounted MDPs Via The Blackwell Discount Factor
Julien Grand-Clément; Marek Petrik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the Blackwell discount factor for Markov Decision Processes (MDPs).
1443, Guiding Language Models of Code with Global Context Using Monitors
Lakshya A Agrawal; Aditya Kanade; Navin Goyal; Shuvendu Lahiri; Sriram Rajamani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a notion of monitors that use static analysis in the background to guide the decoding.
1444, Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View
Zhiyu Lin; Yifei Gao; Yunfan Yang; Jitao Sang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, the cause of the model’s under-fitting behavior is attributed to the limited information content in HFC. Based on these findings, we propose a Balance Spectrum Sampling (BaSS) strategy, which effectively counteract the long-tailed effect and enhance the model’s learning on HFC.
1445, Two Sides of One Coin: The Limits of Untuned SGD and The Power of Adaptive Methods
Junchi YANG; Xiang Li; Ilyas Fatkhullin; Niao He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we prove that SGD with arbitrary $\eta > 0$, referred to as untuned SGD, still attains an order-optimal convergence rate $\widetilde{\mathcal{O}}(T^{-1/4})$ in terms of gradient norm for minimizing smooth objectives.
1446, Truncated Affinity Maximization for Graph Anomaly Detection
Hezhe Qiao; Guansong Pang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this anomaly-discriminative property is ignored by existing GAD methods that are typically built using a conventional anomaly detection objective, such as data reconstruction. In this work, we explore this property to introduce a novel unsupervised anomaly scoring measure for GAD – local node affinity – that assigns a larger anomaly score to nodes that are less affiliated with their neighbors, with the affinity defined as similarity on node attributes/representations.
1447, Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
Nika Haghtalab; Chara Podimata; Kunhe Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a generalization of the standard Stackelberg Games (SGs) framework: _Calibrated Stackelberg Games_.
1448, Combating Representation Learning Disparity with Geometric Harmonization
Zhihan Zhou; Jiangchao Yao; Feng Hong; Yanfeng Wang; Bo Han; Ya Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The attribution is that the vanilla SSL methods that pursue the sample-level uniformity easily leads to representation learning disparity, where head classes with the huge sample number dominate the feature regime but tail classes with the small sample number passively collapse. To address this problem, we propose a novel Geometric Harmonization (GH) method to encourage the category-level uniformity in representation learning, which is more benign to the minority and almost does not hurt the majority under long-tailed distribution.
1449, Power Laws for Hyperparameter Optimization
Arlind Kadra; Maciej Janowski; Martin Wistuba; Josif Grabocka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Deep Power Laws (DPL), an ensemble of neural network models conditioned to yield predictions that follow a power-law scaling pattern.
1450, Calibrating ``Cheap Signals'' in Peer Review Without A Prior
Yuxuan Lu; Yuqing Kong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unlike previous works relying on prior knowledge or historical data, we propose a one-shot noise calibration process without any prior information.
1451, Revisiting Adversarial Robustness Distillation from The Perspective of Robust Fairness
Xinli Yue; Mou Ningping; Qian Wang; Lingchen Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We further validate this issue through fine-grained experiments with various model capacities and find that it may arise due to the gap of capacity between teacher and student models, as well as the existing methods treating each class equally during distillation. Based on these observations, we propose $\textbf{Fair}$ $\textbf{A}$dversarial $\textbf{R}$obustness $\textbf{D}$istillation (Fair-ARD), a novel framework for enhancing the robust fairness of student models by increasing the weights of difficult classes, and design a geometric perspective-based method to quantify the difficulty of different classes for determining the weights.
1452, Privacy Amplification Via Compression: Achieving The Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation
Wei-Ning Chen; Dan Song; Ayfer Ozgur; Peter Kairouz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose two different ways to leverage compression for privacy amplification and achieve the optimal privacy-communication-accuracy trade-offs.
1453, Learning with Explanation Constraints
Rattana Pukdee; Dylan Sam; J. Zico Kolter; Maria-Florina Balcan; Pradeep Ravikumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While supervised learning assumes the presence of labeled data, we may have prior information about how models should behave. In this paper, we formalize this notion as learning from explanation constraints and provide a learning theoretic framework to analyze how such explanations can improve the learning of our models.
1454, Sample Based Explanations Via Generalized Representers
Che-Ping Tsai; Chih-Kuan Yeh; Pradeep Ravikumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A key contribution of the paper is to show that generalized representers are the only class of sample based explanations satisfying a natural set of axiomatic properties.
1455, Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion
Kunxun Qi; Jianfeng Du; Hai Wan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a two-stage framework that imposes both structural and textual knowledge to learn rule-based systems.
1456, Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
Jian Chen; Ruiyi Zhang; Tong Yu; Rohan Sharma; Zhiqiang Xu; Tong Sun; Changyou Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we reformulate the label-noise problem from a generative-model perspective, *i.e.*, labels are generated by gradually refining an initial random guess.
1457, Demystifying The Optimal Performance of Multi-Class Classification
Minoh Jeong; Martina Cardone; Alex Dytso;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by this work, we here propose an estimator for the Bayes error rate of supervised multi-class classification problems.
1458, Formalizing Locality for Normative Synaptic Plasticity Models
Colin Bredenberg; Ezekiel Williams; Cristina Savin; Blake Richards; Guillaume Lajoie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we define different classes of locality, each of which makes clear what quantities cannot be included in a learning rule if an algorithm is to qualify as local with respect to a given (biological) constraint.
1459, Inferring The Future By Imagining The Past
Kartik Chandra; Tony Chen; Tzu-Mao Li; Jonathan Ragan-Kelley; Josh Tenenbaum;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It also suggests some degree of cognitive plausibility, and indeed we present human subject studies showing that our algorithm matches human intuitions in a variety of domains that previous methods could not scale to.
1460, Large Language Models of Code Fail at Completing Code with Potential Bugs
Tuan Dinh; Jinman Zhao; Samson Tan; Renato Negrinho; Leonard Lausen; Sheng Zha; George Karypis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most existing works ignore the possible presence of bugs in the code context for generation, which are inevitable in software development. Therefore, we introduce and study the buggy-code completion problem, inspired by the realistic scenario of real-time code suggestion where the code context contains potential bugs – anti-patterns that can become bugs in the completed program.
1461, Neural (Tangent Kernel) Collapse
Mariia Seleznova; Dana Weitzner; Raja Giryes; Gitta Kutyniok; Hung-Hsu Chou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergence of symmetry and structure in the last-layer features of well-trained classification DNNs.
1462, Large Language Models Are Zero Shot Time Series Forecasters
Marc Finzi; Nate Gruver; Shikai Qiu; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By encoding time series as a string of numerical digits, we can view time series forecasting as next-token prediction in text. Surprisingly, when encoded this way we find that large language models (LLMs) like GPT-3 can zero shot extrapolate time series at a level comparable or exceeding the performance of purpose-built time series models.
1463, Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations
Anudhyan Boral; Zhong Yi Wan; Leonardo Zepeda-Nunez; James Lottes; Qing Wang; Yi-Fan Chen; John Anderson; Fei Sha;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a data-driven learning framework that assimilates two powerful ideas: ideal large eddy simulation (LES) from turbulence closure modeling and neural stochastic differential equations (SDE) for stochastic modeling.
1464, Meek Separators and Their Applications in Targeted Causal Discovery
Kirankumar Shiragur; Jiaqi Zhang; Caroline Uhler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, we propose two randomized algorithms that achieve logarithmic approximation for subset search and causal matching, respectively.
1465, Efficient Adversarial Contrastive Learning Via Robustness-Aware Coreset Selection
Xilie Xu; Jingfeng ZHANG; Feng Liu; Masashi Sugiyama; Mohan Kankanhalli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To speed up ACL, this paper proposes a robustness-aware coreset selection (RCS) method.
1466, A Fractional Graph Laplacian Approach to Oversmoothing
Sohir Maskey; Raffaele Paolino; Aras Bacho; Gitta Kutyniok;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we generalize the concept of oversmoothing from undirected to directed graphs.
1467, Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
Saurabh Garg; Amrith Setlur; Zachary Lipton; Sivaraman Balakrishnan; Virginia Smith; Aditi Raghunathan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, despite the popularity and compatibility of these techniques, their efficacy in combination remains surprisingly unexplored. In this paper, we first undertake a systematic empirical investigation of this combination, finding (i) that in domain adaptation settings, self-training and contrastive learning offer significant complementary gains; and (ii) that in semi-supervised learning settings, surprisingly, the benefits are not synergistic.
1468, Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
Daesung Kim; Hye Won Chung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the rank-1 symmetric matrix completion and prove that GD converges to the ground truth when small random initialization is used.
1469, Unpaired Multi-Domain Causal Representation Learning
Nils Sturma; Chandler Squires; Mathias Drton; Caroline Uhler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we give sufficient conditions for identifiability of the joint distribution and the shared causal graph in a linear setup.
1470, Estimating and Controlling for Equalized-Odds Via Sensitive Attribute Predictors
Beepul Bharti; Paul Yi; Jeremias Sulam;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we study the well known \emph{equalized odds} (EOD) definition of fairness.
1471, (Amplified) Banded Matrix Factorization: A Unified Approach to Private Training
Christopher A. Choquette-Choo; Arun Ganesh; Ryan McKenna; H. Brendan McMahan; John Rush; Abhradeep Guha Thakurta; Zheng Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show how MF can subsume prior state-of-the-art algorithms in both federated and centralized training settings, across all privacy budgets.
1472, Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems
Benjamin Coleman; Wang-Cheng Kang; Matthew Fahrbach; Ruoxi Wang; Lichan Hong; Ed Chi; Derek Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work introduces a simple yet highly effective framework, Feature Multiplexing, where one single representation space is used for many different categorical features.
1473, Swarm Reinforcement Learning for Adaptive Mesh Refinement
Niklas Freymuth; Philipp Dahlinger; Tobias Würth; Simon Reisch; Luise Kärger; Gerhard Neumann;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We formulate AMR as a novel Adaptive Swarm Markov Decision Process in which a mesh is modeled as a system of simple collaborating agents that may split into multiple new agents.
1474, A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games
Zaiwei Chen; Kaiqing Zhang; Eric Mazumdar; Asuman Ozdaglar; Adam Wierman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study a natural variant of best-response learning dynamics in two-player zero-sum stochastic games.
1475, PriorBand: Practical Hyperparameter Optimization in The Age of Deep Learning
Neeratyoy Mallik; Carl Hvarfner; Edward Bergman; Danny Stoll; Maciej Janowski; Marius Lindauer; Luigi Nardi; Frank Hutter;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Consequently, manual experimentation is still the most prevalent approach to optimize hyperparameters, relying on the researcher's intuition, domain knowledge, and cheap preliminary explorations. To resolve this misalignment between HPO algorithms and DL researchers, we propose PriorBand, an HPO algorithm tailored to DL, able to utilize both expert beliefs and cheap proxy tasks.
1476, Enhancing Adversarial Contrastive Learning Via Adversarial Invariant Regularization
Xilie Xu; Jingfeng ZHANG; Feng Liu; Masashi Sugiyama; Mohan Kankanhalli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we leverage the technique of causal reasoning to interpret the ACL and propose adversarial invariant regularization (AIR) to enforce independence from style factors.
1477, Lower Bounds on Adaptive Sensing for Matrix Recovery
Praneeth Kacham; David Woodruff;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study lower bounds on adaptive sensing algorithms for recovering low rank matrices using linear measurements.
1478, Twisting Towards Perfection: Asymptotically Exact Conditional Sampling in Diffusion Models
Luhuan Wu; Brian Trippe; Christian Naesseth; John Cunningham; David Blei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we introduce the Twisted Diffusion Sampler, or TDS, a sequential Monte Carlo (SMC) algorithm that targets the conditional distributions of diffusion models.
1479, Optimal Approximation Using Complex-valued Neural Networks
Paul Geuchen; Felix Voigtlaender;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We thus analyze the expressivity of CVNNs by studying their approximation properties.
1480, PCF-GAN: Generating Sequential Data Via The Characteristic Function of Measures on The Path Space
Hang Lou; Siran Li; Hao Ni;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Towards this goal, a key step is the development of an effective discriminator to distinguish between time series distributions. We propose the so-called PCF-GAN, a novel GAN that incorporates the path characteristic function (PCF) as the principled representation of time series distribution into the discriminator to enhance its generative performance.
1481, Exploiting Connections Between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
Aaron Havens; Alexandre Araujo; Siddharth Garg; Farshad Khorrami; Bin Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we advance the understanding of certified robustness of DEQs via exploiting the connections between various Lipschitz network parameterizations for both explicit and implicit models.
1482, Individualized Dosing Dynamics Via Neural Eigen Decomposition
Stav Belogolovsky; Ido Greenberg; Danny Eytan; Shie Mannor;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, medical dosing models must generalize reliably over individual patients and changing treatment policies. To address these challenges, we introduce the Neural Eigen Stochastic Differential Equation algorithm (NESDE).
1483, Optimization or Architecture: What Matters in Non-Linear Filtering?
Ido Greenberg; Netanel Yannay; Shie Mannor;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We suggest the Optimized KF (OKF), which adjusts numeric optimization to the positive-definite KF parameters.
1484, Train Hard, Fight Easy: Robust Meta Reinforcement Learning
Ido Greenberg; Shie Mannor; Gal Chechik; Eli Meirom;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we define a robust MRL objective with a controlled robustness level.
1485, Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation
Hongcheng Wang; Andy Guan Hong Chen; Xiaoqi Li; Mingdong Wu; Hao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Hence, we propose Demand-driven Navigation (DDN), which leverages the user's demand as the task instruction and prompts the agent to find the object matches the specified demand.
1486, Statistical Insights Into HSIC in High Dimensions
Tao Zhang; Yaowu Zhang; Tingyou Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most existing works have focused on either fixed or very high-dimensional covariates. In this work, we bridge the gap between these two scenarios and provide statistical insights into the performance of HSIC when the dimensions grow at different rates.
1487, Generalized Equivalences Between Subsampling and Ridge Regularization
Pratik Patil; Jin-Hong Du;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We establish precise structural and risk equivalences between subsampling and ridge regularization for ensemble ridge estimators.
1488, Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks Without Weight Symmetry
Bariscan Bozkurt; Cengiz Pehlevan; Alper Erdogan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we propose correlative information maximization between layer activations as an alternative normative approach to describe the signal propagation in biological neural networks in both forward and backward directions.
1489, Nonlinear Meta-Learning Can Guarantee Faster Rates
Dimitri Meunier; Zhu Li; Arthur Gretton; Samory Kpotufe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the present work, we derive theoretical guarantees for meta-learning with nonlinear representations.
1490, ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets
Damien Teney; Yong Lin; Seong Joon Oh; Ehsan Abbasnejad;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper shows with multiple datasets that inverse correlations between ID and OOD performance do happen in real-world data ---not only in theoretical worst-case settings.
1491, Thin and Deep Gaussian Processes
Daniel Augusto de Souza; Alexander Nikitin; ST John; Magnus Ross; Mauricio A Álvarez; Marc Deisenroth; João Paulo Gomes; Diego Mesquita; César Lincoln Mattos;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work proposes a novel construction synthesizing of both approaches (Thin and Deep GPs, TDGP).
1492, Toolbox for Multimodal Learn (scikit-multimodallearn)
Dominique Benielli; Baptiste Bauvin; Sokol Koço; Riikka Huusari; Cécile Capponi; Hachem Kadri; François Laviolette;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper details the content of the library, including a specific multimodal data formatting and classification and regression algorithms.
1493, Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Julien Siems; Konstantin Ditschuneit; Winfried Ripken; Alma Lindborg; Maximilian Schambach; Johannes Otterbach; Martin Genzel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we demonstrate how concurvity can severly impair the interpretability of GAMs and propose a remedy: a conceptually simple, yet effective regularizer which penalizes pairwise correlations of the non-linearly transformed feature variables.
1494, A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning
Florian Felten; Lucas N. Alegre; Ann Nowe; Ana Bazzan; El Ghazali Talbi; Grégoire Danoy; Bruno da Silva;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To facilitate and accelerate research and benchmarking in multi-objective RL problems, we introduce a comprehensive collection of software libraries that includes: (i) MO-Gymnasium, an easy-to-use and flexible API enabling the rapid construction of novel MORL environments.
1495, FLAIR : A Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery
Anatol Garioud; Nicolas Gonthier; Loic Landrieu; Apolline De Wit; Marion Valette; Marc Poupée; Sebastien Giordano; boris Wattrelos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the French Land cover from Aerospace ImageRy (FLAIR), an extensive dataset from the French National Institute of Geographical and Forest Information (IGN) that provides a unique and rich resource for large-scale geospatial analysis.
1496, Generalized Test Utilities for Long-tail Performance in Extreme Multi-label Classification
Erik Schultheis; Marek Wydmuch; Wojciech Kotlowski; Rohit Babbar; Krzysztof Dembczynski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we analyze generalized metrics budgeted at k as an alternative solution.
1497, EvoFed: Leveraging Evolutionary Strategies for Efficient and Privacy-Preserving Federated Learning
Mohammadmahdi Rahimi; Younghyun Park; Humaira Kousar; Hasnain Bhatti; Jaekyun Moon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, its broad adoption is hindered by the high communication costs of transmitting large model parameters. This paper presents EvoFed, a novel approach that integrates Evolutionary Strategies (ES) with FL to address these challenges.
1498, NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks
Seokil Ham; Jungwuk Park; Dong-Jun Han; Jaekyun Moon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This makes multi-exit networks highly vulnerable to simple adversarial attacks. In this paper, we propose NEO-KD, a knowledge-distillation-based adversarial training strategy that tackles this fundamental challenge of multi-exit networks with two key contributions. NEO-KD first resorts to neighbor knowledge distillation to guide the output of the adversarial examples to tend to the ensembled outputs of neighbor exits of clean data.
1499, On The Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds Where Optimism Fails
Yi Feng; Hu Fu; Qun Hu; Ping Li; Ioannis Panageas; bo peng; Xiao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the last-iterate behavior of various algorithms in two types of unconstrained, time-varying, bilinear zero-sum games: periodic and convergent perturbed games.
1500, On The Role of Randomization in Adversarially Robust Classification
Lucas Gnecco Heredia; Muni Sreenivas Pydi; Laurent Meunier; Benjamin Negrevergne; Yann Chevaleyre;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we clarify the role of randomization in building adversarially robust classifiers.
1501, Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows
Alexandre Verine; Benjamin Negrevergne; Muni Sreenivas Pydi; Yann Chevaleyre;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our main contribution is a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows, which explicitly optimizes a user-defined trade-off between precision and recall.
1502, Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
Hamish Flynn; David Reeb; Melih Kandemir; Jan Peters;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present improved algorithms with worst-case regret guarantees for the stochastic linear bandit problem.
1503, [Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
Athanasios Charisoudis; Simon Ekman von Huth; Emil Jansson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this pa-per, we attempt a replication of the MAE under significant computational constraints.
1504, Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
Minsoo Kim; Sihwa Lee; Janghwan Lee; Sukjin Hong; Du-Seong Chang; Wonyong Sung; Jungwook Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current QAT methods for generative models have resulted in a noticeable loss of accuracy. To counteract this issue, we propose a novel knowledge distillation method specifically designed for GLMs.
1505, Temporal Conditioning Spiking Latent Variable Models of The Neural Response to Natural Visual Scenes
Gehua Ma; Runhao Jiang; Rui Yan; Huajin Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work presents the temporal conditioning spiking latent variable models (TeCoS-LVM) to simulate the neural response to natural visual stimuli.
1506, GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry Via Positional Denoising
Hyeonsu Kim; Jeheon Woo; SEONGHWAN KIM; Seokhyun Moon; Jun Hyeong Kim; Woo Youn Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, they often require 3D geometries obtained from high-level quantum mechanical calculations, which are practically infeasible, limiting their applicability to real-world problems. To tackle this, we propose a new training framework, GeoTMI, that employs denoising process to predict properties accurately using easy-to-obtain geometries (corrupted versions of correct geometries, such as those obtained from low-level calculations).
1507, Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression
Robert Allison; Anthony Stephenson; Edward O Pyzer-Knapp;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new perspective by exploring robustness properties and limiting behaviour of GP nearest-neighbour (GPnn) prediction.
1508, Counterfactual Generation with Identifiability Guarantee
Hanqi Yan; Lingjing Kong; Lin Gui; Yuejie Chi; Eric Xing; Yulan He; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we tackle the dependence between the content and the style variables inherent in the counterfactual generation task.
1509, The Tunnel Effect: Building Data Representations in Deep Neural Networks
Wojciech Masarczyk; Mateusz Ostaszewski; Ehsan Imani; Razvan Pascanu; Piotr Miłoś; Tomasz Trzcinski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore the tunnel's behavior through comprehensive empirical studies, highlighting that it emerges early in the training process.
1510, OpenLane-V2: A Topology Reasoning Benchmark for Scene Understanding in Autonomous Driving
Huijie Wang; Tianyu Li; Yang Li; Li Chen; Chonghao Sima; Zhenbo Liu; Bangjun Wang; Peijin Jia; Yuting Wang; Shengyin Jiang; Feng Wen; Hang Xu; Ping Luo; Junchi Yan; Wei Zhang; Hongyang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Observing that human drivers rely on both lanes and traffic signals to operate their vehicles safely, we present OpenLane-V2, the first dataset on topology reasoning for traffic scene structure.
1511, Reproducibility Study of ”Label-Free Explainability for Unsupervised Models”
Julius Wagenbach; Gergely Papp; Niklas Mather; Laurens de Vries;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present our reproducibility study of Label-Free Explainability for Unsupervised Models, a paper that introduces two post‐hoc explanation techniques for neural networks: (1) label‐free feature importance and (2) label‐free example importance.
1512, H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
Yanjie Ze; Yuyao Liu; Ruizhe Shi; Jiaxin Qin; Zhecheng Yuan; Jiashun Wang; Xiaolong Wang; Huazhe Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a human $\textbf{H}$and-$\textbf{In}$formed visual representation learning framework to solve difficult $\textbf{Dex}$terous manipulation tasks ($\textbf{H-InDex}$) with reinforcement learning.
1513, RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization
Zhecheng Yuan; Sizhe Yang; Pu Hua; Can Chang; Kaizhe Hu; Xiaolong Wang; Huazhe Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite the focus on algorithms aimed at resolving visual generalization problems, we argue that the devil is in the existing benchmarks as they are restricted to isolated tasks and generalization categories, undermining a comprehensive evaluation of agents' visual generalization capabilities. To bridge this gap, we introduce RL-ViGen: a novel **R**einforcement **L**earning Benchmark for **Vi**sual **Gen**eralization, which contains diverse tasks and a wide spectrum of generalization types, thereby facilitating the derivation of more reliable conclusions.
1514, MoVie: Visual Model-Based Policy Adaptation for View Generalization
Sizhe Yang; Yanjie Ze; Huazhe Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This inherent difficulty is known as the problem of $\textit{view generalization}$. In this work, we systematically categorize this fundamental problem into four distinct and highly challenging scenarios that closely resemble real-world situations.
1515, Fast Bellman Updates for Wasserstein Distributionally Robust MDPs
Zhuodong Yu; Ling Dai; Shaohang Xu; Siyang Gao; Chin Pang Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a computationally efficient solution framework for solving distributionally robust MDPs with Wasserstein ambiguity sets.
1516, Improving The Knowledge Gradient Algorithm
Le Yang; Siyang Gao; Chin Pang Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It is built on the simple idea of always choosing the measurement that yields the greatest expected one-step improvement in the estimate of the best mean of the arms. In this research, we show that this policy has limitations, causing the algorithm not asymptotically optimal.
1517, M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors
Jonggyu Jang; Sangwoo Oh; Youjin Kim; Dongmin Seo; Youngchol Choi; Hyun Jong Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We have collected and annotated a new dataset called ``Multi-Modal Ship and flOating matter Detection in Aerial Images (M$^{2}$SODAI),'', which includes synchronized image pairs of RGB and HSI data, along with bounding box labels for nearly 6,000 instances per category.
1518, Bullying10K: A Large-Scale DVS Dataset Towards Privacy-Preserving
Yiting Dong; Yang Li; Dongcheng Zhao; Guobin Shen; Yi Zeng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the Bullying10K dataset, encompassing various actions, complex movements, and occlusions from real-life scenarios.
1519, Subclass-Dominant Label Noise: A Counterexample for The Success of Early Stopping
Yingbin Bai; Zhongyi Han; Erkun Yang; Jun Yu; Bo Han; Dadong Wang; Tongliang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we empirically investigate a previously overlooked and widespread type of label noise, subclass-dominant label noise (SDN).
1520, On Learning Necessary and Sufficient Causal Graphs
Hengrui Cai; Yixin Wang; Michael Jordan; Rui Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose learning a class of *necessary and sufficient causal graphs (NSCG)* that exclusively comprises causally relevant variables for an outcome of interest, which we term *causal features*.
1521, Efficient Subgame Refinement for Extensive-form Games
Zhenxing Ge; Zheng Xu; Tianyu Ding; Wenbin Li; Yang Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To overcome this issue, recent subgame solving methods allow for subgame solving on limited knowledge order subgames, increasing their applicability in large games; yet this may still face obstacles due to extensive information set sizes. To address this challenge, we propose a generative subgame solving (GS2) framework, which utilizes a generation function to identify a subset of the earliest-reached nodes, reducing the size of the subgame.
1522, Optimal Treatment Regimes for Proximal Causal Learning
Tao Shen; Yifan Cui;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The recently proposed proximal causal inference framework shows that proxy variables that abound in real life scenarios can be leveraged to identify causal effects and therefore facilitate decision-making. Building upon this line of work, we propose a novel optimal individualized treatment regime based on so-called outcome-inducing and treatment-inducing confounding bridges.
1523, UltraRE: Enhancing RecEraser for Recommendation Unlearning Via Error Decomposition
Yuyuan Li; Chaochao Chen; Yizhao Zhang; Weiming Liu; Lingjuan Lyu; Xiaolin Zheng; Dan Meng; Jun Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As the state-of-the-art framework, i.e., RecEraser, naturally achieves full unlearning completeness, our objective is to enhance it in terms of model utility and unlearning efficiency. In this paper, we rethink RecEraser from an ensemble-based perspective and focus on its three potential losses, i.e., redundancy, relevance, and combination.
1524, A Robust and Opponent-Aware League Training Method for StarCraft II
Ruozi Huang; Xipeng Wu; Hongsheng Yu; Zhong Fan; Haobo Fu; Qiang Fu; Wei Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we improve AlphaStar's league training in two significant aspects.
1525, CQM: Curriculum Reinforcement Learning with A Quantized World Model
Seungjae Lee; Daesol Cho; Jonghae Park; H. Jin Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, they usually rely on manually specified goal spaces. To alleviate this limitation and improve the scalability of the curriculum, we propose a novel curriculum method that automatically defines the semantic goal space which contains vital information for the curriculum process, and suggests curriculum goals over it.
1526, Hypothesis Selection with Memory Constraints
Maryam Aliakbarpour; Mark Bun; Adam Smith;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the hypothesis selection problem under memory constraints.
1527, Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method
Tianyi Liu; Kejun Wu; Yi Wang; Wenyang Liu; Kim-Hui Yap; Lap-Pui Chau;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communication (e.g., telepresence, live streaming, and internet video) and multimedia forensics. To address this, we introduce the bitstream-corrupted video (BSCV) benchmark, the first benchmark dataset with more than 28,000 video clips, which can be used for bitstream-corrupted video recovery in the real world.
1528, Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection
suresh kumar amalapuram; Sumohana Channappayya; Bheemarjuna Reddy Tamma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present two novel contributions to improve the performance of CL-based network intrusion detection in the context of class imbalance and scalability.
1529, TD Convergence: An Optimization Perspective
Kavosh Asadi; Shoham Sabach; Yao Liu; Omer Gottesman; Rasool Fakoor;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the convergence behavior of the celebrated temporal-difference (TD) learning algorithm.
1530, Budgeting Counterfactual for Offline RL
Yao Liu; Pratik Chaudhari; Rasool Fakoor;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Contrary to existing approaches that use regularization on either the policy or value function, we propose an approach to explicitly bound the amount of out-of-distribution actions during training.
1531, DSR: Dynamical Surface Representation As Implicit Neural Networks for Protein
Daiwen Sun; He Huang; Yao Li; Xinqi Gong; Qiwei Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel neural network-based approach to modeling protein dynamics using an implicit representation of a protein's surface in 3D and time.
1532, ReSync: Riemannian Subgradient-based Robust Rotation Synchronization
Huikang Liu; Xiao Li; Anthony Man-Cho So;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work presents ReSync, a Riemannian subgradient-based algorithm for solving the robust rotation synchronization problem, which arises in various engineering applications.
1533, GEX: A Flexible Method for Approximating Influence Via Geometric Ensemble
SungYub Kim; Kyungsu Kim; Eunho Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Accordingly, by improving each point, we introduce a new IF approximation method with the following features: i) the removal of linearization to alleviate the bilinear constraint and ii) the utilization of Geometric Ensemble (GE) tailored for non-linear losses.
1534, Small Batch Deep Reinforcement Learning
Johan Obando Ceron; Marc Bellemare; Pablo Samuel Castro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although critical to the learning process, this value is typically not adjusted when proposing new algorithms. In this work we present a broad empirical study that suggests reducing the batch size can result in a number of significant performance gains; this is surprising, as the general tendency when training neural networks is towards larger batch sizes for improved performance.
1535, Robust Asynchronous Collaborative 3D Detection Via Bird's Eye View Flow
Sizhe Wei; Yuxi Wei; Yue Hu; Yifan Lu; Yiqi Zhong; Siheng Chen; Ya Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To model the motion in a scene, we propose BEV flow, which is a collection of the motion vector corresponding to each spatial location.
1536, Interpretable and Explainable Logical Policies Via Neurally Guided Symbolic Abstraction
Quentin Delfosse; Hikaru Shindo; Devendra Dhami; Kristian Kersting;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To achieve both, we introduce Neurally gUided Differentiable loGic policiEs (NUDGE).
1537, Feature Dropout: Revisiting The Role of Augmentations in Contrastive Learning
Alex Tamkin; Margalit Glasgow; Xiluo He; Noah Goodman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We perform contrastive learning experiments on a range of image and audio datasets with multiple downstream tasks (e.g. for digits superimposed on photographs, predicting the class of one vs. the other).
1538, FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding
Pengxiang Wu; Siman Wang; Kevin Dela Rosa; Derek Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Notably, most existing works only consider domains like 3D landmarks, making it difficult to generalize the conclusions made by these works to other domains, e.g., logo and other 2D flat objects. To bridge this gap, we introduce a new dataset for benchmarking visual search methods on flat images with diverse patterns.
1539, Defending Pre-trained Language Models As Few-shot Learners Against Backdoor Attacks
Tianyu Du; Zhaohan Xi; Changjiang Li; Ren Pang; Shouling Ji; Jinghui Chen; Fenglong Ma; Ting Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we conduct a pilot study showing that PLMs as few-shot learners are highly vulnerable to backdoor attacks while existing defenses are inadequate due to the unique challenges of few-shot scenarios.
1540, LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging Via Second-order Graph Matching
Duy M. H. Nguyen; Hoang Nguyen; Nghiem Diep; Tan Ngoc Pham; Tri Cao; Binh Nguyen; Paul Swoboda; Nhat Ho; Shadi Albarqouni; Pengtao Xie; Mathias Niepert; Daniel Sonntag;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While pre-trained networks on ImageNet and vision-language foundation models trained on web-scale data are the prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images. To bridge this gap, we introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets.
1541, Lookaround Optimizer: $k$ Steps Around, 1 Step Average
Jiangtao Zhang; Shunyu Liu; Jie Song; Tongtian Zhu; Zhengqi Xu; Mingli Song;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, inspired by weight average, we propose Lookaround, a straightforward yet effective SGD-based optimizer leading to flatter minima with better generalization.
1542, Off-Policy Evaluation for Human Feedback
Qitong Gao; Ge Gao; Juncheng Dong; Vahid Tarokh; Min Chi; Miroslav Pajic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consequently, the nature of HF signals makes extrapolating accurate OPE estimations to be challenging. To resolve this, we introduce an OPE for HF (OPEHF) framework that revives existing OPE methods in order to accurately evaluate the HF signals.
1543, Disentangling Cognitive Diagnosis with Limited Exercise Labels
Xiangzhi Chen; Le Wu; Fei Liu; Lei Chen; Kun Zhang; Richang Hong; Meng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Disentanglement based Cognitive Diagnosis (DisenCD) to address the challenges of limited exercise labels.
1544, Context-lumpable Stochastic Bandits
Chung-Wei Lee; Qinghua Liu; Yasin Abbasi Yadkori; Chi Jin; Tor Lattimore; Csaba Szepesvari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a contextual bandit problem with $S $ contexts and $K $ actions.
1545, Optimistic Natural Policy Gradient: A Simple Efficient Policy Optimization Framework for Online RL
Qinghua Liu; Gellért Weisz; András György; Chi Jin; Csaba Szepesvari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a simple efficient policy optimization framework---Optimistic NPG for online RL.
1546, Into The Single Cell Multiverse: An End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts
Ruth Dannenfelser; Jeffrey Zhong; Ran Zhang; Vicky Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Procedural knowledge extraction, i.e., breaking down a described process into a series of steps, has received much less attention, perhaps in part due to the lack of structured datasets that capture the knowledge extraction process from end-to-end. To address this unmet need, we present FlaMBé (Flow annotations for Multiverse Biological entities), a collection of expert-curated datasets across a series of complementary tasks that capture procedural knowledge in biomedical texts.
1547, Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses
Jacob Granley; Tristan Fauvel; Matthew Chalk; Michael Beyeler;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Alternatively, deep learning models can optimize stimulus encoding strategies, but typically assume perfect knowledge of patient-specific variations. Here we propose a novel, practically feasible approach that overcomes both of these fundamental limitations.
1548, Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
Jiayi Huang; Han Zhong; Liwei Wang; Lin Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While numerous works have focused on devising efficient algorithms for reinforcement learning (RL) with uniformly bounded rewards, it remains an open question whether sample or time-efficient algorithms for RL with large state-action space exist when the rewards are \emph{heavy-tailed}, i.e., with only finite $(1+\epsilon)$-th moments for some $\epsilon\in(0,1]$. In this work, we address the challenge of such rewards in RL with linear function approximation.
1549, Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning
Akhil Bagaria; Ben Abbatematteo; Omer Gottesman; Matt Corsaro; Sreehari Rammohan; George Konidaris;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consequently, data obtained from option execution becomes invalid over time, leading to an inaccurate initiation set that subsequently harms downstream task performance. We highlight three issues---data non-stationarity, temporal credit assignment, and pessimism---specific to learning initiation sets, and propose to address them using tools from off-policy value estimation and classification.
1550, Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling
ting li; Jianguo Li; Zhanxing Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We incorporate the local change of input signal into the latent dynamics in an attention-based manner and design a residual architecture over basis expansion to depict the periodicity in the underlying dynamics.
1551, Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
Subhojyoti Mukherjee; Qiaomin Xie; Josiah Hanna; Robert Nowak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the \textit{multi-task bilinear bandit problem}, we aim to find optimal actions for multiple tasks that share a common low-dimensional linear representation.
1552, STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events
Kazuki Shimada; Archontis Politis; Parthasaarathy Sudarsanam; Daniel A. Krause; Kengo Uchida; Sharath Adavanne; Aapo Hakala; Yuichiro Koyama; Naoya Takahashi; Shusuke Takahashi; Tuomas Virtanen; Yuki Mitsufuji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper proposes an audio-visual sound event localization and detection (SELD) task, which uses multichannel audio and video information to estimate the temporal activation and DOA of target sound events.
1553, An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient
Yudong Luo; Guiliang Liu; Pascal Poupart; Yangchen Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent methods restrict the per-step reward variance as a proxy. We thoroughly examine the limitations of these variance-based methods, such as sensitivity to numerical scale and hindering of policy learning, and propose to use an alternative risk measure, Gini deviation, as a substitute.
1554, Dynamic Pricing and Learning with Bayesian Persuasion
Shipra Agrawal; Yiding Feng; Wei Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Without any apriori knowledge of the buyers’ demand function, our goal is to design an online algorithm that can use past purchase responses to adaptively learn the optimal pricing and advertising strategy.
1555, MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks
Allen Nie; Yuhui Zhang; Atharva Shailesh Amdekar; Chris Piech; Tatsunori Hashimoto; Tobias Gerstenberg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work has revealed a number of factors that systematically influence people's judgments, such as the violation of norms and whether the harm is avoidable or inevitable.
1556, Thrust: Adaptively Propels Large Language Models with External Knowledge
Xinran Zhao; Hongming Zhang; Xiaoman Pan; Wenlin Yao; Dong Yu; Jianshu Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary. To achieve this goal, we propose to model whether a PTLM contains enough knowledge to solve an instance with a novel metric, Thrust, which leverages the representation distribution of a small amount of seen instances.
1557, Outlier-Robust Wasserstein DRO
Sloan Nietert; Ziv Goldfeld; Soroosh Shafiee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, WDRO fails to account for non-geometric perturbations such as adversarial outliers, which can greatly distort the Wasserstein distance measurement and impede the learned model. We address this gap by proposing a novel outlier-robust WDRO framework for decision-making under both geometric (Wasserstein) perturbations and non-geometric (total variation (TV)) contamination that allows an $\varepsilon$-fraction of data to be arbitrarily corrupted.
1558, The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data
Peter Nickl; Lu Xu; Dharmesh Tailor; Thomas Möllenhoff; Mohammad Emtiyaz Khan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Understanding model’s sensitivity to its training data is crucial not only for safe and robust operation but also for future adaptations. We present the memory-perturbation equation (MPE) which relates model's sensitivity to perturbation in its memory.
1559, Autonomous Capability Assessment of Black-Box Sequential Decision-Making Systems
Pulkit Verma; Rushang Karia; Siddharth Srivastava;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a new approach for modeling the capabilities of black-box AI systems that can plan and act, along with the possible effects and requirements for executing those capabilities in stochastic settings.
1560, Credal Marginal MAP
Radu Marinescu; Debarun Bhattacharjya; Junkyu Lee; Fabio Cozman; Alexander Gray;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore Credal Marginal MAP inference and develop new exact methods based on variable elimination and depth-first search as well as several approximation schemes based on the mini-bucket partitioning and stochastic local search.
1561, Scientific Document Retrieval Using Multi-level Aspect-based Queries
Jianyou (Andre) Wang; Kaicheng Wang; Xiaoyue Wang; Prudhviraj Naidu; Leon Bergen; Ramamohan Paturi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing evaluation datasets for this task are limited, primarily due to the high costs and effort required to annotate resources that effectively represent complex queries. To address this, we propose a novel task, $\textbf{S}$cientific $\textbf{Do}$cument $\textbf{R}$etrieval using $\textbf{M}$ulti-level $\textbf{A}$spect-based qu$\textbf{E}$ries (DORIS-MAE), which is designed to handle the complex nature of user queries in scientific research.
1562, To Stay or Not to Stay in The Pre-train Basin: Insights on Ensembling in Transfer Learning
Ildus Sadrtdinov; Dmitrii Pozdeev; Dmitry Vetrov; Ekaterina Lobacheva;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study if it is possible to improve ensembles trained from a single pre-trained checkpoint by better exploring the pre-train basin or a close vicinity outside of it.
1563, Distribution Learnability and Robustness
Shai Ben-David; Alex Bie; Gautam Kamath; Tosca Lechner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We examine the relationship between learnability and robust learnability for the problem of distribution learning.
1564, Should We Learn Most Likely Functions or Parameters?
Tim G. J. Rudner; Sanyam Kapoor; Shikai Qiu; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate the implications of directly estimating the most likely function implied by the model and the data.
1565, Closing The Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits
Ruo-Chun Tzeng; Po-An Wang; Alexandre Proutiere; Chi-Jen Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Perturbed Frank-Wolfe Sampling (P-FWS), an algorithm that (i) runs in polynomial time, (ii) achieves the instance-specific minimal sample complexity in the high confidence regime, and (iii) enjoys polynomial sample complexity guarantees in the moderate confidence regime.
1566, Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning
Stefan Stojanovic; Yassir Jedra; Alexandre Proutiere;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study matrix estimation problems arising in reinforcement learning with low-rank structure.
1567, Model-Free Active Exploration in Reinforcement Learning
Alessio Russo; Alexandre Proutiere;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of exploration in Reinforcement Learning and present a novel model-free solution.
1568, Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits
Filippo Vannella; Alexandre Proutiere; Jaeseong Jeong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of regret minimization in Multi-Agent Multi-Armed Bandits (MAMABs) where the rewards are defined through a factor graph.
1569, Best Arm Identification with Fixed Budget: A Large Deviation Perspective
Po-An Wang; Ruo-Chun Tzeng; Alexandre Proutiere;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we establish a connection between the Large Deviation Principle (LDP) satisfied by the empirical proportions of arm draws and that satisfied by the empirical arm rewards.
1570, Anytime Model Selection in Linear Bandits
Parnian Kassraie; Aldo Pacchiano; Nicolas Emmenegger; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our key insight is that, for model selection in linear bandits, we can emulate full-information feedback to the online learner with a favorable bias-variance trade-off.
1571, Likelihood Ratio Confidence Sets for Sequential Decision Making
Nicolas Emmenegger; Mojmir Mutny; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we revisit the likelihood-based inference principle and propose to use \emph{likelihood ratios} to construct \emph{any-time valid} confidence sequences without requiring specialized treatment in each application scenario.
1572, A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning
Alicia Curth; Alan Jeffares; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While most attention has naturally been given to the deep-learning setting, double descent was shown to emerge more generally across non-neural models: known cases include _linear regression, trees, and boosting_. In this work, we take a closer look at the evidence surrounding these more classical statistical machine learning methods and challenge the claim that observed cases of double descent truly extend the limits of a traditional U-shaped complexity-generalisation curve therein.
1573, Meta-Learning with Neural Bandit Scheduler
Yunzhe Qi; Yikun Ban; Tianxin Wei; Jiaru Zou; Huaxiu Yao; Jingrui He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel task scheduling framework under Contextual Bandits settings, named BASS, which directly optimizes the task scheduling strategy based on the status of the meta-model.
1574, Mitigating Catastrophic Forgetting in Federated Class Incremental Learning Using Data-free Generative Models
Sara Babakniya; Zalan Fabian; Chaoyang He; Mahdi Soltanolkotabi; Salman Avestimehr;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, they do not apply directly to FL because of its unique complexities, such as privacy concerns and resource limitations. To overcome these challenges, this paper presents a framework for federated class incremental learning that utilizes a generative model to synthesize samples from past distributions.
1575, Are GATs Out of Balance?
Nimrah Mustafa; Aleksandar Bojchevski; Rebekka Burkholz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We derive a conservation law of GAT gradient flow dynamics, which explains why a high portion of parameters in GATs with standard initialization struggle to change during training.
1576, Contextually Affinitive Neighborhood Refinery for Deep Clustering
Chunlin Yu; Ye Shi; Jingya Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To further mitigate the intrinsic neighborhood noises near cluster boundaries, we propose a progressively relaxed boundary filtering strategy to circumvent the issues brought by noisy neighbors.
1577, Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem
Jincheng Cao; Ruichen Jiang; Nazanin Abolfazli; Erfan Yazdandoost Hamedani; Aryan Mokhtari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study a class of stochastic bilevel optimization problems, also known as stochastic simple bilevel optimization, where we minimize a smooth stochastic objective function over the optimal solution set of another stochastic convex optimization problem.
1578, Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning
Hanlin Zhu; Paria Rashidinejad; Jiantao Jiao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose A-Crab (Actor-Critic Regularized by Average Bellman error), a new algorithm for offline reinforcement learning (RL) in complex environments with insufficient data coverage.
1579, 3D Copy-Paste: Physical Plausible Indoor Object Insertion for Monocular 3D Object Detection
Yunhao Ge; Hong-Xing Yu; Cheng Zhao; Yuliang Guo; Xinyu Huang; Liu Ren; Laurent Itti; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, the potential impact of such a method on downstream perception tasks is unclear. In this paper, we propose a physically plausible indoor 3D object insertion approach to automatically copy virtual objects and paste them into real scenes.
1580, Category-Extensible Out-of-Distribution Detection Via Hierarchical Context Descriptions
Kai Liu; Zhihang Fu; Chao Chen; Sheng Jin; Ze Chen; Mingyuan Tao; Rongxin Jiang; Jieping Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: With the hierarchical contexts being prone to precise category descriptions, we propose a category-extensible OOD method (CATEX), which can efficiently extend the set of recognizable categories by simply merging the hierarchical contexts learned under different sub-task settings.
1581, Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection
Chao Chen; Zhihang Fu; Kai Liu; Ze Chen; Mingyuan Tao; Jieping Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an Optimal Parameter and Neuron Pruning (OPNP) approach, which aims to identify and remove those parameters and neurons that lead to over-fitting.
1582, Kernel Stein Discrepancy Thinning: A Theoretical Perspective of Pathologies and A Practical Fix with Regularization
Clement Benard; Brian Staber; Sébastien Da Veiga;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Nevertheless, Stein thinning suffers from several empirical pathologies, which may result in poor approximations, as observed in the literature. In this article, we conduct a theoretical analysis of these pathologies, to clearly identify the mechanisms at stake, and suggest improved strategies.
1583, Epsilon-fractional Core Stability in Hedonic Games
Simone Fioravanti; Michele Flammini; Bojana Kodric; Giovanna Varricchio;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, core-stable partitions seldom exist and even when they do, it is often computationally intractable to find one. To circumvent these problems, we propose the notion of $\varepsilon$-fractional core-stability, where at most an $\varepsilon$-fraction of all possible coalitions is allowed to core-block.
1584, BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction
Rongqing Li; Changsheng Li; Dongchun Ren; Guangyi Chen; Ye Yuan; Guoren Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a Bi-directional Consistent Diffusion framework tailored for instantaneous trajectory prediction, named BCDiff.
1585, On The Relationship Between Relevance and Conflict in Online Social Link Recommendations
Yanbang Wang; Jon Kleinberg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To date, however, we have very little understanding of how these two implications of link formation relate to each other: are the goals of high relevance and conflict reduction aligned, or are the links that users are most likely to accept fundamentally different from the ones with the greatest potential for reducing conflict? Here we provide the first analysis of this question, using the recently popular Friedkin-Johnsen model of opinion dynamics.
1586, PlanE: Representation Learning Over Planar Graphs
Radoslav Dimitrov; Zeyang Zhao; Ralph Abboud; Ismail Ceylan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The goal of this work is to design architectures for efficiently learning complete invariants of planar graphs.
1587, SSL4EO-L: Datasets and Foundation Models for Landsat Imagery
Adam Stewart; Nils Lehmann; Isaac Corley; Yi Wang; Yi-Chia Chang; Nassim Ait Ait Ali Braham; Shradha Sehgal; Caleb Robinson; Arindam Banerjee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce SSL4EO-L, the first ever dataset designed for Self-Supervised Learning for Earth Observation for the Landsat family of satellites (including 3 sensors and 2 product levels) and the largest Landsat dataset in history (5M image patches).
1588, Closing The Gap Between The Upper Bound and Lower Bound of Adam's Iteration Complexity
Bohan Wang; Jingwen Fu; Huishuai Zhang; Nanning Zheng; Wei Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we close the gap by deriving a new convergence guarantee of Adam, with only an $L$-smooth condition and a bounded noise variance assumption.
1589, ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab
Jieming Cui; Ziren Gong; Baoxiong Jia; Siyuan Huang; Zilong Zheng; Jianzhu Ma; Yixin Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we first curate a comprehensive multimodal dataset, named ProBio, as an initial step towards this objective. This dataset comprises fine-grained hierarchical annotations intended for the purpose of studying activity understanding in BioLab. Next, we devise two challenging benchmarks, transparent solution tracking and multimodal action recognition, to emphasize the unique characteristics and difficulties associated with activity understanding in BioLab settings.
1590, A Unified, Scalable Framework for Neural Population Decoding
Mehdi Azabou; Vinam Arora; Venkataramana Ganesh; Ximeng Mao; Santosh Nachimuthu; Michael Mendelson; Blake Richards; Matthew Perich; Guillaume Lajoie; Eva Dyer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a training framework and architecture designed to model the population dynamics of neural activity across diverse, large-scale neural recordings.
1591, Relax, It Doesn’t Matter How You Get There: A New Self-supervised Approach for Multi-timescale Behavior Analysis
Mehdi Azabou; Michael Mendelson; Nauman Ahad; Maks Sorokin; Shantanu Thakoor; Carolina Urzay; Eva Dyer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we develop a multi-task representation learning model for animal behavior that combines two novel components: (i) an action-prediction objective that aims to predict the distribution of actions over future timesteps, and (ii) a multi-scale architecture that builds separate latent spaces to accommodate short- and long-term dynamics.
1592, Switching Autoregressive Low-rank Tensor Models
Hyun Dong Lee; andrew warrington; Joshua Glaser; Scott Linderman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose _switching autoregressive low-rank tensor_ SALT models, which retain the advantages of both approaches while ameliorating the weaknesses.
1593, Large Language Models Are Fixated By Red Herrings: Exploring Creative Problem Solving and Einstellung Effect Using The Only Connect Wall Dataset
Saeid Alavi Naeini; Raeid Saqur; Mozhgan Saeidi; John Giorgi; Babak Taati;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In addition to presenting the novel Only Connect Wall (OCW) dataset, we also report results from our evaluation of selected pre-trained language models and LLMs (including OpenAI's GPT series) on creative problem solving tasks like grouping clue words by heterogeneous connections, and identifying correct open knowledge domain connections in respective groups.
1594, TransHP: Image Classification with Hierarchical Prompting
Wenhao Wang; Yifan Sun; Wei Li; Yi Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper explores a hierarchical prompting mechanism for the hierarchical image classification (HIC) task.
1595, Learning from Visual Observation Via Offline Pretrained State-to-Go Transformer
Bohan Zhou; Ke Li; Jiechuan Jiang; Zongqing Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing LfVO approaches either only adopt inefficient online learning schemes or require additional task-specific information like goal states, making them not suited for open-ended tasks. To address these issues, we propose a two-stage framework for learning from visual observation.
1596, TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning Over Temporal Knowledge Graph
Xueyuan Lin; Chengjin Xu; Haihong E; Fenglong Su; Gengxian Zhou; Tianyi Hu; Ningyuan Li; Mingzhi Sun; Haoran Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we utilize fuzzy logic to compute the logic part of the Temporal Feature-Logic embedding, thus naturally modeling all first-order logic operations on the entity set.
1597, Attacks on Online Learners: A Teacher-Student Analysis
Riccardo Giuseppe Margiotta; Sebastian Goldt; Guido Sanguinetti;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we use a control-theoretical perspective to study the scenario where an attacker may perturb data labels to manipulate the learning dynamics of an online learner.
1598, Imbalanced Mixed Linear Regression
Pini Zilber; Boaz Nadler;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Unfortunately, most MLR methods do not perform well in such settings. Motivated by this practical challenge, in this work we propose Mix-IRLS, a novel, simple and fast algorithm for MLR with excellent performance on both balanced and imbalanced mixtures.
1599, PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Qiang Zhou; Weize Li; Lihan Jiang; Guoliang Wang; Guyue Zhou; Shanghang Zhang; Hao Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we build MAD using 20 complex-shaped LEGO toys including 4k views with various poses, and high-quality and diverse 3D anomalies in both simulated and real environments.
1600, HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
Han Liu; Zhi Xu; Xiaotong Zhang; Feng Zhang; Fenglong Ma; Hongyang Chen; Hong Yu; Xianchao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Nevertheless, existing methods rely on the complex heuristic algorithm or unreliable gradient estimation strategy, which probably fall into the local optimum and inevitably consume numerous queries, thus are difficult to craft satisfactory adversarial examples with high semantic similarity and low perturbation rate in a limited query budget. To alleviate above issues, we propose a simple yet effective framework to generate high quality textual adversarial examples under the black-box hard-label attack scenarios, named HQA-Attack.
1601, Compressed Video Prompt Tuning
Bing Li; Jiaxin Chen; Xiuguo Bao; Di Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the presence of prompt-based adaptation methods in raw videos, they encounter challenges in multi-modal fusion and addressing inconsistencies between upstream and downstream input flow. In this paper, we introduce Compressed Video Prompt Tuning (CVPT), a novel prompt tuning method to address these limitations.
1602, VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks Via Pre-trained Models
Ziyi Yin; Muchao Ye; Tianrong Zhang; Tianyu Du; Jinguo Zhu; Han Liu; Jinghui Chen; Ting Wang; Fenglong Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to investigate a new yet practical task to craft image and text perturbations using pre-trained VL models to attack black-box fine-tuned models on different downstream tasks.
1603, VCC: Scaling Transformers to 128K Tokens or More By Prioritizing Important Tokens
Zhanpeng Zeng; Cole Hawkins; Mingyi Hong; Aston Zhang; Nikolaos Pappas; Vikas Singh; Shuai Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we propose to significantly improve the efficiency of Transformers for ultra long sequences, by compressing the sequence into a much smaller representation at each layer.
1604, Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection Over Union
Zifu Wang; Maxim Berman; Amal Rannen-Triki; Philip Torr; Devis Tuia; Tinne Tuytelaars; Luc V Gool; Jiaqian Yu; Matthew Blaschko;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This causes traditional evaluation metrics to be biased towards majority classes, e.g. overall pixel-wise accuracy (Acc), or large objects, e.g. Acc, mean pixel-wise accuracy (mAcc) and per-dataset mean intersection over union ($\text{mIoU}^D$). To address these shortcomings, we propose the use of fine-grained mIoUs along with corresponding worst-case metrics, thereby offering a more holistic evaluation of segmentation techniques.
1605, Jaccard Metric Losses: Optimizing The Jaccard Index with Soft Labels in Semantic Segmentation
Zifu Wang; Xuefei Ning; Matthew Blaschko;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we identify a lack of flexibility in these losses to support vital training techniques like label smoothing, knowledge distillation, and semi-supervised learning, mainly due to their inability to process soft labels. To address this, we introduce Jaccard Metric Losses (JMLs).
1606, Flow Factorized Representation Learning
Yue Song; T. Anderson Keller; Nicu Sebe; Max Welling;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose an alternative viewpoint on such structured representation learning which we call Flow Factorized Representation Learning, and demonstrate it to learn both more efficient and more usefully structured representations than existing frameworks.
1607, FouriDown: Factoring Down-Sampling Into Shuffling and Superposing
Qi Zhu; man zhou; Jie Huang; Naishan Zheng; Hongzhi Gao; Chongyi Li; Yuan Xu; Feng Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we revisit the working mechanism of the spatial down-sampling family and analyze the biased effects caused by the static weighting strategy employed in previous approaches.
1608, Deep Fractional Fourier Transform
Hu Yu; Jie Huang; Lingzhi LI; man zhou; Feng Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a new spatial-frequency analysis tool, Fractional Fourier Transform (FRFT), to provide comprehensive \textbf{unified} spatial-frequency perspectives.
1609, Transition-constant Normalization for Image Enhancement
Jie Huang; man zhou; Jinghao Zhang; Gang Yang; Mingde Yao; Chongyi Li; Zhiwei Xiong; Feng Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To fully leverage the potential of normalization, we present a novel Transition-Constant Normalization (TCN) for various image enhancement tasks.
1610, Attention As Implicit Structural Inference
Ryan Singh; Christopher L Buckley;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the underlying intuition and formalism of attention in Transformers is based on ideas of keys and queries in database management systems. In this work, we pursue a structural inference perspective, building upon, and bringing together, previous theoretical descriptions of attention such as; Gaussian Mixture Models, alignment mechanisms and Hopfield Networks.
1611, Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection
Ruiying Lu; YuJie Wu; Long Tian; Dongsheng Wang; Bo Chen; Xiyang Liu; Ruimin Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Under such a challenging setting, popular reconstruction-based networks with continuous latent representation assumption always suffer from the identical shortcut issue, where both normal and abnormal samples can be well recovered and difficult to distinguish. To address this pivotal issue, we make three improvements.
1612, Density of States Prediction of Crystalline Materials Via Prompt-guided Multi-Modal Transformer
Namkyeong Lee; Heewoong Noh; Sungwon Kim; Dongmin Hyun; Gyoung S. Na; Chanyoung Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose to integrate heterogeneous information obtained from the crystalline materials and the energies via a multi-modal transformer, thereby modeling the complex relationships between the atoms in the crystalline materials and various energy levels for DOS prediction.
1613, A General Framework for Equivariant Neural Networks on Reductive Lie Groups
Ilyes Batatia; Mario Geiger; Jose Munoz; Tess Smidt; Lior Silberman; Christoph Ortner;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a general Equivariant Neural Network architecture capable of respecting the symmetries of the finite-dimensional representations of any reductive Lie Group.
1614, GAN You See Me? Enhanced Data Reconstruction Attacks Against Split Inference
Ziang Li; Mengda Yang; Yaxin Liu; Juan Wang; Hongxin Hu; Wenzhe Yi; Xiaoyang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consequently, these approaches yield unsatisfactory attack results and are sensitive to defense mechanisms. To overcome these challenges, we propose a GAN-based LAtent Space Search attack (GLASS) that harnesses abundant prior knowledge from public data using advanced StyleGAN technologies.
1615, SheetCopilot: Bringing Software Productivity to The Next Level Through Large Language Models
Hongxin Li; Jingran Su; Yuntao Chen; Qing Li; ZHAO-XIANG ZHANG;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a SheetCopilot agent which takes natural language task and control spreadsheet to fulfill the requirements.
1616, UDC-SIT: A Real-World Dataset for Under-Display Cameras
Kyusu Ahn; Byeonghyun Ko; HyunGyu Lee; Chanwoo Park; Jaejin Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a real-world UDC dataset called UDC-SIT.
1617, The Bayesian Stability Zoo
Shay Moran; Hilla Schefler; Jonathan Shafer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Along the way, we prove boosting results that enable amplification of the stability of an algorithm.
1618, Optimal Privacy Guarantees Against Sub-optimal Adversaries in Differentially Private Machine Learning
Georgios Kaissis; Alexander Ziller; Stefan Kolek; Anneliese Riess; Daniel Rueckert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we examine a common threat model relaxation, where (sub-optimal) adversaries lack access to the exact model training database, but may possess related or partial data.
1619, How to Scale Your EMA
Dan Busbridge; Jason Ramapuram; Pierre Ablin; Tatiana Likhomanenko; Eeshan Gunesh Dhekane; Xavier Suau Cuadros; Russell Webb;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Prior works have treated the model EMA separately from optimization, leading to different training dynamics across batch sizes and lower model performance. In this work, we provide a scaling rule for optimization in the presence of model EMAs and demonstrate its validity across a range of architectures, optimizers, and data modalities.
1620, Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution
Xiaotong Luo; Yuan Xie; Yanyun Qu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple yet effective Bi-Sampling Parameter Attribution (BSPA) method for accurate image SR.
1621, Addressing Negative Transfer in Diffusion Models
Hyojun Go; Jin-Young Kim; Yunsung Lee; Seunghyun Lee; Shinhyeok Oh; Hyeongdon Moon; Seungtaek Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to analyze diffusion training from an MTL standpoint, presenting two key observations: $\textbf{(O1)}$ the task affinity between denoising tasks diminishes as the gap between noise levels widens, and $\textbf{(O2)}$ negative transfer can arise even in the context of diffusion training.
1622, Generative Pre-Training of Spatio-Temporal Graph Neural Networks
Zhonghang Li; Lianghao Xia; Yong Xu; Chao Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a spatio-temporal pre-training framework that can be easily integrated into downstream baselines and improve their performance.
1623, CosNet: A Generalized Spectral Kernel Network
Yanfang Xue; Pengfei Fang; Jinyue Tian; Shipeng Zhu; hui xue;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most existing spectral kernel-based methods eliminate the imaginary part, thereby limiting the representation power of the spectral kernel. To tackle this issue, we propose a generalized spectral kernel network, namely, \underline{Co}mplex-valued \underline{s}pectral kernel \underline{Net}work (CosNet), which includes spectral kernel mapping generalization (SKMG) module and complex-valued spectral kernel embedding (CSKE) module.
1624, How to Turn Your Knowledge Graph Embeddings Into Generative Models Via Probabilistic Circuits
Lorenzo Loconte; Nicola Di Mauro; Robert Peharz; Antonio Vergari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work re-interprets the score functions of these KGEs as circuits � constrained computational graphs allowing efficient marginalisation. Then, we design two recipes to obtain efficient generative circuit models by either restricting their activations to be non-negative or squaring their outputs.
1625, Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space Via Soft Elimination
Osama Hanna; Lin Yang; Christina Fragouli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide the first efficient batched algorithm for contextual linear bandits with large action spaces.
1626, Direct Preference-based Policy Optimization Without Reward Modeling
Gaon An; Junhyeok Lee; Xingdong Zuo; Norio Kosaka; Kyung-Min Kim; Hyun Oh Song;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Instead, we propose a PbRL algorithm that directly learns from preference without requiring any reward modeling.
1627, SLIBO-Net: Floorplan Reconstruction Via Slicing Box Representation with Local Geometry Regularization
Jheng-Wei Su; Kuei-Yu Tung; Chi-Han Peng; Peter Wonka; Hung-Kuo (James) Chu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address these, we presents SLIBO-Net, an innovative approach to reconstructing 2D floorplans from unstructured 3D point clouds.
1628, Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
Gleb Bazhenov; Denis Kuznedelev; Andrey Malinin; Artem Babenko; Liudmila Prokhorenkova;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a general approach for inducing diverse distributional shifts based on graph structure.
1629, XTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data
Jing Gong; Minsheng Hao; Xin Zeng; Chiming Liu; Jianzhu Ma; Xingyi Cheng; Taifeng Wang; Xuegong Zhang; Le Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This highlights the need for unsupervised representation learning to fully ingest these data, yet classical transformer architectures are prohibitive to train on such data in terms of both computation and memory. To address this challenge, we propose a novel asymmetric encoder-decoder transformer for scRNA-seq data, called xTrimoGene, which leverages the sparse characteristic of the data to scale up the pre-training.
1630, Reconstructing The Mind's Eye: FMRI-to-Image with Contrastive Learning and Diffusion Priors
Paul Scotti; Atmadeep Banerjee; Jimmie Goode; Stepan Shabalin; Alex Nguyen; ethan cohen; Aidan Dempster; Nathalie Verlinde; Elad Yundler; David Weisberg; Tanishq Abraham; Kenneth Norman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present MindEye, a novel fMRI-to-image approach to retrieve and reconstruct viewed images from brain activity.
1631, On The Overlooked Structure of Stochastic Gradients
Zeke Xie; Qian-Yuan Tang; Mingming Sun; Ping Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we mainly make two contributions. First, we conduct formal statistical tests on the distribution of stochastic gradients and gradient noise across both parameters and iterations.
1632, Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning
Ahmadreza Moradipari; Mohammad Pedramfar; Modjtaba Shokrian Zini; Vaneet Aggarwal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we prove state-of-the-art Bayesian regret bounds for Thompson Sampling in reinforcement learning in a multitude of settings.
1633, A Unified Approach for Maximizing Continuous DR-submodular Functions
Mohammad Pedramfar; Christopher Quinn; Vaneet Aggarwal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a unified approach for maximizing continuous DR-submodular functions that encompasses a range of settings and oracle access types.
1634, Few-Shot Class-Incremental Learning Via Training-Free Prototype Calibration
Qi-wei Wang; Da-Wei Zhou; Yi-Kai Zhang; De-Chuan Zhan; Han-Jia Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To figure out this intriguing phenomenon, we observe that although the feature extractor is only trained on base classes, it can surprisingly represent the *semantic similarity* between the base and *unseen* new classes. Building upon these analyses, we propose a *simple yet effective* Training-frEE calibratioN (TEEN) strategy to enhance the discriminability of new classes by fusing the new prototypes (i.e., mean features of a class) with weighted base prototypes.
1635, Incentives in Private Collaborative Machine Learning
Rachael Sim; Yehong Zhang; Nghia Hoang; Xinyi Xu; Bryan Kian Hsiang Low; Patrick Jaillet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we introduce _differential privacy_ (DP) as an incentive.
1636, SaVeNet: A Scalable Vector Network for Enhanced Molecular Geometric Representation Learning
Sarp Aykent; Tian Xia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the raised concerns, we introduce an efficient and effective framework, Scalable Vector Network (SaVeNet), designed to accommodate a range of geometric requirements without depending on costly embeddings.
1637, SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning
Yi-Chung Chen; Hsi-Wen Chen; Shun-Gui Wang; Ming-syan Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the computation of the Shapley value is expensive, despite using techniques like gradient-based model reconstruction and truncating unnecessary evaluations. Therefore, we present an efficient approach called Single-round Participants Amalgamation for Contribution Evaluation (SPACE).
1638, ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation
ya sheng sun; Yifan Yang; Houwen Peng; Yifei Shen; Yuqing Yang; Han Hu; Lili Qiu; Hideki Koike;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing.
1639, On The Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective
Zeke Xie; Zhiqiang Xu; Jingzhao Zhang; Issei Sato; Masashi Sugiyama;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we discover that, weight decay can unfortunately lead to large gradient norms at the final phase (or the terminated solution) of training, which often indicates bad convergence and poor generalization.
1640, Spuriosity Didn’t Kill The Classifier: Using Invariant Predictions to Harness Spurious Features
Cian Eastwood; Shashank Singh; Andrei L Nicolicioiu; Marin Vlastelica Pogančić; Julius von Kügelgen; Bernhard Schölkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Along the way, we present a solution to the so-called marginal problem from probability theory, in the special case of conditionally-independent features, which may be of independent interest.
1641, SOL: Sampling-based Optimal Linear Bounding of Arbitrary Scalar Functions
Yuriy Biktairov; Jyotirmoy Deshmukh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Fora more general class of functions Lipshitz-continuous in $R$ we propose a sampling-based approach (SOL) which, given an instance of the bounding problem, efficiently computes the tightest linear bounds within a given $\varepsilon > 0$ threshold.
1642, $\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods Across Metrics, Modalities and Models
Xuhong Li; Mengnan Du; Jiamin Chen; Yekun Chai; Himabindu Lakkaraju; Haoyi Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces an XAI benchmark named $\mathcal{M}^4$, which allows evaluating various input feature attribution methods using the same set of faithfulness metrics across multiple data modalities (images and texts) and network structures (ResNets, MobileNets, Transformers).
1643, MathNAS: If Blocks Have A Role in Mathematical Architecture Design
Qinsi Wang; Jinghan Ke; Zhi Liang; Sihai Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we introduce MathNAS, a general NAS framework based on mathematical programming.
1644, A Normative Theory of Social Conflict
Sergey Shuvaev; Evgeny Amelchenko; Dmitry Smagin; Natalia Kudryavtseva; Grigori Enikolopov; Alex Koulakov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Social conflict is a survival mechanism manifesting in normal and pathological behaviors. To understand its underlying principles, we collected behavioral and whole-brain neural data in 100+ mice advancing through stages of social conflict.
1645, Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions
Kai Tan; Pierre C Bellec;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While classical large-sample theory provides asymptotic normality of the MLE under certain conditions, such classical results are expected to fail in high-dimensions as documented for the binary logistic case in the seminal work of Sur and Candès [2019]. We address this issue in classification problems with 3 or more classes, by developing asymptotic normality and asymptotic chi-square results for the multinomial logistic MLE (also known as cross-entropy minimizer) on null covariates.
1646, Large Language Model As Attributed Training Data Generator: A Tale of Diversity and Bias
Yue Yu; Yuchen Zhuang; Jieyu Zhang; Yu Meng; Alexander Ratner; Ranjay Krishna; Jiaming Shen; Chao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Thus, we investigate training data generation with diversely attributed prompts (e.g., specifying attributes like length and style), which have the potential to yield diverse and attributed generated data.
1647, Jigsaw: Learning to Assemble Multiple Fractured Objects
Jiaxin Lu; Yifan Sun; Qixing Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents Jigsaw, a novel framework for assembling physically broken 3D objects from multiple pieces.
1648, Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities
Jingyuan Sun; Mingxiao Li; Yunhao Zhang; Marie-Francine Moens; Zijiao Chen; Shaonan Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the task is challenging due to the noisy nature of fMRI signals and the intricate pattern of brain visual representations. To mitigate these challenges, we introduce a two-phase fMRI representation learning framework.
1649, Semantic HELM: An Interpretable Memory for Reinforcement Learning
Fabian Paischer; Thomas Adler; Markus Hofmarcher; Sepp Hochreiter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel memory mechanism that operates on human language to illuminate the decision-making process.
1650, DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models
Tsun-Hsuan Johnson Wang; Juntian Zheng; Pingchuan Ma; Yilun Du; Byungchul Kim; Andrew Spielberg; Josh Tenenbaum; Chuang Gan; Daniela Rus;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present DiffuseBot, a physics-augmented diffusion model that generates soft robot morphologies capable of excelling in a wide spectrum of tasks.
1651, CD-GraB: Coordinating Distributed Example Orders for Provably Accelerated Training
A. Feder Cooper; Wentao Guo; Duc Khiem Pham; Tiancheng Yuan; Charlie Ruan; Yucheng Lu; Christopher De Sa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, GraB is limited by design: While it demonstrates an impressive ability to scale-up training on centralized data, it does not naturally extend to modern distributed ML workloads. We therefore propose Coordinated Distributed GraB (CD-GraB), which uses insights from prior work on kernel thinning to translate the benefits of provably faster permutation-based example ordering to distributed settings.
1652, Video Timeline Modeling For News Story Understanding
Meng Liu; Mingda Zhang; Jialu Liu; Hanjun Dai; Ming-Hsuan Yang; Shuiwang Ji; Zheyun Feng; Boqing Gong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a novel problem, namely video timeline modeling.
1653, Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection
Cheng-Ju Ho; Chen-Hsuan Tai; Yen-Yu Lin; Ming-Hsuan Yang; Yi-Hsuan Tsai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Diffusion-SS3D, a new perspective of enhancing the quality of pseudo-labels via the diffusion model for semi-supervised 3D object detection.
1654, Uncertainty Quantification Over Graph with Conformalized Graph Neural Networks
Kexin Huang; Ying Jin; Emmanuel Candes; Jure Leskovec;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates.
1655, On Computing Pairwise Statistics with Local Differential Privacy
Badih Ghazi; Pritish Kamath; Ravi Kumar; Pasin Manurangsi; Adam Sealfon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of computing pairwise statistics, i.e., ones of the form $\binom{n}{2}^{-1} \sum_{i \ne j} f(x_i, x_j)$, where $x_i$ denotes the input to the $i$th user, with differential privacy (DP) in the local model.
1656, High-dimensional Contextual Bandit Problem Without Sparsity
Junpei Komiyama; Masaaki Imaizumi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this research, we investigate the high-dimensional linear contextual bandit problem where the number of features $p$ is greater than the budget $T$, or it may even be infinite.
1657, Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
Yuan Wang; Naisong Luo; Tianzhu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we rethink the importance of support information and propose a new query-centric FSS model Adversarial Mining Transformer (AMFormer), which achieves accurate query image segmentation with only rough support guidance or even weak support labels.
1658, CS4ML: A General Framework for Active Learning with Arbitrary Data Based on Christoffel Functions
Juan M. Cardenas; Ben Adcock; Nick Dexter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a general framework for active learning in regression problems.
1659, Residual Q-Learning: Offline and Online Policy Customization Without Value
Chenran Li; Chen Tang; Haruki Nishimura; Jean Mercat; Masayoshi TOMIZUKA; Wei Zhan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel and principled approach to interpret and determine the trade-off between the two task objectives.
1660, Class-conditional Conformal Prediction with Many Classes
Tiffany Ding; Anastasios Angelopoulos; Stephen Bates; Michael Jordan; Ryan Tibshirani;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a method called clustered conformal prediction, which clusters together classes that have “similar'' conformal scores and then performs conformal prediction at the cluster level.
1661, Read and Reap The Rewards: Learning to Play Atari with The Help of Instruction Manuals
Yue Wu; Yewen Fan; Paul Pu Liang; Amos Azaria; Yuanzhi Li; Tom Mitchell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-performing agent.
1662, Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework
Paul Pu Liang; Yun Cheng; Xiang Fan; Chun Kai Ling; Suzanne Nie; Richard Chen; Zihao Deng; Nicholas Allen; Randy Auerbach; Faisal Mahmood; Russ Salakhutdinov; Louis-Philippe Morency;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Subsequently, what are the most suitable multimodal models to capture these interactions? To answer these questions, we propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task.
1663, Factorized Contrastive Learning: Going Beyond Multi-view Redundancy
Paul Pu Liang; Zihao Deng; Martin Q. Ma; James Zou; Louis-Philippe Morency; Ruslan Salakhutdinov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper proposes FactorCL, a new multimodal representation learning method to go beyond multi-view redundancy.
1664, Differentially Private Approximate Near Neighbor Counting in High Dimensions
Alexandr Andoni; Piotr Indyk; Sepideh Mahabadi; Shyam Narayanan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To achieve the latter, the problem is relaxed to allow a “fuzzy” definition of the range boundary, e.g., a count of the points in a ball of radius $r$ might also include points in a ball of radius $cr$ for some $c>1$. In this paper we present an efficient algorithm that offers a sweet spot between these two classes.
1665, Unconstrained Dynamic Regret Via Sparse Coding
Zhiyu Zhang; Ashok Cutkosky; Yannis Paschalidis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: That is, sensible regret bounds should depend on certain complexity measures of the comparator relative to one's prior knowledge. This paper achieves a new type of these adaptive regret bounds via a sparse coding framework.
1666, Waypoint Transformer: Reinforcement Learning Via Supervised Learning with Intermediate Targets
Anirudhan Badrinath; Yannis Flet-Berliac; Allen Nie; Emma Brunskill;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The root cause of this underperformance lies in their inability to seamlessly connect segments of suboptimal trajectories. To overcome this limitation, we present a novel approach to enhance RvS methods by integrating intermediate targets.
1667, PromptIR: Prompting for All-in-One Image Restoration
Vaishnav Potlapalli; Syed Waqas Zamir; Salman Khan; Fahad Shahbaz Khan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a prompt-based learning approach, PromptIR, for All-In-One image restoration that can effectively restore images from various types and levels of degradation.
1668, Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
Jang-Hyun Kim; Sangdoo Yun; Hyun Oh Song;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a unified approach for identifying the problematic data by utilizing a largely ignored source of information: a relational structure of data in the feature-embedded space.
1669, Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation
Ruida Zhou; Tao Liu; Min Cheng; Dileep Kalathil; P. R. Kumar; Chao Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a robust natural actor-critic (RNAC) approach that incorporates the new uncertainty sets and employs function approximation.
1670, Contextual Bandits and Imitation Learning with Preference-Based Active Queries
Ayush Sekhari; Karthik Sridharan; Wen Sun; Runzhe Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The learner's objective is two-fold: to minimize regret associated with the executed actions, while simultaneously, minimizing the number of comparison queries made to the expert. In this paper, we assume that the learner has access to a function class that can represent the expert's preference model under appropriate link functions and present an algorithm that leverages an online regression oracle with respect to this function class.
1671, FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space
Shengzhong Liu; Tomoyoshi Kimura; Dongxin Liu; Ruijie Wang; Jinyang Li; Suhas Diggavi; Mani Srivastava; Tarek Abdelzaher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel contrastive learning framework, called FOCAL, for extracting comprehensive features from multimodal time-series sensing signals through self-supervised training.
1672, Zeroth-Order Methods for Nonsmooth, Nonconvex, and Hierarchical Federated Optimization
Yuyang Qiu; Uday Shanbhag; Farzad Yousefian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study three broadly applicable problem classes in FL: (i) Nondifferentiable nonconvex optimization, e.g., in training of ReLU neural networks; (ii) Federated bilevel optimization, e.g., in hyperparameter learning; (iii) Federated minimax problems, e.g., in adversarial training.
1673, Joint Bayesian Inference of Graphical Structure and Parameters with A Single Generative Flow Network
Tristan Deleu; Mizu Nishikawa-Toomey; Jithendaraa Subramanian; Nikolay Malkin; Laurent Charlin; Yoshua Bengio;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Generative Flow Networks (GFlowNets), a class of generative models over discrete and structured sample spaces, have been previously applied to the problem of inferring the marginal posterior distribution over the directed acyclic graph (DAG) of a Bayesian Network, given a dataset of observations. Based on recent advances extending this framework to non-discrete sample spaces, we propose in this paper to approximate the joint posterior over not only the structure of a Bayesian Network, but also the parameters of its conditional probability distributions.
1674, ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP
Lu Yan; Zhuo Zhang; Guanhong Tao; Kaiyuan Zhang; Xuan Chen; Guangyu Shen; Xiangyu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an innovative test-time poisoned sample detection framework that hinges on the interpretability of model predictions, grounded in the semantic meaning of inputs.
1675, Django: Detecting Trojans in Object Detection Models Via Gaussian Focus Calibration
Guangyu Shen; Siyuan Cheng; Guanhong Tao; Kaiyuan Zhang; Yingqi Liu; Shengwei An; Shiqing Ma; Xiangyu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While existing trigger inversion methods assume that each instance from the support set is equally affected by the injected trigger, we observe that the poison effect can vary significantly across bounding boxes in object detection models due to its dense prediction nature, leading to an undesired optimization objective misalignment issue for existing trigger reverse-engineering methods. To address this challenge, we propose the first object detection backdoor detection framework Django (\textit{\underline{D}etecting Tro\underline{jan}s in Object Detection Models via \underline{G}aussian F\underline{o}cus Calibration}).
1676, This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations
Chiyu Ma; Brandon Zhao; Chaofan Chen; Cynthia Rudin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present ProtoConcepts, a novel method for interpretable image classification combining deep learning and case-based reasoning using prototypical parts.
1677, StressID: A Multimodal Dataset for Stress Identification
Hava Chaptoukaev; Valeriya Strizhkova; Michele Panariello; Bianca Dalpaos; Aglind Reka; Valeria Manera; Susanne Thümmler; Esma ISMAILOVA; Nicholas W.; francois bremond; Massimiliano Todisco; Maria A Zuluaga; Laura M. Ferrari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: $\texttt{StressID}$ is a new dataset specifically designed for stress identification from unimodal and multimodal data.
1678, Multi-Agent Learning with Heterogeneous Linear Contextual Bandits
Anh Do; Thanh Nguyen-Tang; Raman Arora;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, a formal understanding of how and when learners in heterogeneous environments benefit from sharing their respective experiences is far from complete. In this paper, we seek answers to these questions in the context of linear contextual bandits.
1679, Convergence Guarantees for Adversarial Training on Linearly Separable Data
Poorya Mianjy; Raman Arora;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, for the inner loop that implements the adversarial attack during training using projected gradient descent (PGD), we propose maximizing a \emph{lower bound} on the $0/1$-loss by reflecting a surrogate loss about the origin.
1680, Optimistic Rates for Multi-Task Representation Learning
Austin Watkins; Enayat Ullah; Thanh Nguyen-Tang; Raman Arora;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of transfer learning via Multi-Task Representation Learning (MTRL), wherein multiple source tasks are used to learn a good common representation, and a predictor is trained on top of it for the target task.
1681, Cappy: Outperforming and Boosting Large Multi-Task LMs with A Small Scorer
Bowen Tan; Yun Zhu; Lijuan Liu; Eric Xing; Zhiting Hu; Jindong Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Additionally, the most powerful multi-task LLMs, such as OPT-IML-175B and FLAN-PaLM-540B, are not publicly accessible, severely hindering their potential for adaptation. To address these challenges, we introduce a pretrained small scorer, Cappy, specifically designed to enhance the performance and efficiency of multi-task LLMs.
1682, IBA: Towards Irreversible Backdoor Attacks in Federated Learning
Thuy Dung Nguyen; Tuan Nguyen; Anh Tran; Khoa D Doan; Kok-Seng Wong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In many cases, the trigger inserted is often visually apparent, and the backdoor effect is quickly diluted if the adversary is removed from the training process. To address these limitations, we propose a novel backdoor attack framework in FL that jointly learns the optimal and visually stealthy trigger and then gradually implants the backdoor into a global model.
1683, On The Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration
Shuai Zhang; Meng Wang; Hongkang Li; Miao Liu; Pin-Yu Chen; Songtao Lu; Sijia Liu; Keerthiram Murugesan; Subhajit Chaudhury;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper provides a theoretical understanding of deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning.
1684, Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
Hao Wang; Luxi He; Rui Gao; Flavio Calmon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We demonstrate how to characterize aleatoric discrimination by applying Blackwell's results on comparing statistical experiments. We then quantify epistemic discrimination as the gap between a model's accuracy when fairness constraints are applied and the limit posed by aleatoric discrimination.
1685, Path Following Algorithms for $\ell_2$-regularized $M$-estimation with Approximation Guarantee
Yunzhang Zhu; Renxiong Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the context of $\ell_2$-regularized $M$-estimation problem, we propose a novel grid point selection scheme and an adaptive stopping criterion for any given optimization algorithm that produces an approximated solution path with approximation error guarantee.
1686, Contextual Gaussian Process Bandits with Neural Networks
Haoting Zhang; Jinghai He; Rhonda Righter; Zeyu Zheng; Zuo-Jun Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a neural network-accompanied Gaussian process (NN-AGP) model, which leverages neural networks to approximate the unknown reward function regarding the contextual variable, and maintains a Gaussian process with the decision variable.
1687, AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity
Jingyuan Li; Leo Scholl; Trung Le; Amy Orsborn; Eli Shlizerman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address modeling neural population dynamics via the forecasting task and aim to improve the forecasting performance by including a prior, which consists of neurons interacting with each other as a multivariate dynamic system.
1688, Learning Time-Invariant Representations for Individual Neurons from Population Dynamics
Lu Mi; Trung Le; Tianxing He; Eli Shlizerman; Uygar Sümbül;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we propose an unsupervised deep learning based method to assign time-invariant representations to individual neurons based on permutation-, and population size-invariant summary of population recordings.
1689, Errors-in-variables Fr\'echet Regression with Low-rank Covariate Approximation
Kyunghee Han; Dogyoon Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, its practical applicability has been hindered by its reliance on ideal scenarios with abundant and noiseless covariate data. In this paper, we present a novel estimation method that tackles these limitations by leveraging the low-rank structure inherent in the covariate matrix.
1690, HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception
Peiyan Dong; Zhenglun Kong; Xin Meng; Pinrui Yu; Yifan Gong; Geng Yuan; Hao Tang; Yanzhi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we concentrate on building efficient algorithms with practical latency by considering the hardware properties, including memory access cost and degree of parallelism.
1691, PackQViT: Faster Sub-8-bit Vision Transformers Via Full and Packed Quantization on The Mobile
Peiyan Dong; LEI LU; Chao Wu; Cheng Lyu; Geng Yuan; Hao Tang; Yanzhi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an activation-aware fully sub-8-bit quantization-aware training (QAT) framework called \textbf{\M} for efficient yet accurate ViT acceleration on mobile phones to facilitate real-time AI-powered decision-making.
1692, Deep Contract Design Via Discontinuous Piecewise Affine Neural Networks
Tonghan Wang; Paul Duetting; Dmitry Ivanov; Inbal Talgam-Cohen; David Parkes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we initiate the study of deep learning for the automated design of optimal contracts.
1693, Machine Learning Detects Terminal Singularities
Sara Veneziale; Tom Coates; Alexander Kasprzyk;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite their importance, the classification of Q-Fano varieties remains unknown. In this paper we demonstrate that machine learning can be used to understand this classification.
1694, AutoGO: Automated Computation Graph Optimization for Neural Network Evolution
Mohammad Salameh; Keith Mills; Negar Hassanpour; Fred Han; Shuting Zhang; Wei Lu; Shangling Jui; CHUNHUA ZHOU; Fengyu Sun; Di Niu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods either search for neural architectures in heuristic design spaces or apply low-level adjustments to computation primitives to improve inference efficiency on hardware. We present Automated Graph Optimization (AutoGO), a framework to evolve neural networks in a low-level Computation Graphs (CG) of primitive operations to improve both its performance and hardware friendliness.
1695, On The Identifiability of Sparse ICA Without Assuming Non-Gaussianity
Ignavier Ng; Yujia Zheng; Xinshuai Dong; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To accommodate Gaussian sources, we develop an identifiability theory that relies on second-order statistics without imposing further preconditions on the distribution of sources, by introducing novel assumptions on the connective structure from sources to observed variables.
1696, Practical Equivariances Via Relational Conditional Neural Processes
Daolang Huang; Manuel Haussmann; Ulpu Remes; ST John; Grégoire Clarté; Kevin Sebastian Luck; Samuel Kaski; Luigi Acerbi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Relational Conditional Neural Processes (RCNPs), an effective approach to incorporate equivariances into any neural process model.
1697, Temporal Causal Mediation Through A Point Process: Direct and Indirect Effects of Healthcare Interventions
Çağlar Hızlı; ST John; Anne Juuti; Tuure Saarinen; Kirsi Pietiläinen; Pekka Marttinen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing approaches to dynamic causal mediation analysis are limited to regular measurement intervals, simple parametric models, and disregard long-range mediator--outcome interactions. To address these limitations, we propose a non-parametric mediator--outcome model where the mediator is assumed to be a temporal point process that interacts with the outcome process.
1698, SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems
Christopher Yeh; Victor Li; Rajeev Datta; Julio Arroyo; Nicolas Christianson; Chi Zhang; Yize Chen; Mohammad Mehdi Hosseini; Azarang Golmohammadi; Yuanyuan Shi; Yisong Yue; Adam Wierman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present SustainGym, a suite of five environments designed to test the performance of RL algorithms on realistic sustainable energy system tasks, ranging from electric vehicle charging to carbon-aware data center job scheduling.
1699, Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning
Zachary Charles; Nicole Mitchell; Krishna Pillutla; Michael Reneer; Zachary Garrett;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a library, Dataset Grouper, to create large-scale group-structured (e.g., federated) datasets, enabling federated learning simulation at the scale of foundation models.
1700, Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking
Juanhui Li; Harry Shomer; Haitao Mao; Shenglai Zeng; Yao Ma; Neil Shah; Jiliang Tang; Dawei Yin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, multiple limitations currently exist that hinders our ability to properly evaluate these new methods. This includes, but is not limited to: (1) The underreporting of performance on multiple baselines, (2) A lack of a unified data split and evaluation metric on some datasets, (3) An unrealistic evaluation setting that produces negative samples that are easy to classify. To overcome these challenges we first conduct a fair comparison across prominent methods and datasets, utilizing the same dataset settings and hyperparameter settings. We then create a new real-world evaluation setting that samples difficult negative samples via multiple heuristics.
1701, Structured Neural Networks for Density Estimation and Causal Inference
Asic Chen; Ruian (Ian) Shi; Xiang Gao; Ricardo Baptista; Rahul Krishnan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the Structured Neural Network (StrNN), which masks specific pathways in a neural network.
1702, Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”
Farrukh Baratov; Goksenin Yuksel; Darie Petcu; Jan Bakker;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, the authors propose a new metric to measure bias amplification, called LIC, and evaluate it on multiple image captioning models.
1703, CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graphs
Guangyao Zhai; Evin Pınar Örnek; Shun-Cheng Wu; Yan Di; Federico Tombari; Nassir Navab; Benjamin Busam;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense.
1704, Algorithmic Regularization in Tensor Optimization: Towards A Lifted Approach in Matrix Sensing
Ziye Ma; Javad Lavaei; Somayeh Sojoudi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we examine the role of GD in inducing implicit regularization for tensor optimization, particularly within the context of the lifted matrix sensing framework.
1705, MVDoppler: Unleashing The Power of Multi-View Doppler for MicroMotion-based Gait Classification
Soheil Hor; Shubo Yang; Jaeho Choi; Amin Arbabian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces a new large multi-view Doppler dataset together with baseline perception models for micro-motion-based gait analysis and classification.
1706, Bi-Level Offline Policy Optimization with Limited Exploration
Wenzhuo Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration, especially under function approximation. To tackle this issue, we propose a bi-level structured policy optimization algorithm that models a hierarchical interaction between the policy (upper-level) and the value function (lower-level).
1707, [Re] On The Reproducibility of “FairCal: Fairness Calibration for Face Verification”
Marga Don; Satchit Chatterji; Milena Kapralova; Ryan Amaudruz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper aims to reproduce the study FairCal: Fairness Calibration for Face Verification by Salvador et al., focused on verifying three main claims: FairCal (introduced by the authors) achieves state-of-the-art (i) global accuracy, (ii) fairness-calibrated probabilities and (iii) equality in false positive rates across sensitive attributes (i.e. predictive equality).
1708, Stabilized Neural Differential Equations for Learning Constrained Dynamics
Alistair White; Niki Kilbertus; Maximilian Gelbrecht; Niklas Boers;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose stabilized neural differential equations (SNDEs), a method to enforce arbitrary manifold constraints for neural differential equations.
1709, No-Regret Learning in Dynamic Competition with Reference Effects Under Logit Demand
Mengzi Amy Guo; Donghao Ying; Javad Lavaei; Zuo-Jun Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the online projected gradient ascent algorithm (OPGA), where the firms adjust prices using the first-order derivatives of their log-revenues that can be obtained from the market feedback mechanism.
1710, Minimum Norm Interpolation By Shallow Networks: Explicit Regularization and Implicit Bias
Jiyoung Park; Ian Pelakh; Stephan Wojtowytsch;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate how shallow ReLU networks interpolate between known regions as the number of data points and parameters tends to infinity.
1711, Gaussian Differential Privacy on Riemannian Manifolds
Yangdi Jiang; Xiaotian Chang; Yi Liu; Lei Ding; Linglong Kong; Bei Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By harnessing the power of the renowned Bishop-Gromov theorem in geometric analysis, we propose a Riemannian Gaussian distribution that integrates the Riemannian distance, allowing us to achieve GDP in Riemannian manifolds with bounded Ricci curvature.
1712, Mechanism Design for Collaborative Normal Mean Estimation
Yiding Chen; Jerry Zhu; Kirthevasan Kandasamy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study collaborative normal mean estimation, where $m$ strategic agents collect i.i.d samples from a normal distribution $\mathcal{N}(\mu, \sigma^2)$ at a cost.
1713, RDumb: A Simple Approach That Questions Our Progress in Continual Test-time Adaptation
Ori Press; Steffen Schneider; Matthias Kümmerer; Matthias Bethge;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To examine the reported progress in the field, we propose the continually changing corruptions (CCC) benchmark for measuring asymptotic performance of TTA techniques.
1714, RELIC: Reproducibility and Extension on LIC Metric in Quantifying Bias in Captioning Models
Martijn van Raaphorst; Egoitz Gonzalez; Marta Grasa; Paula Antequera Hernández;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces LIC, a metric to quantify bias amplification by image captioning models, which is tested for gender and racial bias amplification.
1715, Adversarial Model for Offline Reinforcement Learning
Mohak Bhardwaj; Tengyang Xie; Byron Boots; Nan Jiang; Ching-An Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel model-based offline Reinforcement Learning (RL) framework, called Adversarial Model for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon an arbitrary reference policy regardless of data coverage.
1716, PHOTOSWAP: Personalized Subject Swapping in Images
Jing Gu; Yilin Wang; Nanxuan Zhao; Tsu-Jui Fu; Wei Xiong; Qing Liu; Zhifei Zhang; HE Zhang; Jianming Zhang; HyunJoon Jung; Xin Eric Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Envision seamlessly substituting a tabby cat lounging on a sunlit window sill in a photograph with your own playful puppy, all while preserving the original charm and composition of the image. We present \emph{Photoswap}, a novel approach that enables this immersive image editing experience through personalized subject swapping in existing images.
1717, Optimistic Active Exploration of Dynamical Systems
Bhavya; Lenart Treven; Cansu Sancaktar; Sebastian Blaes; Stelian Coros; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: How should we explore an unknown dynamical system such that the estimated model allows us to solve multiple downstream tasks in a zero-shot manner? In this paper, we address this challenge, by developing an algorithm -- OPAX -- for active exploration.
1718, Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness
Gang Li; Wei Tong; Tianbao Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this type of adversarial robustness is insufficient for many applications, as minor perturbations on a single example can significantly impact AP while not greatly influencing the accuracy of the prediction system. To tackle this issue, we introduce a novel formulation that combines an AP surrogate loss with a regularization term representing adversarial ranking robustness, which maintains the consistency between ranking of clean data and that of perturbed data.
1719, On The Imitation of Non-Markovian Demonstrations: From Low-Level Stability to High-Level Planning
Adam Block; Daniel Pfrommer; Max Simchowitz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a theoretical framework for studying the imitation of stochastic, non-Markovian, potentially multi-modal expert demonstrations in nonlinear dynamical systems.
1720, Im-Promptu: In-Context Composition from Image Prompts
Bhishma Dedhia; Michael Chang; Jake Snell; Tom Griffiths; Niraj Jha;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we investigate whether analogical reasoning can enable in-context composition over composable elements of visual stimuli.
1721, Simple, Scalable and Effective Clustering Via One-Dimensional Projections
Moses Charikar; Monika Henzinger; Lunjia Hu; Maximilian Vötsch; Erik Waingarten;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a simple randomized clustering algorithm that provably runs in expected time $O(\mathsf{nnz}(X) + n\log n)$ for arbitrary $k$.
1722, COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs
Tiep Le; VASUDEV LAL; Phillip Howard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite their demonstrated utility for NLP, multimodal counterfactual examples have been relatively unexplored due to the difficulty of creating paired image-text data with minimal counterfactual changes. To address this challenge, we introduce a scalable framework for automatic generation of counterfactual examples using text-to-image diffusion models.
1723, Latent SDEs on Homogeneous Spaces
Sebastian Zeng; Florian Graf; Roland Kwitt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the unobserved solution of a latent stochastic differential equation (SDE).
1724, Invertible Normalizing Flow Neural Networks By JKO Scheme
Chen Xu; Xiuyuan Cheng; Yao Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Using numerical experiments with synthetic and real data, we show that the proposed JKO-iFlow model achieves similar or better performance in generating new samples compared with existing flow and diffusion models at a significantly reduced computational and memory cost.
1725, BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking
Bin Huang; Jiaqian Yu; Yiwei Chen; Siyang Pan; Qiang Wang; Zhi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: State-of-the-art VOT trackers extract positive and negative examples that are used to guide the tracker to distinguish the object from the background. In this paper, we show that this characteristic can be exploited to introduce new threats and hence propose a simple yet effective poison-only backdoor attack.
1726, Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction
Yangqing Fu; Ming Sun; Buqing Nie; Yue Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the computational complexity of MCTS-based algorithms is influenced by the size of the search space. To address this issue, we propose a novel probability tree state abstraction (PTSA) algorithm to improve the search efficiency of MCTS.
1727, Understanding and Addressing The Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning
Hongyu Zang; Xin Li; Leiji Zhang; Yang Liu; Baigui Sun; Riashat Islam; Remi Tachet des Combes; Romain Laroche;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We aim to understand why bisimulation methods succeed in online settings, but falter in offline tasks.
1728, Causal Effect Regularization: Automated Detection and Removal of Spurious Attributes
Abhinav Kumar; Amit Deshpande; Amit Sharma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, in real-world data, information about spurious attributes is typically unavailable. Therefore, we propose a method to automatically identify spurious attributes by estimating their causal effect on the label and then use a regularization objective to mitigate the classifier's reliance on them.
1729, A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective
Yazhou Ren; Chenhang Cui; Jingyu Pu; Jiawei Li; Xiaorong Pu; Tianyi Wu; Yutao Shi; Lifang He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study presents a new approach called Sufficient Multi-View Clustering (SUMVC) that examines the multi-view clustering framework from an information-theoretic standpoint.
1730, Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics
Koen Minartz; Yoeri Poels; Simon Koop; Vlado Menkovski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Equivariant Probabilistic Neural Simulation (EPNS), a framework for autoregressive probabilistic modeling of equivariant distributions over system evolutions.
1731, Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network
Yixiao Zhou; Ruiqi Jia; Xiaoqing Lyu; Yumeng Zhao; Hefeng Quan; Hongxiang Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: More specifically, existing methods are insufficient to capture the relative spatial relations through current graph construction approaches from the locations of semantic keypoints. To address these issues, we introduce a positional reconstruction encoder-decoder (PR-EnDec) to model intrinsic graph spatial structure, and present an end-to-end graph matching network PREGM based on PR-EnDec.
1732, QATCH: Benchmarking Table Representation Learning Models on Your Data
Simone Papicchio; Paolo Papotti; Luca Cagliero;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present QATCH (Query-Aided TRL Checklist), a toolbox to highlight TRL models' strengths and weaknesses on unseen data.
1733, Score-based Generative Modeling Through Stochastic Evolution Equations
Sungbin Lim; EUN BEE YOUN; Taehyun Byun; Taewon Kang; Seungwoo Kim; Kyungjae Lee; Sungjoon Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we derive a generalized time-reversal formula to build a bridge between probabilistic diffusion models and stochastic evolution equations and propose a score-based generative model called Hilbert Diffusion Model (HDM).
1734, Score-based Generative Models with Lévy Processes
EUN BEE YOUN; Keehun Park; Sungwoong Kim; Sungbin Lim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In order to overcome the limitations of Brownian motion, we introduce a novel score-based generative model referred to as Lévy-Itō Model (LIM).
1735, Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile
Wenwen Zhang; Arvin Tashakori; Zenan Jiang; Amir Servati; Harishkumar Narayana; Saeid Soltanian; Rou Yi Yeap; Menghan Ma; Lauren Toy; Peyman Servati;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The kinematics of human movements and locomotion are closely linked to the activation and contractions of muscles. To investigate this, we present a multimodal dataset with benchmarks collected using a novel pair of Intelligent Knee Sleeves (Texavie MarsWear Knee Sleeves) for human pose estimation.
1736, Energy Guided Diffusion for Generating Neurally Exciting Images
Pawel Pierzchlewicz; Konstantin Willeke; Arne Nix; Pavithra Elumalai; Kelli Restivo; Tori Shinn; Cate Nealley; Gabrielle Rodriguez; Saumil Patel; Katrin Franke; Andreas Tolias; Fabian Sinz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, as the predictive network becomes deeper and more complex, synthesizing MEIs via straightforward gradient ascent (GA) can struggle to produce qualitatively good results and overfit to idiosyncrasies of a more complex model, potentially decreasing the MEI's model-to-brain transferability. To solve this problem, we propose a diffusion-based method for generating MEIs via Energy Guidance (EGG).
1737, SpecTr: Fast Speculative Decoding Via Optimal Transport
Ziteng Sun; Ananda Theertha Suresh; Jae Hun Ro; Ahmad Beirami; Himanshu Jain; Felix Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we provide a principled understanding of speculative decoding through the lens of optimal transport (OT) with *membership cost*.
1738, Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos Via Temporal Alignment
Zihui (Sherry) Xue; Kristen Grauman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose AE2, a self-supervised embedding approach with two key designs: (1) an object-centric encoder that explicitly focuses on regions corresponding to hands and active objects; (2) a contrastive-based alignment objective that leverages temporally reversed frames as negative samples.
1739, Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training
Aleksandra Nowak; Bram Grooten; Decebal Constantin Mocanu; Jacek Tabor;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While the growing criterion's impact on DST performance is relatively well studied, the influence of the pruning criterion remains overlooked. To address this issue, we design and perform an extensive empirical analysis of various pruning criteria to better understand their impact on the dynamics of DST solutions.
1740, Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery
Mateusz Olko; Michał Zając; Aleksandra Nowak; Nino Scherrer; Yashas Annadani; Stefan Bauer; Łukasz Kuciński; Piotr Miłoś;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel Gradient-based Intervention Targeting method, abbreviated GIT, that ’trusts’ the gradient estimator of a gradient-based causal discovery framework to provide signals for the intervention targeting function.
1741, Quantification of Uncertainty with Adversarial Models
Kajetan Schweighofer; Lukas Aichberger; Mykyta Ielanskyi; Sepp Hochreiter;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We suggest Quantification of Uncertainty with Adversarial Models (QUAM) to better estimate the epistemic uncertainty.
1742, Gigastep - One Billion Steps Per Second Multi-agent Reinforcement Learning
Mathias Lechner; lianhao yin; Tim Seyde; Tsun-Hsuan Johnson Wang; Wei Xiao; Ramin Hasani; Joshua Rountree; Daniela Rus;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Multi-agent reinforcement learning (MARL) research is faced with a trade-off: it either uses complex environments requiring large compute resources, which makes it inaccessible to researchers with limited resources, or relies on simpler dynamics for faster execution, which makes the transferability of the results to more realistic tasks challenging. Motivated by these challenges, we present Gigastep, a fully vectorizable, MARL environment implemented in JAX, capable of executing up to one billion environment steps per second on consumer-grade hardware.
1743, Scattering Vision Transformer: Spectral Mixing Is What Matters in Transformers
Badri Patro; Vijay Agneeswaran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a Scattering Vision Transformer (SVT) which uses a spectrally scattering network to capture fine-grained information about an image.
1744, An Efficient Dataset Condensation Plugin and Its Application to Continual Learning
Enneng Yang; Li Shen; Zhenyi Wang; Tongliang Liu; Guibing Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a simple-yet-efficient dataset condensation plugin that matches the raw and synthetic datasets in a low-dimensional manifold.
1745, LightSpeed: Lighter and Faster Neural Light Field on Mobile Devices
Aarush Gupta; Junli Cao; Chaoyang Wang; Jian Ren; Sergey Tulyakov; Ju Hu; László Jeni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we find that using the light slab representation is an efficient representation for learning a neural light field.
1746, Estimating Noise Correlations in Neural Populations with Wishart Processes
Amin Nejatbakhsh; Isabel Garon; Alex Williams;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our key idea is to exploit the fact that conditions are smoothly parameterized in many neuroscience experiments, enabling us to pool statistical power from trials in neighboring conditions.
1747, How Hard Are Computer Vision Datasets? Calibrating Dataset Difficulty to Viewing Time
David Mayo; Jesse Cummings; Xinyu Lin; Dan Gutfreund; Boris Katz; Andrei Barbu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Humans outperform object recognizers despite the fact that models perform well on current datasets, including those explicitly designed to challenge machines with debiased images or distribution shift. This problem persists, in part, because we have no guidance on the absolute difficulty of an image or dataset making it hard to objectively assess progress toward human-level performance, to cover the range of human abilities, and to increase the challenge posed by a dataset. We develop a dataset difficulty metric the MVT, Minimum Viewing Time, that addresses these three problems.
1748, Eliminating Domain Bias for Federated Learning in Representation Space
Jianqing Zhang; Yang Hua; Jian Cao; Hao Wang; Tao Song; Zhengui XUE; Ruhui Ma; Haibing Guan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator for federated learning (DBE).
1749, A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation
Junfeng Zuo; Xiao Liu; Ying Nian Wu; Si Wu; Wenhao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a canonical nonlinear recurrent circuit dynamics, modeled as a continuous attractor network, whose neuronal population responses embed a temporal sequence that is TS equivariant.
1750, Finite-Time Analysis of Whittle Index Based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation
GUOJUN XIONG; Jian Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale.
1751, FDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models
Hao ZHANG; Tianyuan DAI; Yanbo Xu; Yu-Wing Tai; Chi-Keung Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Face Diffusion NeRF (FDNeRF), a new generative method to reconstruct high-quality Face NeRFs from single images, complete with semantic editing and relighting capabilities.
1752, On Slicing Optimality for Mutual Information
Ammar Fayad; Majd Ibrahim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a principled framework that searches for an \textit{optimal} distribution of slices for MI.
1753, Mr. Sum: Large-scale Video Summarization Dataset and Benchmark
Jinhwan Sul; Jihoon Han; Joonseok Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes Mr. Highlight, a large-scale video highlight detection dataset, which contains 31,892 videos and reliable labels aggregated over 50,000+ users per video.
1754, Fast Scalable and Accurate Discovery of DAGs Using The Best Order Score Search and Grow Shrink Trees
Bryan Andrews; Joseph Ramsey; Ruben Sanchez Romero; Jazmin Camchong; Erich Kummerfeld;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the accuracy and execution time of learning algorithms generally struggle to scale to problems with hundreds of highly connected variables---for instance, recovering brain networks from fMRI data. We introduce the best order score search (BOSS) and grow-shrink trees (GSTs) for learning directed acyclic graphs (DAGs) in this paradigm.
1755, Online Convex Optimization with Unbounded Memory
Raunak Kumar; Sarah Dean; Robert Kleinberg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we introduce a generalization of the OCO framework, ``Online Convex Optimization with Unbounded Memory'', that captures long-term dependence on past decisions.
1756, Verifiable Feature Attributions: A Bridge Between Post Hoc Explainability and Inherent Interpretability
Usha Bhalla; Suraj Srinivas; Himabindu Lakkaraju;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we aim to bridge the gap between the aforementioned strategies by proposing \emph{Verifiability Tuning} (VerT), a method that transforms black-box models into models that naturally yield faithful and verifiable feature attributions.
1757, Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
Ayush Tewari; Tianwei Yin; George Cazenavette; Semon Rezchikov; Josh Tenenbaum; Fredo Durand; Bill Freeman; Vincent Sitzmann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A key contribution of our work is the integration of a differentiable forward model into the denoising process.
1758, Meta-Learning Adversarial Bandit Algorithms
Misha Khodak; Ilya Osadchiy; Keegan Harris; Maria-Florina Balcan; Kfir Y. Levy; Ron Meir; Steven Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study online meta-learning with bandit feedback, with the goal of improving performance across multiple tasks if they are similar according to some natural similarity measure.
1759, Scalable Membership Inference Attacks Via Quantile Regression
Martin Bertran; Shuai Tang; Aaron Roth; Michael Kearns; Jamie Morgenstern; Steven Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we introduce a new class of attack based on performing quantile regression on the distribution of confidence scores induced by the model under attack on points that were not used in training.
1760, Learning Shared Safety Constraints from Multi-task Demonstrations
Konwoo Kim; Gokul Swamy; ZUXIN LIU; DING ZHAO; Sanjiban Choudhury; Steven Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show how to learn constraints from expert demonstrations of safe task completion by extending inverse reinforcement learning (IRL) techniques to the space of constraints.
1761, Adaptive Principal Component Regression with Applications to Panel Data
Anish Agarwal; Keegan Harris; Justin Whitehouse; Steven Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As an application of our bounds, we provide a framework for counterfactual estimation of unit-specific treatment effects in panel data settings when interventions are assigned adaptively.
1762, Improved Self-Normalized Concentration in Hilbert Spaces: Sublinear Regret for GP-UCB
Justin Whitehouse; Aaditya Ramdas; Steven Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This has led to a longstanding open question: are existing regret analyses for GP-UCB tight, or can bounds be improved by using more sophisticated analytical techniques? In this work, we resolve this open question and show that GP-UCB enjoys nearly optimal regret.
1763, Strategic Apple Tasting
Keegan Harris; Chara Podimata; Steven Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our goal is to achieve sublinear strategic regret, which compares the performance of the principal to that of the best fixed policy in hindsight, if the agents were truthful when revealing their contexts.
1764, DataPerf: Benchmarks for Data-Centric AI Development
Mark Mazumder; Colby Banbury; Xiaozhe Yao; Bojan Karlaš; William Gaviria Rojas; Sudnya Diamos; Greg Diamos; Lynn He; Alicia Parrish; Hannah Rose Kirk; Jessica Quaye; Charvi Rastogi; Douwe Kiela; David Jurado; David Kanter; Rafael Mosquera; Will Cukierski; Juan Ciro; Lora Aroyo; Bilge Acun; Lingjiao Chen; Mehul Raje; Max Bartolo; Evan Sabri Eyuboglu; Amirata Ghorbani; Emmett Goodman; Addison Howard; Oana Inel; Tariq Kane; Christine R. Kirkpatrick; D. Sculley; Tzu-Sheng Kuo; Jonas Mueller; Tristan Thrush; Joaquin Vanschoren; Margaret Warren; Adina Williams; Serena Yeung; Newsha Ardalani; Praveen Paritosh; Ce Zhang; James Zou; Carole-Jean Wu; Cody Coleman; Andrew Ng; Peter Mattson; Vijay Janapa Reddi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We aim to foster innovation in data-centric AI through competition, comparability, and reproducibility.
1765, On Learning Latent Models with Multi-Instance Weak Supervision
Kaifu Wang; Efthymia Tsamoura; Dan Roth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide the first theoretical study of multi-instance PLL with possibly an unknown transition $\sigma$.
1766, Generative Category-level Object Pose Estimation Via Diffusion Models
Jiyao Zhang; Mingdong Wu; Hao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To avoid the costly integration process when estimating the likelihood, we introduce an alternative method that distils an energy-based model from the original score-based model, enabling end-to-end likelihood estimation.
1767, Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
Tianhao Wu; Mingdong Wu; Jiyao Zhang; Yunchong Gan; Hao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel task called human-assisting dexterous grasping that aims to train a policy for controlling a robotic hand's fingers to assist users in grasping objects.
1768, Optimization of Inter-group Criteria for Clustering with Minimum Size Constraints
Eduardo Laber; Lucas Murtinho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To complement our work, we present an empirical study with 10 real datasets that provides evidence that our methods work very well in practical settings.
1769, Robust Data Valuation with Weighted Banzhaf Values
Weida Li; Yaoliang Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Surprisingly, our empirical study shows that the Banzhaf value is not always the most robust when compared to a broader family: weighted Banzhaf values. To analyze this scenario, we introduce the concept of Kronecker noise to model more realistic ambient noises, and we prove that the uniquely robust value lies in the family of weighted Banzhaf values while minimizing the worst-case entropy.
1770, [Re] On The Reproducibility of CartoonX
Robin Sasse; Aniek Eijpe; Jona Ruthardt; Elias Dubbeldam;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this reproducibility study, we examine the claims of the original authors of CartoonX that it: (i) extracts relevant piece-wise smooth parts of the image, resulting in explanations which are more straightforward to interpret for humans; (ii) achieves lower distortion in the model output, using fewer coefficients than other state-of-the-art methods; (iii) is model-agnostic. Finally, we examine how to reduce the runtime.
1771, V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs
Jun Yin; Senzhang Wang; Chaozhuo Li; Xing Xie; Jianxin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, a robust graph representation extractor, which takes insights of variational inference, is proposed to infer the latent distribution of graph representations.
1772, Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks
Jun Yin; Senzhang Wang; Hao Yan; Chaozhuo Li; Jianxun Lian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by the great success of recent pre-training techniques, we for the first time propose the Pre-training Interpretable Graph Neural Network ($\pi$-GNN) to distill the universal interpretability of GNNs by pre-training over synthetic graphs with ground-truth explanations. Specifically, we introduce a structural pattern learning module to extract diverse universal structure patterns and integrate them together to comprehensively represent the graphs of different types.
1773, Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths
Lars Holdijk; Yuanqi Du; Ferry Hooft; Priyank Jaini; Berend Ensing; Max Welling;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Showing a formal relation between the problem of sampling molecular transition paths, the Schrodinger bridge problem and stochastic optimal control with neural network policies, we propose a machine learning method for sampling said transitions.
1774, Alternation Makes The Adversary Weaker in Two-player Games
Volkan Cevher; Ashok Cutkosky; Ali Kavis; Georgios Piliouras; Stratis Skoulakis; Luca Viano;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: More precisely, we present two online learning algorithms for alternating OLO that respectively admit $\mathcal{O}((\log n)^{4/3} T^{1/3})$ regret for the $n$-dimensional simplex and $\mathcal{O}(\rho \log T)$ regret for the ball of radius $\rho>0$.
1775, BioMassters: A Benchmark Dataset for Forest Biomass Estimation Using Multi-modal Satellite Time-series
Andrea Nascetti; Ritu Yadav; Kirill Brodt; Qixun Qu; Hongwei Fan; Yuri Shendryk; Isha Shah; Christine Chung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The aim of the BioMassters data challenge and benchmark dataset is to investigate the potential of multi-modal satellite data (Sentinel-1 SAR and Sentinel-2 MSI) to estimate forest biomass at a large scale using the Finnish Forest Centre's open forest and nature airborne LiDAR data as a reference.
1776, Interpreting Unsupervised Anomaly Detection in Security Via Rule Extraction
Ruoyu Li; Qing Li; Yu Zhang; Dan Zhao; Yong Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a post-hoc method to globally explain a black-box unsupervised anomaly detection model via rule extraction.
1777, Don’t Just Prune By Magnitude! Your Mask Topology Is A Secret Weapon
Duc Hoang; Souvik Kundu; Shiwei Liu; Zhangyang Atlas Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, no prior work explicitly explores the role of parameters in the graph's connectivity, making the graph-based understanding of pruned masks and the magnitude/gradient-based pruning practice isolated from one another. This paper strives to fill in this gap, by analyzing the Weighted Spectral Gap of Ramanujan structures in sparse neural networks and investigates its correlation with final performance.
1778, Neural Frailty Machine: Beyond Proportional Hazard Assumption in Neural Survival Regressions
Ruofan Wu; Jiawei Qiao; Mingzhe Wu; Wen Yu; Ming Zheng; Tengfei LIU; Tianyi Zhang; Weiqiang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present neural frailty machine (NFM), a powerful and flexible neural modeling framework for survival regressions.
1779, Estimating Generic 3D Room Structures from 2D Annotations
Denys Rozumnyi; Stefan Popov; Kevis-kokitsi Maninis; Matthias Niessner; Vittorio Ferrari;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a novel method to produce generic 3D room layouts just from 2D segmentation masks, which are easy to annotate for humans.
1780, Provable Training for Graph Contrastive Learning
Yue Yu; Xiao Wang; Mengmei Zhang; Nian Liu; Chuan Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To answer these questions, we first present experimental evidence showing that the training of GCL is indeed imbalanced across all nodes. To address this problem, we propose the metric node compactness, which is the lower bound of how a node follows the GCL principle related to the range of augmentations.
1781, Lovász Principle for Unsupervised Graph Representation Learning
Ziheng Sun; Chris Ding; Jicong Fan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel graph-level representation learning principle called Lovász principle, which is motivated by the Lovász number in graph theory.
1782, On Permutation Symmetries in Bayesian Neural Network Posteriors
Simone Rossi; Ankit Singh; Thomas Hannagan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building on the work of Ainsworth et al. (2023), we frame the problem as a combinatorial optimization one, using an approximation to the sum of bilinear assignment problem.
1783, Adaptive SGD with Polyak Stepsize and Line-search: Robust Convergence and Variance Reduction
Xiaowen Jiang; Sebastian Stich;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we make two contributions: Firstly, we propose two new variants of SPS and SLS, called AdaSPS and AdaSLS, which guarantee convergence in non-interpolation settings and maintain sub-linear and linear convergence rates for convex and strongly convex functions when training over-parameterized models. AdaSLS requires no knowledge of problem-dependent parameters, and AdaSPS requires only a lower bound of the optimal function value as input. Secondly, we equip AdaSPS and AdaSLS with a novel variance reduction technique and obtain algorithms that require $\widetilde{\mathcal{O}}(n+1/\epsilon)$ gradient evaluations to achieve an $\smash{\mathcal{O}(\epsilon)}$-suboptimality for convex functions, which improves upon the slower $\mathcal{O}(1/\epsilon^2)$ rates of AdaSPS and AdaSLS without variance reduction in the non-interpolation regimes.
1784, ResMem: Learn What You Can and Memorize The Rest
Zitong Yang; MICHAL LUKASIK; Vaishnavh Nagarajan; Zonglin Li; Ankit Rawat; Manzil Zaheer; Aditya Menon; Sanjiv Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we propose the residual-memorization (ResMem) algorithm, a new method that augments an existing prediction model (e.g., a neural network) by fitting the model's residuals with a nearest-neighbor based regressor.
1785, When Does Confidence-Based Cascade Deferral Suffice?
Wittawat Jitkrittum; Neha Gupta; Aditya Menon; Harikrishna Narasimhan; Ankit Rawat; Sanjiv Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we seek to better understand the conditions under which confidence-based deferral may fail, and when alternate deferral strategies can perform better.
1786, On Student-teacher Deviations in Distillation: Does It Pay to Disobey?
Vaishnavh Nagarajan; Aditya Menon; Srinadh Bhojanapalli; Hossein Mobahi; Sanjiv Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, it has been shown in recent work that, despite being trained to fit the teacher's probabilities, the student both significantly deviates from these probabilities, while performing even better than the teacher. Our work aims to reconcile this paradoxical observation by characterizing the precise nature of the student-teacher deviations, and by arguing how it is possible that they co-occur with better generalization.
1787, Training Fully Connected Neural Networks Is $\exists\mathbb{R}$-Complete
Daniel Bertschinger; Christoph Hertrich; Paul Jungeblut; Tillmann Miltzow; Simon Weber;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the algorithmic problem of finding the optimal weights and biases for a two-layer fully connected neural network to fit a given set of data points, also known as empirical risk minimization.
1788, Mode Connectivity in Auction Design
Christoph Hertrich; Yixin Tao; László A. Végh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent work in differentiable economics showed that neural networks can efficiently learn known optimal auction mechanisms and discover interesting new ones. In an attempt to theoretically justify their empirical success, we focus on one of the first such networks, RochetNet, and a generalized version for affine maximizer auctions.
1789, Linear Time Algorithms for K-means with Multi-Swap Local Search
Junyu Huang; Qilong Feng; Ziyun Huang; Jinhui Xu; Jianxin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a multi-swap local search algorithm for the $k$-means problem with linear running time in the data size.
1790, Uncertainty Quantification Via Neural Posterior Principal Components
Elias Nehme; Omer Yair; Tomer Michaeli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a method for predicting the PCs of the posterior distribution for any input image, in a single forward pass of a neural network.
1791, Variational Annealing on Graphs for Combinatorial Optimization
Sebastian Sanokowski; Wilhelm Berghammer; Sepp Hochreiter; Sebastian Lehner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Subgraph Tokenization in which the configuration of a set of solution variables is represented by a single token.
1792, Deep Stochastic Processes Via Functional Markov Transition Operators
Jin Xu; Emilien Dupont; Kaspar Märtens; Thomas Rainforth; Yee Whye Teh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Markov Neural Processes (MNPs), a new class of Stochastic Processes (SPs) which are constructed by stacking sequences of neural parameterised Markov transition operators in function space.
1793, Decompose Novel Into Known: Part Concept Learning For 3D Novel Class Discovery
Tingyu Weng; Jun Xiao; Haiyong Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address 3D novel class discovery (NCD) that discovers novel classes from an unlabeled dataset by leveraging the knowledge of disjoint known classes.
1794, Image Captioners Are Scalable Vision Learners Too
Michael Tschannen; Manoj Kumar; Andreas Steiner; Xiaohua Zhai; Neil Houlsby; Lucas Beyer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: At the same time, image captioning on this type of data is commonly considered an inferior pretraining strategy. In this paper, we perform a fair comparison of these two pretraining strategies, carefully matching training data, compute, and model capacity.
1795, QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules
Haiyang Yu; Meng Liu; Youzhi Luo; Alex Strasser; Xiaofeng Qian; Xiaoning Qian; Shuiwang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 2,399 molecular dynamics trajectories and 130,831 stable molecular geometries, based on the QM9 dataset.
1796, FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
Zhuo Huang; Li Shen; Jun Yu; Bo Han; Tongliang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose FlatMatch which minimizes a cross-sharpness measure to ensure consistent learning performance between the two datasets.
1797, Conditional Score-based Diffusion Models for Bayesian Inference in Infinite Dimensions
Lorenzo Baldassari; Ali Siahkoohi; Josselin Garnier; Knut Solna; Maarten V. de Hoop;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This may not be feasible in inverse problems with computationally costly forward operators. To address these limitations, in this work we propose a method to learn the posterior distribution in infinite-dimensional Bayesian linear inverse problems using amortized conditional SDMs.
1798, Making Scalable Meta Learning Practical
Sang Choe; Sanket Vaibhav Mehta; Hwijeen Ahn; Willie Neiswanger; Pengtao Xie; Emma Strubell; Eric Xing;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we focus on making scalable meta learning practical by introducing SAMA, which combines advances in both implicit differentiation algorithms and systems.
1799, Importance-aware Co-teaching for Offline Model-based Optimization
Ye Yuan; Can Chen; Zixuan Liu; Willie Neiswanger; Xue (Steve) Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we propose $\textit{\textbf{I}mportance-aware \textbf{C}o-\textbf{T}eaching for Offline Model-based Optimization}~(\textbf{ICT})$.
1800, Towards Combinatorial Generalization in Catalyst Systems: A Kohn-Sham Charge-Density Approach
Phillip Pope; David Jacobs;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we investigate another approach based on the pointwise learning of the Kohn-Sham charge-density.
1801, Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
Changsheng Lv; Shuai Zhang; Yapeng Tian; Mengshi Qi; Huadong Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a Disentangled Counterfactual Learning (DCL) approach for physical audiovisual commonsense reasoning.
1802, Algorithm Selection for Deep Active Learning with Imbalanced Datasets
Jifan Zhang; Shuai Shao; Saurabh Verma; Robert Nowak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning.
1803, Max-Sliced Mutual Information
Dor Tsur; Ziv Goldfeld; Kristjan Greenewald;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work proposes a middle ground in the form a scalable information-theoretic generalization of CCA, termed max-sliced mutual information (mSMI).
1804, Learning to Modulate Pre-trained Models in RL
Thomas Schmied; Markus Hofmarcher; Fabian Paischer; Razvan Pascanu; Sepp Hochreiter;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our study shows that with most fine-tuning approaches, the performance on pre-training tasks deteriorates significantly. Therefore, we propose a novel method, Learning-to-Modulate (L2M), that avoids the degradation of learned skills by modulating the information flow of the frozen pre-trained model via a learnable modulation pool.
1805, SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models
Shuchen Xue; Mingyang Yi; Weijian Luo; Shifeng Zhang; Jiacheng Sun; Zhenguo Li; Zhi-Ming Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we systematically study stochasticity sampling from two aspects: variance-controlled diffusion SDE and linear multi-step SDE solver.
1806, A Graph-Theoretic Framework for Understanding Open-World Representation Learning
Yiyou Sun; Zhenmei Shi; Yixuan Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, based on our graph formulation, we introduce a new algorithm called Spectral Open-world Representation Learning (SORL), and show that minimizing our loss is equivalent to performing spectral decomposition on the graph.
1807, DäRF: Boosting Few-shot Neural Radiance Field with Joint Monocular Depth Adaptation
Jiuhn Song; Seonghoon Park; Honggyu An; Seokju Cho; Min-Seop Kwak; Sungjin Cho; Seungryong Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Employing monocular depth estimation (MDE) networks, pretrained on large-scale RGB-D datasets, with powerful generalization capability may be a key to solving this problem: however, using MDE in conjunction with NeRF comes with a new set of challenges due to various ambiguity problems exhibited by monocular depths. In this light, we propose a novel framework, dubbed DäRF, that achieves robust NeRF reconstruction with a handful of real-world images by combining the strengths of NeRF and monocular depth estimation through online complementary training.
1808, Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement
Jinbiao Chen; Zizhen Zhang; Zhiguang Cao; Yaoxin Wu; Yining Ma; Te Ye; Jiahai Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: On the one hand, to hinder duplicated solutions for different subproblems, we propose an indicator-enhanced deep reinforcement learning method to guide the model, and design a heterogeneous graph attention mechanism to capture the relations between the instance graph and the Pareto front graph.
1809, Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural K-Opt
Yining Ma; Zhiguang Cao; Yeow Meng Chee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present Neural k-Opt (NeuOpt), a novel learning-to-search (L2S) solver for routing problems.
1810, FedFed: Feature Distillation Against Data Heterogeneity in Federated Learning
Zhiqin Yang; Yonggang Zhang; Yu Zheng; Xinmei Tian; Hao Peng; Tongliang Liu; Bo Han;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Sharing clients' information has shown great potentiality in mitigating data heterogeneity, yet incurs a dilemma in preserving privacy and promoting model performance. To alleviate the dilemma, we raise a fundamental question: Is it possible to share partial features in the data to tackle data heterogeneity?In this work, we give an affirmative answer to this question by proposing a novel approach called **Fed**erated **Fe**ature **d**istillation (FedFed).
1811, Continuous Parametric Optical Flow
Jianqin Luo; Zhexiong Wan; yuxin mao; Bo Li; Yuchao Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present continuous parametric optical flow, a parametric representation of dense and continuous motion over \emph{arbitrary time interval}.
1812, HyTrel: Hypergraph-enhanced Tabular Data Representation Learning
Pei Chen; Soumajyoti Sarkar; Leonard Lausen; Balasubramaniam Srinivasan; Sheng Zha; Ruihong Huang; George Karypis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, many of these models do not take into account the row/column permutation invariances, hierarchical structure, etc. that exist in tabular data. To alleviate these limitations, we propose HyTrel, a tabular language model, that captures the permutation invariances and three more structural properties of tabular data by using hypergraphs--where the table cells make up the nodes and the cells occurring jointly together in each row, column, and the entire table are used to form three different types of hyperedges.
1813, Training Neural Operators to Preserve Invariant Measures of Chaotic Attractors
Ruoxi Jiang; Peter Y. Lu; Elena Orlova; Rebecca Willett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an alternative framework designed to preserve invariant measures of chaotic attractors that characterize the time-invariant statistical properties of the dynamics.
1814, StableFDG: Style and Attention Based Learning for Federated Domain Generalization
Jungwuk Park; Dong-Jun Han; Jinho Kim; Shiqiang Wang; Christopher Brinton; Jaekyun Moon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose StableFDG, a \textit{style and attention based learning strategy} for accomplishing federated domain generalization, introducing two key contributions. The first is style-based learning, which enables each client to explore novel styles beyond the original source domains in its local dataset, improving domain diversity based on the proposed style sharing, shifting, and exploration strategies.
1815, Cookie Consent Has Disparate Impact on Estimation Accuracy
Erik Miehling; Rahul Nair; Elizabeth Daly; Karthikeyan Natesan Ramamurthy; Robert Redmond;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Is the impact of a user's consent decision on the recommender system's ability to learn about their latent attributes uniform across demographics? We investigate these questions in the context of an engagement-driven recommender system using simulation.
1816, Iterative Reachability Estimation for Safe Reinforcement Learning
Milan Ganai; Zheng Gong; Chenning Yu; Sylvia Herbert; Sicun Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new framework, Reachability Estimation for Safe Policy Optimization (RESPO), for safety-constrained RL in general stochastic settings.
1817, Fractal Landscapes in Policy Optimization
Tao Wang; Sylvia Herbert; Sicun Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a framework for understanding one inherent limitation of the policy gradient approach: the optimization landscape in the policy space can be extremely non-smooth or fractal, so that there may not be gradients to estimate in the first place.
1818, Towards Optimal Effective Resistance Estimation
Rajat Vadiraj Dwaraknath; Ishani Karmarkar; Aaron Sidford;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide new algorithms and conditional hardness for the problem of estimating effective resistances in $n$-node $m$-edge undirected, expander graphs.
1819, Fixing The NTK: From Neural Network Linearizations to Exact Convex Programs
Rajat Vadiraj Dwaraknath; Tolga Ergen; Mert Pilanci;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The latter research direction also yielded an alternative formulation of the ReLU network, called a gated ReLU network, that is globally optimizable via efficient unconstrained convex programs. In this work, we interpret the convex program for this gated ReLU network as a Multiple Kernel Learning (MKL) model with a weighted data masking feature map and establish a connection to the NTK.
1820, REFINE: A Fine-Grained Medication Recommendation System Using Deep Learning and Personalized Drug Interaction Modeling
Suman Bhoi; Mong Li Lee; Wynne Hsu; Ngiap Chuan Tan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a deep learning-based fine-grained medication recommendation system called REFINE, which is designed to improve treatment outcomes and minimize adverse drug interactions.
1821, Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning
Yue Tan; Chen Chen; Weiming Zhuang; Xin Dong; Lingjuan Lyu; Guodong Long;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To explore the possibility of using inter-client heterogeneity in handling intra-client heterogeneity, we firstly propose a contrastive learning-based FL framework, namely FedICON, to capture invariant knowledge among heterogeneous clients and consistently tune the model to adapt to test data.
1822, Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis
Zhu Wang; Sourav Medya; Sathya Ravi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, it is still unclear how domain or prior modal knowledge can be specified in a backpropagation friendly manner, especially in large-scale and noisy settings. To address these challenges, we propose a simplified alternative of combining features from pretrained deep networks and freely available semantic explicit knowledge.
1823, Mitigating The Effect of Incidental Correlations on Part-based Learning
Gaurav Bhatt; Deepayan Das; Leonid Sigal; Vineeth N Balasubramanian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study asserts that part-based representations could be more interpretable and generalize better with limited data, employing two innovative regularization methods.
1824, Learning Linear Causal Representations from Interventions Under General Nonlinear Mixing
Simon Buchholz; Goutham Rajendran; Elan Rosenfeld; Bryon Aragam; Bernhard Schölkopf; Pradeep Ravikumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of learning causal representations from unknown, latent interventions in a general setting, where the latent distribution is Gaussian but the mixing function is completely general.
1825, OpenDataVal: A Unified Benchmark for Data Valuation
Kevin Jiang; Weixin Liang; James Zou; Yongchan Kwon;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce *OpenDataVal*, an easy-to-use and unified benchmark framework that empowers researchers and practitioners to apply and compare various data valuation algorithms.
1826, Analyzing Generalization of Neural Networks Through Loss Path Kernels
Yilan Chen; Wei Huang; Hao Wang; Charlotte Loh; Akash Srivastava; Lam Nguyen; Lily Weng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the generalization capability of neural networks trained with (stochastic) gradient descent.
1827, Collaboratively Learning Linear Models with Structured Missing Data
Chen Cheng; Gary Cheng; John Duchi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our goal is to determine how to coordinate the agents in order to produce the best estimator for each agent.
1828, Arbitrariness Lies Beyond The Fairness-Accuracy Frontier
Carol Long; Hsiang Hsu; Wael Alghamdi; Flavio Calmon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We argue that a third axis of ``arbitrariness'' should be considered when deploying models to aid decision-making in applications of individual-level impact. To address this challenge, we propose an ensemble algorithm applicable to any fairness intervention that provably ensures more consistent predictions.
1829, AQuA: A Benchmarking Tool for Label Quality Assessment
Mononito Goswami; Vedant Sanil; Arjun Choudhry; Arvind Srinivasan; Chalisa Udompanyawit; Artur Dubrawski;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we propose a benchmarking environment _AQuA_ to rigorously evaluate methods that enable machine learning in the presence of label noise.
1830, Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games
Youbang Sun; Tao Liu; Ruida Zhou; P. R. Kumar; Shahin Shahrampour;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Abstract: This work studies an independent natural policy gradient (NPG) algorithm for the multi-agent reinforcement learning problem in Markov potential games. It is shown that, under mild ...
1831, Federated Linear Bandits with Finite Adversarial Actions
Li Fan; Ruida Zhou; Chao Tian; Cong Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the unique challenges of *adversarial finite* action sets, we propose the FedSupLinUCB algorithm, which extends the SupLinUCB and OFUL principles in linear contextual bandits.
1832, DISCS: A Benchmark for Discrete Sampling
Katayoon Goshvadi; Haoran Sun; Xingchao Liu; Azade Nova; Ruqi Zhang; Will Grathwohl; Dale Schuurmans; Hanjun Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, two key challenges seriously hinder the further research of discrete sampling. First, since there is no consensus for the experimental setting, the empirical results in different research papers are often not comparable. Secondly, implementing samplers and target distributions often require nontrivial amount of effort in terms of calibration, parallelism, and evaluation. To tackle these challenges, we propose \emph{DISCS} (DISCrete Sampling), a tailored package and benchmark that supports unified and efficient implementation and evaluations for discrete sampling from three types of tasks, namely the sampling for classical graphical models, combinatorial optimization, and energy based generative models.
1833, [Re] Exploring The Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification
Priyanka Bose; Chandra shekhar Pandey; Fraida Fund;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We aim to reproduce a result from the paper �Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification� [1].
1834, LaFTer: Label-Free Tuning of Zero-shot Classifier Using Language and Unlabeled Image Collections
Muhammad Jehanzeb Mirza; Leonid Karlinsky; Wei Lin; Horst Possegger; Mateusz Kozinski; Rogerio Feris; Horst Bischof;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, despite these great advances, the performance of these zero-shot classifiers still falls short of the results of dedicated (closed category set) classifiers trained with supervised fine-tuning. In this paper we show, for the first time, how to reduce this gap without any labels and without any paired VL data, using an unlabeled image collection and a set of texts auto-generated using a Large Language Model (LLM) describing the categories of interest and effectively substituting labeled visual instances of those categories.
1835, Deep Recurrent Optimal Stopping
Niranjan Damera Venkata; Chiranjib Bhattacharyya;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we present two new and different perspectives on the optimal stopping problem that do not require the WBE.
1836, On Private and Robust Bandits
Yulian Wu; Xingyu Zhou; Youming Tao; Di Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study private and robust multi-armed bandits (MABs), where the agent receives Huber's contaminated heavy-tailed rewards and meanwhile needs to ensure differential privacy.
1837, Learning Via Look-Alike Clustering: A Precise Analysis of Model Generalization
Adel Javanmard; Vahab Mirrokni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore a natural technique called look-alike clustering, which involves replacing sensitive features of individuals with the cluster's average values.
1838, On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
Rajat Modi; Vibhav Vineet; Yogesh Rawat;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we investigate the impact of occlusions on video action detection.
1839, Context Shift Reduction for Offline Meta-Reinforcement Learning
Yunkai Gao; Rui Zhang; Jiaming Guo; Fan Wu; Qi Yi; Shaohui Peng; Siming Lan; Ruizhi Chen; Zidong Du; Xing Hu; Qi Guo; Ling Li; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets.
1840, Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
Siming Lan; Rui Zhang; Qi Yi; Jiaming Guo; Shaohui Peng; Yunkai Gao; Fan Wu; Ruizhi Chen; Zidong Du; Xing Hu; xishan zhang; Ling Li; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In addition, these methods do not take into account that without constraints, some modules may learn similar functions, resulting in restricting the model's expressiveness and generalization capability of modular methods. In this paper, we propose the Contrastive Modules with Temporal Attention(CMTA) method to address these limitations.
1841, Deep Learning with Kernels Through RKHM and The Perron-Frobenius Operator
Yuka Hashimoto; Masahiro Ikeda; Hachem Kadri;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Reproducing kernel Hilbert $C^*$-module (RKHM) is a generalization of reproducing kernel Hilbert space (RKHS) by means of $C^*$-algebra, and the Perron-Frobenius operator is a linear operator related to the composition of functions. Combining these two concepts, we present deep RKHM, a deep learning framework for kernel methods.
1842, Incentivized Communication for Federated Bandits
Zhepei Wei; Chuanhao Li; Haifeng Xu; Hongning Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Negligence of such self-interested behaviors can significantly affect the learning efficiency and even the practical operability of federated bandit learning. In light of this, we aim to spark new insights into this under-explored research area by formally introducing an incentivized communication problem for federated bandits, where the server shall motivate clients to share data by providing incentives.
1843, Physion++: Evaluating Physical Scene Understanding That Requires Online Inference of Different Physical Properties
Hsiao-Yu Tung; Mingyu Ding; Zhenfang Chen; Daniel Bear; Chuang Gan; Josh Tenenbaum; Dan Yamins; Judith Fan; Kevin Smith;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work proposes a novel dataset and benchmark, termed Physion++, that rigorously evaluates visual physical prediction in artificial systems under circumstances where those predictions rely on accurate estimates of the latent physical properties of objects in the scene.
1844, You Only Condense Once: Two Rules for Pruning Condensed Datasets
Yang He; Lingao Xiao; Joey Tianyi Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these scenarios have two significant challenges: 1) the varying computational resources available on the devices require a dataset size different from the pre-defined condensed dataset, and 2) the limited computational resources often preclude the possibility of conducting additional condensation processes. We introduce You Only Condense Once (YOCO) to overcome these limitations.
1845, SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
Lijun Yu; Yong Cheng; Zhiruo Wang; Vivek Kumar; Wolfgang Macherey; Yanping Huang; David Ross; Irfan Essa; Yonatan Bisk; Ming-Hsuan Yang; Kevin Murphy; Alexander Hauptmann; Lu Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos.
1846, AIMS: All-Inclusive Multi-Level Segmentation
Lu Qi; Jason Kuen; Weidong Guo; Jiuxiang Gu; Zhe Lin; Bo Du; Yu Xu; Ming-Hsuan Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a new task, All-Inclusive Multi-Level Segmentation (AIMS), which segments visual regions into three levels: part, entity, and relation (two entities with some semantic relationships).
1847, Task-Robust Pre-Training for Worst-Case Downstream Adaptation
Jianghui Wang; Yang Chen; Xingyu Xie; Cong Fang; Zhouchen Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper considers pre-training a model that guarantees a uniformly good performance over the downstream tasks.
1848, OneNet: Enhancing Time Series Forecasting Models Under Concept Drift By Online Ensembling
yifan zhang; Qingsong Wen; xue wang; Weiqi Chen; Liang Sun; Zhang Zhang; Liang Wang; Rong Jin; Tieniu Tan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Many algorithms are designed for online time series forecasting, with some exploiting cross-variable dependency while others assume independence among variables. Given every data assumption has its own pros and cons in online time series modeling, we propose **On**line **e**nsembling **Net**work (**OneNet**).
1849, Smoothed Analysis of Sequential Probability Assignment
Alankrita Bhatt; Nika Haghtalab; Abhishek Shetty;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study information-theoretically optimal minmax rates as well as a framework for algorithmic reduction involving the maximum likelihood estimator oracle.
1850, Progressive Knowledge Distillation: Constructing Ensembles for Efficient Inference
Don Dennis; Abhishek Shetty; Anish Prasad Sevekari; Kazuhito Koishida; Virginia Smith;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we study the problem of progressive distillation: Given a large, pretrained teacher model , we seek to decompose the model into an ensemble of smaller, low-inference cost student models .
1851, Adversarial Resilience in Sequential Prediction Via Abstention
Surbhi Goel; Steve Hanneke; Shay Moran; Abhishek Shetty;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: On the other hand, assuming fully adversarial data leads to very pessimistic bounds that are often vacuous in practice. To capture this motivation, we propose a new model of sequential prediction that sits between the purely stochastic and fully adversarial settings by allowing the learner to abstain from making a prediction at no cost on adversarial examples.
1852, On Convergence of Polynomial Approximations to The Gaussian Mixture Entropy
Caleb Dahlke; Jason Pacheco;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide new analysis of a widely used approach due to Huber et al.(2008) and show that the series diverges under simple conditions.
1853, A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset
Zahra Gharaee; ZeMing Gong; Nicholas Pellegrino; Iuliia Zarubiieva; Joakim Bruslund Haurum; Scott Lowe; Jaclyn McKeown; Chris Ho; Joschka McLeod; Yi-Yun Wei; Jireh Agda; Sujeevan Ratnasingham; Dirk Steinke; Angel Chang; Graham Taylor; Paul Fieguth;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In an effort to catalog insect biodiversity, we propose a new large dataset of hand-labelled insect images, the BIOSCAN-1M Insect Dataset.
1854, Nearly Optimal Bounds for Cyclic Forgetting
William Swartworth; Deanna Needell; Rachel Ward; Mark Kong; Halyun Jeong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide theoretical bounds on the forgetting quantity in the continual learning setting for linear tasks, where each round of learning corresponds to projecting onto a linear subspace.
1855, Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm
Jie Hao; Kaiyi Ji; Mingrui Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Several works consider other formulations to address this issue, but they ignore the nested nature of bilevel optimization problems and may not solve the bilevel coreset selection problem accurately. To address these issues, we propose a new bilevel formulation, where the inner problem tries to find a model which minimizes the expected training error sampled from a given probability distribution, and the outer problem aims to learn the probability distribution with approximately $K$ (coreset size) nonzero entries such that learned model in the inner problem minimizes the training error over the whole data.
1856, Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds
Michael Crawshaw; Yajie Bao; Mingrui Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This problem is motivated by empirical evidence that the class of relaxed smooth functions, where the Lipschitz constant of the gradient scales linearly with the gradient norm, closely resembles the loss functions of certain neural networks such as recurrent neural networks (RNNs) with possibly exploding gradient. We introduce EPISODE++, the first algorithm to solve this problem.
1857, Global Convergence Analysis of Local SGD for One-hidden-layer Convolutional Neural Network Without Overparameterization
Yajie Bao; Amarda Shehu; Mingrui Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we provide the first global convergence analysis of the vanilla local SGD for one-hidden-layer convolutional neural networks \emph{without overparameterization} and \textit{without injecting noise}, when the input data is Gaussian.
1858, Characterizing The Impacts of Semi-supervised Learning for Weak Supervision
Jeffrey Li; Jieyu Zhang; Ludwig Schmidt; Alexander Ratner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we define a simple, modular design space to study the use of SSL techniques for WS more systematically.
1859, OpenGSL: A Comprehensive Benchmark for Graph Structure Learning
Zhou Zhiyao; Sheng Zhou; Bochao Mao; Xuanyi Zhou; Jiawei Chen; Qiaoyu Tan; Daochen Zha; Can Wang; Yan Feng; Chun Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite the proposal of numerous GSL methods, the progress in this field remains unclear due to inconsistent experimental protocols, including variations in datasets, data processing techniques, and splitting strategies. In this paper, we introduce OpenGSL, the first comprehensive benchmark for GSL, aimed at addressing this gap.
1860, Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning
Yihang Yao; ZUXIN LIU; Zhepeng Cen; Jiacheng Zhu; Wenhao Yu; Tingnan Zhang; DING ZHAO;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we formulate the versatile safe RL problem and consider two primary requirements: training efficiency and zero-shot adaptation capability.
1861, Emergence of Shape Bias in Convolutional Neural Networks Through Activation Sparsity
Tianqin Li; Ziqi Wen; Yangfan Li; Tai Sing Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we report that sparse coding, a ubiquitous principle in the brain, can in itself introduce shape bias into the network.
1862, Pairwise Causality Guided Transformers for Event Sequences
Xiao Shou; Debarun Bhattacharjya; Tian Gao; Dharmashankar Subramanian; Oktie Hassanzadeh; Kristin P Bennett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel approach for enhancing the performance of transformer-based models in multivariate event sequences by injecting pairwise qualitative causal knowledge such as `event Z amplifies future occurrences of event Y'.
1863, H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets
Guanqiang Zhou; Ping Xu; Yue Wang; Zhi Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Accordingly, we propose a fair and robust framework called H-nobs which can offer certified fairness and robustness through the adoption of two key components, a fairness-promoting objective function and a simple robust aggregation scheme called norm-based screening (NBS).
1864, Equitable Model Valuation with Black-box Access
Xinyi Xu; Thanh Lam; Chuan Sheng Foo; Bryan Kian Hsiang Low;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By exploiting a Dirichlet abstraction of a model's predictions, we propose a novel and equitable model valuation method called model Shapley.
1865, Zero-shot Causal Learning
Hamed Nilforoshan; Michael Moor; Yusuf Roohani; Yining Chen; Anja Šurina; Michihiro Yasunaga; Sara Oblak; Jure Leskovec;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose CaML, a causal meta-learning framework which formulates the personalized prediction of each intervention's effect as a task.
1866, Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback
Minyoung Hwang; Gunmin Lee; Hogun Kee; Chan Woo Kim; Kyungjae Lee; Songhwai Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing RLHF models are considered inefficient as they produce only a single preference data from each human feedback. To tackle this problem, we propose a novel RLHF framework called SeqRank, that uses sequential preference ranking to enhance the feedback efficiency.
1867, Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach
Sangwoong Yoon; Young-Uk Jin; Yung-Kyun Noh; Frank Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new method of training energy-based models (EBMs) for anomaly detection that leverages low-dimensional structures within data.
1868, Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision
Jiaxin Zhang; Zhuohang Li; Kamalika Das; Sricharan Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel Interactive Multi-Fidelity Learning (IMFL) framework for cost-effective development of small domain-specific LMs under limited annotation budgets.
1869, Online Clustering of Bandits with Misspecified User Models
Zhiyong Wang; Jize Xie; Xutong Liu; Shuai Li; John C.S. Lui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we are the first to present the important problem of clustering of bandits with misspecified user models (CBMUM), where the expected rewards in user models can be perturbed away from perfect linear models.
1870, Stability of Random Forests and Coverage of Random-Forest Prediction Intervals
Yan Wang; Huaiqing Wu; Dan Nettleton;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate stability of random forests under the mild condition that the squared response ($Y^2$) is light-tailed.
1871, Multi-Fidelity Multi-Armed Bandits Revisited
Xuchuang Wang; Qingyun Wu; Wei Chen; John C.S. Lui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For $\texttt{BAI}$, we present (a) a cost complexity lower bound, (b) an algorithmic framework with two alternative fidelity selection procedures,and (c) both procedures' cost complexity upper bounds.
1872, One-Step Diffusion Distillation Via Deep Equilibrium Models
Zhengyang Geng; Ashwini Pokle; J. Zico Kolter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a simple yet effective means of distilling diffusion models *directly* from the initial noise to the resulting image.
1873, Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
Ziheng Cheng; Shiyue Zhang; Longlin Yu; Cheng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a ParVI framework, called generalized Wasserstein gradient descent (GWG), based on a generalized Wasserstein gradient flow of the KL divergence, which can be viewed as a functional gradient method with a broader class of regularizers induced by convex functions.
1874, Online Constrained Meta-Learning: Provable Guarantees for Generalization
Siyuan Xu; Minghui Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes an online constrained meta-learning framework, which continuously learns from sequential learning tasks, and the learning tasks are subject to hard constraints.
1875, Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking
Mohammad Mahdi Kamani; Yuhang Yao; Hanjia Lyu; Zhongwei Cheng; Lin Chen; Liangju Li; Carlee Joe-Wong; Jiebo Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These datasets are essential for developing and evaluating intelligent algorithms that can effectively recommend rules for automating processes while preserving the privacy of the users, as it involves personal information about users' daily lives. To bridge this gap, we present Wyze Rule Dataset, a large-scale dataset designed specifically for smart home rule recommendation research.
1876, FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks
Yuhang Yao; Weizhao Jin; Srivatsan Ravi; Carlee Joe-Wong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the Federated Graph Convolutional Network (FedGCN) algorithm, which uses federated learning to train GCN models for semi-supervised node classification with fast convergence and little communication.
1877, Inverse Reinforcement Learning with The Average Reward Criterion
Feiyang Wu; Jingyang Ke; Anqi Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Equipped with SPMD, we propose the Inverse Policy Mirror Descent (IPMD) method for solving the IRL problem with a $\mathcal{O}(1/\varepsilon^2)$ complexity.
1878, RanPAC: Random Projections and Pre-trained Models for Continual Learning
Mark McDonnell; Dong Gong; Amin Parvaneh; Ehsan Abbasnejad; Anton van den Hengel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a concise and effective approach for CL with pre-trained models.
1879, On Sparse Modern Hopfield Model
Jerry Yao-Chieh Hu; Donglin Yang; Dennis Wu; Chenwei Xu; Bo-Yu Chen; Han Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the sparse modern Hopfield model as a sparse extension of the modern Hopfield model.
1880, Breadcrumbs to The Goal: Supervised Goal Selection from Human-in-the-Loop Feedback
Marcel Torne Villasevil; Max Balsells I Pamies; Zihan Wang; Samedh Desai; Tao Chen; Pulkit Agrawal; Abhishek Gupta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a technique - Human Guided Exploration (HUGE), that is able to leverage low-quality feedback from non-expert users, which is infrequent, asynchronous and noisy, to guide exploration for reinforcement learning, without requiring careful reward specification.
1881, The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning
Kaiwen Wang; Kevin Zhou; Runzhe Wu; Nathan Kallus; Wen Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we provide one explanation for the benefits of distributional RL through the lens of small-loss bounds, which scale with the instance-dependent optimal cost.
1882, Selective Sampling and Imitation Learning Via Online Regression
Ayush Sekhari; Karthik Sridharan; Wen Sun; Runzhe Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, in this work, we provide an interactive algorithm for IL that uses selective sampling to actively query the noisy expert for feedback.
1883, Network Regression with Graph Laplacians
Yidong Zhou; Hans-Georg Müller;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here we propose to adopt conditional Fréchet means implemented as M-estimators that depend on weights derived from both global and local least squares regression, extending the Fréchet regression framework to networks that are quantified by their graph Laplacians.
1884, Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance
Jiaming Qiu; Xiongtao Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We model the observed similarity measures as noisy responses generated from a function of the intrinsic geodesic distance between data points. A new local regression approach is proposed to learn the Riemannian metric tensor and its derivatives based on a Taylor expansion for the squared geodesic distances, accommodating different types of data such as continuous, binary, or comparative responses.
1885, LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees
Shangyuan LIU; Linglingzhi Zhu; Anthony Man-Cho So;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: More critically, it may suffer from infeasibility as an optimization problem. In this paper, we introduce the first condition that ensures the infeasibility of rSpecT and design a novel model called LogSpecT, along with its practical formulation rLogSpecT to overcome this issue.
1886, PAPR: Proximity Attention Point Rendering
Shichong Peng; Yanshu Zhang; Alireza Moazeni; Ke Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing point-based methods often suffer from the vanishing gradient problem or require a large number of points to accurately model scene geometry and texture. To address these limitations, we propose Proximity Attention Point Rendering (PAPR), a novel method that consists of a point-based scene representation and a differentiable renderer.
1887, Responsible AI (RAI) Games and Ensembles
Yash Gupta; Runtian Zhai; Arun Suggala; Pradeep Ravikumar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In these problems, a learner seeks to minimize its worst-case loss over a set of predefined distributions. In this work, we provide a general framework for studying these problems, which we refer to as \emph{Responsible AI (RAI) games}.
1888, Hierarchical Gaussian Mixture Based Task Generative Model for Robust Meta-Learning
Yizhou Zhang; Jingchao Ni; Wei Cheng; Zhengzhang Chen; Liang Tong; Haifeng Chen; Yan Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While tasks could come from varying distributions in reality, most of the existing meta-learning methods consider both training and testing tasks as from the same uni-component distribution, overlooking two critical needs of a practical solution: (1) the various sources of tasks may compose a multi-component mixture distribution, and (2) novel tasks may come from a distribution that is unseen during meta-training. In this paper, we demonstrate these two challenges can be solved jointly by modeling the density of task instances.
1889, Teaching Cars to See in A Day: Unsupervised Object Discovery with Reward Fine-tuning
Katie Luo; Zhenzhen Liu; Xiangyu Chen; Yurong You; Sagie Benaim; Cheng Perng Phoo; Mark Campbell; Wen Sun; Bharath Hariharan; Kilian Weinberger;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose to adapt similar RL-based methods to unsupervised object discovery, i.e. learning to detect objects from LiDAR points without any training labels.
1890, Sparsity-Preserving Differentially Private Training
Badih Ghazi; Yangsibo Huang; Pritish Kamath; Ravi Kumar; Pasin Manurangsi; Amer Sinha; Chiyuan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, applying DP-SGD naively to embedding models can destroy gradient sparsity, leading to reduced training efficiency. To address this issue, we present two new algorithms, DP-FEST and DP-AdaFEST, that preserve gradient sparsity during private training of large embedding models.
1891, Optimal Unbiased Randomizers for Regression with Label Differential Privacy
Ashwinkumar Badanidiyuru Varadaraja; Badih Ghazi; Pritish Kamath; Ravi Kumar; Ethan Leeman; Pasin Manurangsi; Avinash V Varadarajan; Chiyuan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new family of label randomizers for training _regression_ models under the constraint of label differential privacy (DP).
1892, User-Level Differential Privacy With Few Examples Per User
Badih Ghazi; Pritish Kamath; Ravi Kumar; Pasin Manurangsi; Raghu Meka; Chiyuan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: - For pure-DP, we present a simple technique for adapting the ubiquitous exponential mechanism [McSherry & Talwar, FOCS 2007] to the user-level setting.
1893, Coupled Reconstruction of Cortical Surfaces By Diffeomorphic Mesh Deformation
Hao Zheng; Hongming Li; Yong Fan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To robustly reconstruct the cortical surfaces with topological correctness, we develop a new deep learning-based framework to jointly reconstruct the inner, outer, and their in-between (midthickness) surfaces and estimate cortical thickness directly from 3D MRIs.
1894, Discovering Hierarchical Achievements in Reinforcement Learning Via Contrastive Learning
Seungyong Moon; Junyoung Yeom; Bumsoo Park; Hyun Oh Song;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we identify that proximal policy optimization (PPO), a simple and versatile model-free algorithm, outperforms the prior methods with recent implementation practices.
1895, Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards
Mengfan Xu; Diego Klabjan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study a decentralized multi-agent multi-armed bandit problem in which multiple clients are connected by time dependent random graphs provided by an environment.
1896, Exposing Flaws of Generative Model Evaluation Metrics and Their Unfair Treatment of Diffusion Models
George Stein; Jesse Cresswell; Rasa Hosseinzadeh; Yi Sui; Brendan Ross; Valentin Villecroze; Zhaoyan Liu; Anthony Caterini; Eric Taylor; Gabriel Loaiza-Ganem;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We systematically study a wide variety of image-based generative models spanning semantically-diverse datasets to understand and improve the feature extractors and metrics used to evaluate them.
1897, Long-Term Fairness with Unknown Dynamics
Tongxin Yin; Reilly Raab; Mingyan Liu; Yang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we formalize long-term fairness in the context of online reinforcement learning.
1898, Demo2Code: From Summarizing Demonstrations to Synthesizing Code Via Extended Chain-of-Thought
Yuki Wang; Gonzalo Gonzalez-Pumariega; Yash Sharma; Sanjiban Choudhury;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents Demo2Code, a novel framework that generates robot task code from demonstrations via an extended chain-of-thought and defines a common latent specification to connect the two.
1899, CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches
Phoenix Williams; Ke Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing methods often produce clearly visible distortions since they do not consider the visibility of the patch. To address this, we propose a novel method for constructing adversarial patches that approximates the appearance of the area it covers.
1900, “Why Not Looking Backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
Shuang Li; Ke Li; Wei Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple, yet theoretically grounded, two-step method for automatically terminating BO.
1901, Change Point Detection and Inference in Multivariate Non-parametric Models Under Mixing Conditions
Carlos Misael Madrid Padilla; Haotian Xu; Daren Wang; OSCAR HERNAN MADRID PADILLA; Yi Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the limiting distributions of the change point estimators under the scenarios where the minimal jump size vanishes or remains constant.
1902, Neural Lighting Simulation for Urban Scenes
Ava Pun; Gary Sun; Jingkang Wang; Yun Chen; Ze Yang; Sivabalan Manivasagam; Wei-Chiu Ma; Raquel Urtasun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Different outdoor illumination conditions drastically alter the appearance of urban scenes, and can harm the performance of image-based robot perception systems if they have not been seen during training. Towards this goal, we propose LightSim, a neural lighting camera simulation system that enables diverse, realistic, and controllable data generation.
1903, AVIDa-hIL6: A Large-Scale VHH Dataset Produced from An Immunized Alpaca for Predicting Antigen-Antibody Interactions
Hirofumi Tsuruta; Hiroyuki Yamazaki; Ryota Maeda; Ryotaro Tamura; Jennifer Wei; Zelda Mariet; Poomarin Phloyphisut; Hidetoshi Shimokawa; Joseph R. Ledsam; Lucy Colwell; Akihiro Imura;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the publicly available datasets in existing works have notable limitations, such as small sizes and the lack of non-binding samples and exact amino acid sequences. To overcome these limitations, we have developed AVIDa-hIL6, a large-scale dataset for predicting antigen-antibody interactions in the variable domain of heavy chain of heavy chain antibodies (VHHs), produced from an alpaca immunized with the human interleukin-6 (IL-6) protein, as antigens.
1904, Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing ``Spurious'' Correlations
Qingyao Sun; Kevin Murphy; Sayna Ebrahimi; Alexander D'Amour;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we present a test-time adaptation method that exploits the spurious correlation phenomenon, in contrast to recent approaches that attempt to eliminate spurious correlations through invariance.
1905, VeriX: Towards Verified Explainability of Deep Neural Networks
Min Wu; Haoze Wu; Clark Barrett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present **VeriX** (**Veri**fied e**X**plainability), a system for producing *optimal robust explanations* and generating *counterfactuals* along decision boundaries of machine learning models.
1906, Model-Based Control with Sparse Neural Dynamics
Ziang Liu; Jeff He; Genggeng Zhou; Tobia Marcucci; Fei-Fei Li; Jiajun Wu; Yunzhu Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new framework for integrated model learning and predictive control that is amenable to efficient optimization algorithms.
1907, Information Geometry of The Retinal Representation Manifold
Xuehao Ding; Dongsoo Lee; Joshua Melander; George Sivulka; Surya Ganguli; Stephen Baccus;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we propose a novel framework for understanding stimulus discriminability achieved by retinal representations of naturalistic stimuli with the method of information geometry.
1908, Statistical Knowledge Assessment for Generative Language Models
Qingxiu Dong; Jingjing Xu; Lingpeng Kong; Zhifang Sui; Lei Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Given varying prompts, does a GLM consistently generate factually correct answers? In this paper, we introduce a statistical knowledge assessment framework guided by latent variables and the KaRR metric, which quantifies a model's knowledge by computing its continuous probability across diverse text forms.
1909, Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement
Hui Yuan; Kaixuan Huang; Chengzhuo Ni; Minshuo Chen; Mengdi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore the methodology and theory of reward-directed generation via conditional diffusion models.
1910, Unified Off-Policy Learning to Rank: A Reinforcement Learning Perspective
Zeyu Zhang; Yi Su; Hui Yuan; Yiran Wu; Rishab Balasubramanian; Qingyun Wu; Huazheng Wang; Mengdi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we unified the ranking process under general stochastic click models as a Markov Decision Process (MDP), and the optimal ranking could be learned with offline reinforcement learning (RL) directly.
1911, Online List Labeling with Predictions
Samuel McCauley; Ben Moseley; Aidin Niaparast; Shikha Singh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, incorporating predictions into data structures with strong theoretical guarantees remains underdeveloped. This paper takes a step in this direction by showing that predictions can be leveraged in the fundamental online list labeling problem.
1912, Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
Jan Dubiński; Stanisław Pawlak; Franziska Boenisch; Tomasz Trzcinski; Adam Dziedzic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose *Bucks for Buckets (B4B)*, the first *active defense* that prevents stealing while the attack is happening without degrading representation quality for legitimate API users.
1913, Learning Exponential Families from Truncated Samples
Jane Lee; Andre Wibisono; Emmanouil Zampetakis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A recent line of work provides the first efficient estimation algorithms for the parameters of a Gaussian distribution and for linear regression with Gaussian noise. In this paper we generalize these results to log-concave exponential families.
1914, SEENN: Towards Temporal Spiking Early Exit Neural Networks
Yuhang Li; Tamar Geller; Youngeun Kim; Priyadarshini Panda;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study a fine-grained adjustment of the number of timesteps in SNNs.
1915, Learning A 1-layer Conditional Generative Model in Total Variation
Ajil Jalal; Justin Kang; Ananya Uppal; Kannan Ramchandran; Eric Price;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Given samples $(x, y)$, we show how to learn a 1-layer ReLU conditional generative model in total variation.
1916, How Many Samples Are Needed to Leverage Smoothness?
Vivien Cabannes; Stefano Vigogna;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: By deriving a new lower bound on the generalization error, this paper investigates the role of constants and transitory regimes which are usually not depicted beyond classical learning theory statements while that play a dominant role in practice.
1917, Neural Lyapunov Control for Discrete-Time Systems
Junlin Wu; Andrew Clark; Yiannis Kantaros; Yevgeniy Vorobeychik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose the first approach for learning neural Lyapunov control in discrete-time systems.
1918, Exact Verification of ReLU Neural Control Barrier Functions
Hongchao Zhang; Junlin Wu; Yevgeniy Vorobeychik; Andrew Clark;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents novel exact conditions and algorithms for verifying safety of feedforward NCBFs with ReLU activation functions.
1919, A Partially-Supervised Reinforcement Learning Framework for Visual Active Search
Anindya Sarkar; Nathan Jacobs; Yevgeniy Vorobeychik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an approach that combines the strength of both DRL and conventional active search approaches by decomposing the search policy into a prediction module, which produces a geospatial distribution of regions of interest based on task embedding and search history, and a search module, which takes the predictions and search history as input and outputs the search distribution.
1920, Easy Learning from Label Proportions
Róbert Busa-Fekete; Heejin Choi; Travis Dick; Claudio Gentile; Andres Munoz Medina;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we propose EASYLLP, a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions.
1921, Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Nikki Lijing Kuang; Ming Yin; Mengdi Wang; Yu-Xiang Wang; Yian Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we tackle the challenge of delayed feedback (where the trajectory information is randomly delayed according to some unknown distribution) with linear function approximation.
1922, Prioritizing Samples in Reinforcement Learning with Reducible Loss
Shivakanth Sujit; Somjit Nath; Pedro Braga; Samira Ebrahimi Kahou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a method to prioritize samples based on how much we can learn from a sample.
1923, Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
Guanlin Liu; Lifeng LAI;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Due to the broad range of applications of multi-agent reinforcement learning (MARL), understanding the effects of adversarial attacks against MARL model is essential for the safe applications of this model. Motivated by this, we investigate the impact of adversarial attacks on MARL.
1924, Bayesian Learning Via Q-Exponential Process
Shuyi Li; Michael O'Connor; Shiwei Lan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we generalize the $q$-exponential distribution (with density proportional to) $\exp{(- \frac{1}{2}|u|^q)}$ to a stochastic process named \emph{$Q$-exponential (Q-EP) process} that corresponds to the $L_q$ regularization of functions.
1925, Guiding The Last Layer in Federated Learning with Pre-Trained Models
Gwen Legate; Nicolas Bernier; Lucas Page-Caccia; Edouard Oyallon; Eugene Belilovsky;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here we revisit the problem of FL from a pre-trained model considered in prior work and expand it to a set of computer vision transfer learning problems.
1926, A Heavy-Tailed Algebra for Probabilistic Programming
Feynman Liang; Liam Hodgkinson; Michael Mahoney;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the successes of probabilistic models based on passing noise through neural networks, recent work has identified that such methods often fail to capture tail behavior accurately---unless the tails of the base distribution are appropriately calibrated. To overcome this deficiency, we propose a systematic approach for analyzing the tails of random variables, and we illustrate how this approach can be used during the static analysis (before drawing samples) pass of a probabilistic programming language (PPL) compiler.
1927, Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration
Theo Adrai; Guy Ohayon; Michael Elad; Tomer Michaeli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose an image restoration algorithm that can control the perceptual quality and/or the mean square error (MSE) of any pre-trained model, trading one over the other at test time.
1928, Perceptual Kalman Filters: Online State Estimation Under A Perfect Perceptual-Quality Constraint
Dror Freirich; Tomer Michaeli; Ron Meir;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our analysis goes beyond the classic innovation process of the Kalman filter, and introduces the novel concept of an unutilized information process. Using this tool, we present a recursive formula for perceptual filters, and demonstrate the qualitative effects of perfect perceptual-quality estimation on a video reconstruction problem.
1929, Riemannian Stochastic Optimization Methods Avoid Strict Saddle Points
Ya-Ping Hsieh; Mohammad Reza Karimi Jaghargh; Andreas Krause; Panayotis Mertikopoulos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, in many cases of interest, the resulting minimization problem is _not_ geodesically convex, so the convergence of the chosen solver to a desirable solution - i.e., a local minimizer - is by no means guaranteed. In this paper, we study precisely this question, that is, whether stochastic Riemannian optimization algorithms are guaranteed to avoid saddle points with probability $1$.
1930, Stochastic Approximation Algorithms for Systems of Interacting Particles
Mohammad Reza Karimi Jaghargh; Ya-Ping Hsieh; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In practice, discrete time steps,finite particle numbers, and complex integration schemes are employed, creating a theoretical gapbetween continuous-time and discrete-time processes. In this paper, we present a novel frameworkthat establishes a precise connection between these discrete-time schemes and their correspondingmean-field limits in terms of convergence properties and asymptotic behavior.
1931, A Dynamical System View of Langevin-Based Non-Convex Sampling
Mohammad Reza Karimi Jaghargh; Ya-Ping Hsieh; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, little is known beyond the elementary schemes of stochastic gradient Langevin dynamics. To address these issues, we develop a novel framework that lifts the above issues by harnessing several tools from the theory of dynamical systems.
1932, 3D Molecule Generation By Denoising Voxel Grids
Pedro O. Pinheiro; Joshua Rackers; Joseph Kleinhenz; Michael Maser; Omar Mahmood; Andrew Watkins; Stephen Ra; Vishnu Sresht; Saeed Saremi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a new score-based approach to generate 3D molecules represented as atomic densities on regular grids.
1933, Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control
Xingang Guo; Darioush Keivan; Geir Dullerud; Peter Seiler; Bin Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These are built upon the concept of Goldstein subdifferential or other notions of enlarged subdifferential. In this paper, we study the complexity of finding $(\delta,\epsilon)$-stationary points for such nonsmooth robust control design tasks using policy optimization methods which can only access the zeroth-order oracle (i.e. the $\mathcal{H}_\infty$ norm of the closed-loop system).
1934, A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Guillaume Huguet; Alexander Tong; Edward De Brouwer; Yanlei Zhang; Guy Wolf; Ian Adelstein; Smita Krishnaswamy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While it is thought that these methods preserve underlying manifold structure of data by learning a proxy for geodesic distances, no specific theoretical links have been established. Here, we establish such a link via results in Riemannian geometry explicitly connecting heat diffusion to manifold distances.
1935, Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method
Constantine Caramanis; Dimitris Fotakis; Alkis Kalavasis; Vasilis Kontonis; Christos Tzamos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In those methods a deep neural network is used as a solution generator which is then trained by gradient-based methods (e.g., policy gradient) to successively obtain better solution distributions. In this work we introduce a novel theoretical framework for analyzing the effectiveness of such methods.
1936, A Computationally Efficient Sparsified Online Newton Method
Fnu Devvrit; Sai Surya Duvvuri; Rohan Anil; Vineet Gupta; Cho-Jui Hsieh; Inderjit Dhillon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce Sparsified Online Newton (SONew), a memory-efficient second-order algorithm that exploits specific sparsity patterns within the gradient second moment matrix.
1937, Globally Solving The Gromov-Wasserstein Problem for Point Clouds in Low Dimensional Euclidean Spaces
Martin Ryner; Jan Kronqvist; Johan Karlsson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a framework for computing the Gromov-Wasserstein problem between two sets of points in low dimensional spaces, where the discrepancy is the squared Euclidean norm.
1938, Action Inference By Maximising Evidence: Zero-Shot Imitation from Observation with World Models
Xingyuan Zhang; Philip Becker-Ehmck; Patrick van der Smagt; Maximilian Karl;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This ability highly depends on the fact that humans have a model of their own embodiment that allows them to infer the most likely actions that led to the observed behaviour. In this paper, we propose Action Inference by Maximising Evidence (AIME) to replicate this behaviour using world models.
1939, Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?
Yutong He; Xinmeng Huang; Kun Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we present the first theoretical formulation for characterizing the total communication cost in distributed optimization with communication compression.
1940, Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing
Shuyao Li; Yu Cheng; Ilias Diakonikolas; Jelena Diakonikolas; Rong Ge; Stephen Wright;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the problem of finding SOSPs in the strong contamination model, where a constant fraction of the datapoints are arbitrarily corrupted.
1941, Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning
Gen Li; Wenhao Zhan; Jason Lee; Yuejie Chi; Yuxin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Leveraging recent advances in reward-agnostic exploration and offline RL, we design a three-stage hybrid RL algorithm that beats the best of both worlds --- pure offline RL and pure online RL --- in terms of sample complexities.
1942, Equal Opportunity of Coverage in Fair Regression
Fangxin Wang; Lu Cheng; Ruocheng Guo; Kay Liu; Philip S Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Binned Fair Quantile Regression (BFQR), a distribution-free post-processing method to improve EOC with reasonable width for any trained ML models.
1943, Systematic Visual Reasoning Through Object-Centric Relational Abstraction
Taylor Webb; Shanka Subhra Mondal; Jonathan D Cohen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent work in computer vision has introduced models with the capacity to extract object-centric representations, leading to the ability to process multi-object visual inputs, but falling short of the systematic generalization displayed by human reasoning. Other recent models have employed inductive biases for relational abstraction to achieve systematic generalization of learned abstract rules, but have generally assumed the presence of object-focused inputs. Here, we combine these two approaches, introducing Object-centric Relational Abstraction (OCRA), a model that extracts explicit representations of both objects and abstract relations, and achieves strong systematic generalization in tasks involving complex visual displays.
1944, Recovering Unbalanced Communities in The Stochastic Block Model with Application to Clustering with A Faulty Oracle
Chandra Sekhar Mukherjee; Pan Peng; Jiapeng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide a simple SVD-based algorithm for recovering the communities in the SBM with communities of varying sizes.
1945, TabMT: Generating Tabular Data with Masked Transformers
Manbir Gulati; Paul Roysdon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present TabMT, a novel Masked Transformer architecture for generating synthetic tabular data.
1946, Unbiased Learning of Deep Generative Models with Structured Discrete Representations
Henry C Bendekgey; Gabe Hope; Erik Sudderth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose novel algorithms for learning SVAEs, and are the first to demonstrate the SVAE's ability to handle multimodal uncertainty when data is missing by incorporating discrete latent variables.
1947, IVRE: Interactive Visual Reasoning Under Uncertainty
Manjie Xu; Guangyuan Jiang; Wei Liang; Chi Zhang; Yixin Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we devise the IVRE (as ``ivory'') environment for evaluating artificial agents' reasoning ability under uncertainty.
1948, Conan: Active Reasoning in An Open-World Environment
Manjie Xu; Guangyuan Jiang; Wei Liang; Chi Zhang; Yixin Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead of merely being passively questioned and retrieving from a knowledge base, humans can actively respond, explore, gather, and reason from both the new and the known to derive a solution to incomplete-information questions. To fill in this paradoxically absent but critical gap, we introduce an interactive open-world environment, dubbed **Conan**, to motivate and evaluate agents for this active reasoning ability.
1949, Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction
Anagh Malik; Parsa Mirdehghan; Sotiris Nousias; Kyros Kutulakos; David Lindell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, previous lidar-supervised NeRFs focus on rendering conventional camera imagery and use lidar-derived point cloud data as auxiliary supervision; thus, they fail to incorporate the underlying image formation model of the lidar. Here, we propose a novel method for rendering transient NeRFs that take as input the raw, time-resolved photon count histograms measured by a single-photon lidar system, and we seek to render such histograms from novel views.
1950, Multi-Step Generalized Policy Improvement By Leveraging Approximate Models
Lucas N. Alegre; Ana Bazzan; Ann Nowe; Bruno da Silva;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a principled method for performing zero-shot transfer in reinforcement learning (RL) by exploiting approximate models of the environment.
1951, Adapting Fairness Interventions to Missing Values
Raymond Feng; Flavio Calmon; Hao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we analyze how missing values affect algorithmic fairness.
1952, Polyhedron Attention Module: Learning Adaptive-order Interactions
Tan Zhu; Fei Dou; Xinyu Wang; Jin Lu; Jinbo Bi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a Polyhedron Attention Module (PAM) to create piecewise polynomial models where the input space is split into polyhedrons which define the different pieces and on each piece the hyperplanes that define the polyhedron boundary multiply to form the interactive terms, resulting in interactions of adaptive order to each piece.
1953, FLuID: Mitigating Stragglers in Federated Learning Using Invariant Dropout
Irene Wang; Prashant Nair; Divya Mahajan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: As a result, “straggler” devices with lower performance often dictate the overalltraining time in FL. In this work, we aim to alleviate this performance bottleneck due to stragglers by dynamically balancing the training load across the system.
1954, DriveMax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
Cole Gulino; Justin Fu; Wenjie Luo; George Tucker; Eli Bronstein; Yiren Lu; Jean Harb; Xinlei Pan; Yan Wang; Xiangyu Chen; John Co-Reyes; Rishabh Agarwal; Rebecca Roelofs; Yao Lu; Nico Montali; Paul Mougin; Zoey Yang; Brandyn White; Aleksandra Faust; Rowan McAllister; Dragomir Anguelov; Benjamin Sapp;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, realistic simulation requires accurate modeling of multi-agent interactive behaviors to be trustworthy, behaviors which can be highly nuanced and complex. To address these challenges, we introduce DriveMax, a new data-driven simulator for autonomous driving in multi-agent scenes, designed for large-scale simulation and testing.
1955, Expressive Probabilistic Sampling in Recurrent Neural Networks
Shirui Chen; Linxing Jiang; Rajesh PN Rao; Eric Shea-Brown;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We call such circuits $\textit{reservoir-sampler networks}$ (RSNs). We propose an efficient training procedure based on denoising score matching that finds recurrent and output weights such that the RSN implements Langevin sampling.
1956, PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis
Ali TehraniJamsaz; Quazi Ishtiaque Mahmud; Le Chen; Nesreen K. Ahmed; Ali Jannesari;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To overcome the limitations and challenges of current program representations, we propose a novel graph-based program representation called PERFOGRAPH.
1957, Convolutional State Space Models for Long-Range Spatiotemporal Modeling
Jimmy Smith; Shalini De Mello; Jan Kautz; Scott Linderman; Wonmin Byeon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we address the challenges of prior methods and introduce convolutional state space models (ConvSSM) that combine the tensor modeling ideas of ConvLSTM with the long sequence modeling approaches of state space methods such as S4 and S5.
1958, Perceptual Adjustment Queries: An Inverted Measurement Paradigm for Low-rank Metric Learning
Austin Xu; Andrew McRae; Jingyan Wang; Mark Davenport; Ashwin Pananjady;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new type of informative and yet cognitively lightweight query mechanism for collecting human feedback, called the perceptual adjustment query (PAQ).
1959, Towards A Comprehensive Benchmark for FPGA Targeted High-Level Synthesis
Yunsheng Bai; Atefeh Sohrabizadeh; Zongyue Qin; Ziniu Hu; Yizhou Sun; Jason Cong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing open-source datasets for training such models are limited in terms of design complexity and available optimizations. In this paper, we present HLSyn, the first benchmark that addresses these limitations.
1960, Parallel-mentoring for Offline Model-based Optimization
Can Chen; Christopher Beckham; Zixuan Liu; Xue (Steve) Liu; Chris Pal;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores.
1961, Residual Alignment: Uncovering The Mechanisms of Residual Networks
Jianing Li; Vardan Papyan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this paper, we conduct a thorough empirical study of the ResNet architecture by linearizing its constituent residual blocks using Residual Jacobians and measuring their singular value decompositions.
1962, Text-to-Image Diffusion Model on Mobile Devices Within Two Seconds
Yanyu Li; Huan Wang; Qing Jin; Ju Hu; Pavlo Chemerys; Yun Fu; Yanzhi Wang; Sergey Tulyakov; Jian Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is costly and has privacy implications, especially when user data is sent to a third party. To overcome these challenges, we present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in less than two seconds.
1963, Anchor Data Augmentation
Nora Schneider; Shirin Goshtasbpour; Fernando Perez-Cruz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression.
1964, Are Vision Transformers More Data Hungry Than Newborn Visual Systems?
Lalit Pandey; Samantha Wood; Justin Wood;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, researchers question the value of using ViTs as models of biological learning because ViTs are thought to be more “data hungry” than brains, with ViTs requiring more training data than brains to reach similar levels of performance. To test this assumption, we directly compared the learning abilities of ViTs and animals, by performing parallel controlled-rearing experiments on ViTs and newborn chicks.
1965, Certification of Distributional Individual Fairness
Matthew Wicker; Vihari Piratla; Adrian Weller;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study formal guarantees, i.e., certificates, for individual fairness (IF) of neural networks.
1966, Use Perturbations When Learning from Explanations
Juyeon Heo; Vihari Piratla; Matthew Wicker; Adrian Weller;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We consider various approaches to achieving robustness, leading to improved performance over prior MLX methods.
1967, Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
Zhiqi Bu; Yu-Xiang Wang; Sheng Zha; George Karypis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose an easy-to-use replacement, called automatic clipping, that eliminates the need to tune $R$ for any DP optimizers, including DP-SGD, DP-Adam, DP-LAMB and many others.
1968, AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs
Adam Cobb; Anirban Roy; Daniel Elenius; Frederick Heim; Brian Swenson; Sydney Whittington; James Walker; Theodore Bapty; Joseph Hite; Karthik Ramani; Christopher McComb; Susmit Jha;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present AircraftVerse, a publicly available aerial vehicle design dataset.
1969, Tight Bounds for Volumetric Spanners and Applications
Aditya Bhaskara; Sepideh Mahabadi; Ali Vakilian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This notion, which has also been referred to as a well-conditioned basis, has found several applications, including bandit linear optimization, determinant maximization, and matrix low rank approximation. In this paper, we give almost optimal bounds on the size of volumetric spanners for all $\ell_p$ norms, and show that they can be constructed using a simple local search procedure.
1970, Core-sets for Fair and Diverse Data Summarization
Sepideh Mahabadi; Stojan Trajanovski;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We study core-set construction algorithms for the task of Diversity Maximization under fairness constraint.
1971, Learning Energy-based Model Via Dual-MCMC Teaching
Jiali Cui; Tian Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Such biased generator learning may limit the potential of learning the EBM. To address this issue, we present a joint learning framework that interweaves the maximum likelihood learning algorithm for both the EBM and the complementary generator model.
1972, StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on The Microcontroller
Hong-Sheng Zheng; Yu-Yuan Liu; Chen-Fong Hsu; Tsung Tai Yeh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work designs StreamNet that employs the stream buffer to eliminate the redundant computation of patch-based inference.
1973, Understanding The Detrimental Class-level Effects of Data Augmentation
Polina Kirichenko; Mark Ibrahim; Randall Balestriero; Diane Bouchacourt; Shanmukha Ramakrishna Vedantam; Hamed Firooz; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a framework for understanding how DA interacts with class-level learning dynamics.
1974, Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization
Yankun Huang; Qihang Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a non-convex constrained optimization problem, where the objective function is weakly convex and the constraint function is either convex or weakly convex.
1975, Learning Energy-Based Prior Model with Diffusion-Amortized MCMC
Peiyu Yu; Yaxuan Zhu; Sirui Xie; Xiaojian (Shawn) Ma; Ruiqi Gao; Song-Chun Zhu; Ying Nian Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress; the degenerate MCMC sampling quality in practice often leads to degraded generation quality and instability in training, especially with highly multi-modal and/or high-dimensional target distributions. To remedy this sampling issue, in this paper we introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it.
1976, Understanding Diffusion Objectives As The ELBO with Data Augmentation
Diederik Kingma; Ruiqi Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we expose a direct relationship between the weighted loss (with any weighting) and the ELBO objective.
1977, Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search
Indradyumna Roy; Rishi Agarwal; Soumen Chakrabarti; Anirban Dasgupta; Abir De;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we focus on data-sensitive, trainable indices for fast retrieval of relevant documents.
1978, Latent Diffusion for Language Generation
Justin Lovelace; Varsha Kishore; Chao Wan; Eliot Shekhtman; Kilian Weinberger;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We demonstrate that encoder-decoder language models can be utilized to efficiently learn high-quality language autoencoders. We then demonstrate that continuous diffusion models can be learned in the latent space of the language autoencoder, enabling us to sample continuous latent representations that can be decoded into natural language with the pretrained decoder.
1979, A Dual-Stream Neural Network Explains The Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains
Minkyu Choi; Kuan Han; Xiaokai Wang; Yizhen Zhang; Zhongming Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In contrast, computer vision systems tend to use a single feedforward pathway, rendering them less robust, adaptive, or efficient than human vision. To bridge this gap, we developed a dual-stream vision model inspired by the human eyes and brain.
1980, Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes
Ali Younis; Erik Sudderth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While prior discriminative particle filters have used heuristic relaxations of discrete particle resampling, or biased learning by truncating gradients at resampling steps, we achieve unbiased and low-variance gradient estimates by representing posteriors as continuous mixture densities.
1981, PDP: Parameter-free Differentiable Pruning Is All You Need
Minsik Cho; Saurabh Adya; Devang Naik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an efficient yet effective train-timepruning scheme, Parameter-free Differentiable Pruning (PDP), which offers state-of-the-art qualities in model size, accuracy, and training cost.
1982, In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer
Yuzhou Cao; Hussein Mozannar; Lei Feng; Hongxin Wei; Bo An;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we first show that the cause of the miscalibrated and unbounded estimator in prior literature is due to the symmetric nature of the surrogate losses used and not due to softmax. We then propose a novel statistically consistent asymmetric softmax-based surrogate loss that can produce valid estimates without the issue of unboundedness.
1983, Adapt to Adapt: A Tempo-control Framework for Non-stationary Reinforcement Learning
Hyunin Lee; Yuhao Ding; Jongmin Lee; Ming Jin; Javad Lavaei; Somayeh Sojoudi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a Proactive Tempo-control Model-based (\textbf{PTM}) framework that adjusts how many times the agent needs to update the policy (algorithm tempo) to how fast the environment changes (environment tempo).
1984, Causal Normalizing Flows: from Theory to Practice
Adrián Javaloy; Pablo Sanchez-Martin; Isabel Valera;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we deepen on the use of normalizing flows for causal reasoning.
1985, Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice
Dayou Yu; Weishi Shi; Qi Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel active testing while learning (ATL) framework that integrates active learning with active testing.
1986, Accelerating Molecular Graph Neural Networks Via Knowledge Distillation
Filip Ekström Kelvinius; Dimitar Georgiev; Artur Toshev; Johannes Gasteiger;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we, for the first time, explore the utility of knowledge distillation (KD) for accelerating molecular GNNs.
1987, Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness
Evgenii Chzhen; Christophe Giraud; Zhen LI; Gilles Stoltz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To that end, we introduce a dual strategy based on projected-gradient-descent updates, that is able to deal with total-cost constraints of the order of $\sqrt{T}$ up to poly-logarithmic terms.
1988, HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count
Noah Wiederhold; Ava Megyeri; DiMaggio Paris; Sean Banerjee; Natasha Banerjee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the HOH (Human-Object-Human) Handover Dataset, a large object count dataset with 136 objects, to accelerate data-driven research on handover studies, human-robot handover implementation, and artificial intelligence (AI) on handover parameter estimation from 2D and 3D data of person interactions.
1989, EgoEnv: Human-centric Environment Representations from Egocentric Video
Tushar Nagarajan; Santhosh Kumar Ramakrishnan; Ruta Desai; James Hillis; Kristen Grauman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To facilitate human-centric environment understanding, we present an approach that links egocentric video and the environment by learning representations that are predictive of the camera-wearer's (potentially unseen) local surroundings.
1990, Approximate Inference of Marginals Using The IBIA Framework
Shivani Bathla; Vinita Vasudevan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new algorithm for marginal inference that is based on the incremental build-infer-approximate (IBIA) paradigm.
1991, Operator Learning with Neural Fields: Tackling PDEs on General Geometries
Louis Serrano; Lise Le Boudec; Armand Kassaï Koupaï; Yuan Yin; Thomas X Wang; Jean-Noël Vittaut; Patrick Gallinari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite impressive results they still face challenges with respect to the domain geometry and typically rely on some form of discretization. In order to alleviate such limitations, we present CORAL, a new method that leverages coordinate-based networks for solving PDEs on general geometries.
1992, URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates
Michael Kirchhof; Bálint Mucsányi; Seong Joon Oh; Dr. Enkelejda Kasneci;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: With the rising demand for reliable machine learning and uncertainty quantification, there is a need for pretrained models that not only provide embeddings but also transferable uncertainty estimates. To guide the development of such models, we propose the Uncertainty-aware Representation Learning (URL) benchmark.
1993, The Cambridge Law Corpus: A Corpus for Legal AI Research
Andreas Östling; Holli Sargeant; Huiyuan Xie; Ludwig Bull; Alexander Terenin; Leif Jonsson; Måns Magnusson; Felix Steffek;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce the Cambridge Law Corpus (CLC), a corpus for legal AI research.
1994, Katakomba: Tools and Benchmarks for Data-Driven NetHack
Vladislav Kurenkov; Alexander Nikulin; Denis Tarasov; Sergey Kolesnikov;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we argue that there are three major obstacles for adoption: tool-wise, implementation-wise, and benchmark-wise.
1995, Beyond Geometry: Comparing The Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis
Mitchell Ostrow; Adam Eisen; Leo Kozachkov; Ila Fiete;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Yet in recurrent networks, computations are implemented at the level of neural dynamics, which do not have a simple one-to-one mapping with geometry. To bridge this gap, we introduce a novel similarity metric that compares two systems at the level of their dynamics.
1996, Mind The Spikes: Benign Overfitting of Kernels and Neural Networks in Fixed Dimension
Moritz Haas; David Holzmüller; Ulrike Luxburg; Ingo Steinwart;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we show that the smoothness of the estimators, and not the dimension, is the key: benign overfitting is possible if and only if the estimator's derivatives are large enough.
1997, Time-Independent Information-Theoretic Generalization Bounds for SGLD
Futoshi Futami; Masahiro Fujisawa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide novel information-theoretic generalization bounds for stochastic gradient Langevin dynamics (SGLD) under the assumptions of smoothness and dissipativity, which are widely used in the sampling and non-convex optimization literature.
1998, Experimental Designs for Heteroskedastic Variance
Justin Weltz; Tanner Fiez; Alexander Volfovsky; Eric Laber; Blake Mason; houssam nassif; Lalit Jain;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Assuming that $\Sigma^{\ast}\in \mathbb{R}^{d\times d}$ is an unknown matrix, we propose, analyze and empirically evaluate a novel design for uniformly bounding estimation error of the variance parameters, $\sigma_x^2$.
1999, Realistic Synthetic Financial Transactions for Anti-Money Laundering Models
Erik Altman; Beni Egressy; Jovan Blanuša; Kubilay Atasu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We describe the generator in detail and show that our datasets can help compare different Graph Neural Networks in terms of their anti-money laundering abilities.
2000, Critical Initialization of Wide and Deep Neural Networks Using Partial Jacobians: General Theory and Applications
Darshil Doshi; Tianyu He; Andrey Gromov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we describe a new practical way to diagnose criticality.
2001, Aggregating Capacity in FL Through Successive Layer Training for Computationally-Constrained Devices
Kilian Pfeiffer; Ramin Khalili; Joerg Henkel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new method that enables successive freezing and training of the parameters of the FL model at devices, reducing the training’s resource requirements at the devices, while still allowing enough co-adaptation between parameters.
2002, Joint Processing of Linguistic Properties in Brains and Language Models
SUBBAREDDY OOTA; Manish Gupta; Mariya Toneva;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For a deeper understanding of this alignment, it is important to understand the correspondence between the detailed processing of linguistic information by the human brain versus language models. We investigate this correspondence via a direct approach, in which we eliminate information related to specific linguistic properties in the language model representations and observe how this intervention affects the alignment with fMRI brain recordings obtained while participants listened to a story.
2003, Extracting Reward Functions from Diffusion Models
Felipe Nuti; Tim Franzmeyer; João Henriques;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of extracting a reward function by comparing a decision-making diffusion model that models low-reward behavior and one that models high-reward behavior; a setting related to inverse reinforcement learning.
2004, EV-Eye: Rethinking High-frequency Eye Tracking Through The Lenses of Event Cameras
Guangrong Zhao; Yurun Yang; Jingwei Liu; Ning Chen; Yiran Shen; Hongkai Wen; Guohao Lan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present EV-Eye, a first-of-its-kind large scale multimodal eye tracking dataset aimed at inspiring research on high-frequency eye/gaze tracking.
2005, Revealing The Unseen: Benchmarking Video Action Recognition Under Occlusion
Shresth Grover; Vibhav Vineet; Yogesh Rawat;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the effect of occlusion on video action recognition.
2006, Data Minimization at Inference Time
Cuong Tran; Nando Fioretto;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The paper demonstrates that, in a personalized setting, individuals may only need to disclose a small subset of features without compromising decision-making accuracy. The paper also provides an efficient sequential algorithm to determine the appropriate attributes for each individual to provide.
2007, A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
Yuanyuan Liu; Fanhua Shang; Weixin An; Junhao Liu; Hongying Liu; Zhouchen Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel extra-gradient difference acceleration algorithm for solving constrained nonconvex-nonconcave (NC-NC) minimax problems.
2008, Color Equivariant Convolutional Networks
Attila Lengyel; Ombretta Strafforello; Robert-Jan Bruintjes; Alexander Gielisse; Jan van Gemert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Color Equivariant Convolutions (CEConvs), a novel deep learning building block that enables shape feature sharing across the color spectrum while retaining important color information.
2009, AUDIT: Audio Editing By Following Instructions with Latent Diffusion Models
Yuancheng Wang; Zeqian Ju; Xu Tan; Lei He; Zhizheng Wu; Jiang Bian; sheng zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose AUDIT, an instruction-guided audio editing model based on latent diffusion models.
2010, Dynamics Generalisation Via Adaptive Policies
Michael Beukman; Devon Jarvis; Richard Klein; Steven James; Benjamin Rosman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we consider the problem of generalising to new transition dynamics, corresponding to cases in which the environment's response to the agent's actions differs.
2011, Automated Classification of Model Errors on ImageNet
Momchil Peychev; Mark Müller; Marc Fischer; Martin Vechev;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this process is time-consuming, prone to inconsistencies, and requires trained experts, making it unsuitable for regular model evaluation thus limiting its utility. To overcome these limitations, we propose the first automated error classification framework, a valuable tool to study how modelling choices affect error distributions.
2012, De Novo Drug Design Using Reinforcement Learning with Multiple GPT Agents
Xiuyuan Hu; Hao Zhang; Yang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although technologies such as transformer model and reinforcement learning have been applied in drug design, their potential has not been fully realized. Therefore, we propose MolRL-MGPT, a reinforcement learning algorithm with multiple GPT agents for drug molecular generation.
2013, Distributionally Robust Bayesian Optimization with $\varphi$-divergences
Hisham Husain; Vu Nguyen; Anton van den Hengel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While this work is pioneering, it admittedly suffers from various practical shortcomings such as finite contexts assumptions, leaving behind the main question \textit{Can one devise a computationally tractable algorithm for solving this DRO-BO problem}? In this work, we tackle this question to a large degree of generality by considering robustness against data-shift in $\varphi$-divergences, which subsumes many popular choices, such as the $\chi^2$-divergence, Total Variation, and the extant Kullback-Leibler (KL) divergence.
2014, AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways Via Contrastive Learning
Mohammadamin Tavakoli; Pierre Baldi; Ann Marie Carlton; Yin Ting Chiu; Alexander Shmakov; David Van Vranken;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, their reliance on reactions from the US Patent Office results in lack of interpretable predictions and limited generalizability to other chemistry domains, such as radical and atmospheric chemistry. To address these challenges, we introduce a new reaction predictor system, RMechRP, that leverages contrastive learning in conjunction with mechanistic pathways, the most interpretable representation of chemical reactions.
2015, Building The Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark
Nikita Gushchin; Alexander Kolesov; Petr Mokrov; Polina Karpikova; Andrei Spiridonov; Evgeny Burnaev; Alexander Korotin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Still the area lacks non-trivial tests allowing a researcher to understand how well do the methods solve SB or its equivalent continuous EOT problem. We fill this gap and propose a novel way to create pairs of probability distributions for which the ground truth OT solution in known by the construction.
2016, [Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification
Ermin Omeragic; Vuk Đuranović;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a novel augmentation method that can be used for graph classification tasks: $\mathcal{G}$-Mixup. Our goal is to reproduce eight claims that the authors make in their paper.
2017, Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning
Arnaud Robert; Ciara Pike-Burke; Aldo Faisal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we derive analytical bounds for the proposed class of goal-conditioned RL algorithms (e.g. Dot-2-Dot) that lead us to a novel Q-learning algorithm.
2018, [Re] Hierarchical Shrinkage: Improving The Accuracy and Interpretability of Tree-Based Methods
Domen Mohorčič; David Ocepek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The paper presents a novel post-hoc regularization technique for tree-based models, called Hierarchical Shrinkage (Agarwal 2022).
2019, Representation Learning Via Consistent Assignment of Views Over Random Partitions
Thalles Santos Silva; Adín Ramírez Rivera;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present Consistent Assignment of Views over Random Partitions (CARP), a self-supervised clustering method for representation learning of visual features.
2020, 4M: Massively Multimodal Masked Modeling
David Mizrahi; Roman Bachmann; Oguzhan Kar; Teresa Yeo; Mingfei Gao; Afshin Dehghan; Amir Zamir;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, recent large language models exhibit a wide range of capabilities, hinting at the possibility of similarly versatile models in computer vision. In this paper, we take a step in this direction and propose an effective multi-modal pre-training scheme, called 4M.
2021, A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
Jiaxin Shi; Lester Mackey;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide the first finite-particle convergence rate for Stein variational gradient descent (SVGD), a popular algorithm for approximating a probability distribution with a collection of particles.
2022, One Risk to Rule Them All: Addressing Distributional Shift in Offline Reinforcement Learning Via Risk-Aversion
Marc Rigter; Bruno Lacerda; Nick Hawes;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Previous works on risk in offline RL combine together offline RL techniques (to avoid distributional shift), with risk-sensitive RL algorithms (to achieve risk-aversion). In this work, we propose risk-aversion as a mechanism to jointly address *both* of these issues.
2023, DISCOVER: Making Vision Networks Interpretable Via Competition and Dissection
Konstantinos Panousis; Sotirios Chatzis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose DISCOVER, a novel framework for creating Intepretable Vision Networks.
2024, Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance
Nikita Kornilov; Ohad Shamir; Aleksandr Lobanov; Alexander Gasnikov; Innokentiy Shibaev; Eduard Gorbunov; Darina Dvinskikh; Samuel Horváth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we consider non-smooth stochastic convex optimization problems with two-point zero-order feedback.
2025, Single-Call Stochastic Extragradient Methods: Improved Analysis Under Weaker Conditions
Sayantan Choudhury; Eduard Gorbunov; Nicolas Loizou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In addition, several important questions regarding the convergence properties of these methods are still open, including mini-batching, efficient step-size selection, and convergence guarantees under different sampling strategies. In this work, we address these questions and provide convergence guarantees for two large classes of structured non-monotone VIPs: (i) quasi-strongly monotone problems (a generalization of strongly monotone problems) and (ii) weak Minty variational inequalities (a generalization of monotone and Minty VIPs).
2026, Byzantine-Tolerant Methods for Distributed Variational Inequalities
Nazarii Tupitsa; Eduard Gorbunov; Abdulla Jasem Almansoori; Yanlin Wu; Martin Takac; Karthik Nandakumar; Samuel Horváth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our work makes a further step in this direction by providing several (provably) Byzantine-robust methods for distributed variational inequality, thoroughly studying their theoretical convergence, removing the limitations of the previous work, and providing numerical comparisons supporting the theoretical findings.
2027, Provably Efficient Offline Reinforcement Learning in Regular Decision Processes
Roberto Cipollone; Anders Jonsson; Alessandro Ronca; Mohammad Sadegh Talebi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present RegORL, an algorithm that suitably combines automata learning techniques and state-of-the-art algorithms for offline RL in MDPs.
2028, Trade-off Between Efficiency and Consistency for Removal-based Explanations
Yifan Zhang; Haowei He; Zhiquan Tan; Yang Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we present two novel algorithms founded on the standard polynomial basis, aimed at minimizing interpretation error.
2029, Incentivizing Honesty Among Competitors in Collaborative Learning and Optimization
Florian E. Dorner; Nikola Konstantinov; Georgi Pashaliev; Martin Vechev;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This can incentivize dishonest updates that damage other participants' models, potentially undermining the benefits of collaboration. In this work, we formulate a game that models such interactions and study two learning tasks within this framework: single-round mean estimation and multi-round SGD on strongly-convex objectives.
2030, Unleash The Potential of Image Branch for Cross-modal 3D Object Detection
Yifan Zhang; Qijian Zhang; Junhui Hou; Yixuan Yuan; Guoliang Xing;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents a new cross-modal 3D object detector, namely BiProDet, which aims to unleash the potential of the image branch from two aspects.
2031, NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries
Qijian Zhang; Junhui Hou; Yohanes Adikusuma; Wenping Wang; Ying He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we introduce neural geodesic fields (NeuroGFs), which are learned to represent the all-pairs geodesics of a given mesh.
2032, Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation
Quang Nguyen; Truong Vu; Anh Tran; Khoi Nguyen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By utilizing the text prompts, cross-attention, and self-attention of SD, we introduce three innovative techniques: \textit{class-prompt appending}, \textit{class-prompt cross-attention}, and \textit{self-attention exponentiation}.
2033, Time Series Kernels Based on Nonlinear Vector AutoRegressive Delay Embeddings
Giovanni De Felice; John Goulermas; Vladimir Gusev;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we present a new kernel based on the recently established equivalence between reservoir dynamics and Nonlinear Vector AutoRegressive (NVAR) processes.
2034, Tanh Works Better with Asymmetry
Dongjin Kim; Woojeong Kim; Suhyun Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, in the case of bounded activation functions like Tanh, we discovered that the swapped order achieves considerably better performance than the conventional order on various benchmarks and architectures. This paper reports this remarkable phenomenon and closely examines what contributes to this performance improvement.
2035, Variational Weighting for Kernel Density Ratios
Sangwoong Yoon; Frank Park; Gunsu YUN; Iljung Kim; Yung-Kyun Noh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Drawing upon tools from the multidimensional calculus of variations, we derive an optimal weight function that reduces bias in standard kernel density estimates for density ratios, leading to improved estimates of prediction posteriors and information-theoretic measures.
2036, A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning
Hangfan Zhang; Jinyuan Jia; Jinghui Chen; Lu Lin; Dinghao Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This leads to sub-optimal and less durable attack effectiveness, i.e., their attack success rate is low when the attack budget is limited and decreases quickly if the attacker can no longer perform attacks anymore. To address these limitations, we propose A3FL, a new backdoor attack which adversarially adapts the backdoor trigger to make it less likely to be removed by the global training dynamics.
2037, Efficient Activation Function Optimization Through Surrogate Modeling
Garrett Bingham; Risto Miikkulainen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper aims to improve the state of the art through three steps: First, the benchmark datasets \texttt{Act-Bench-CNN}, \texttt{Act-Bench-ResNet}, and \texttt{Act-Bench-ViT} were created by training convolutional, residual, and vision transformer architectures from scratch with 2{,}913 systematically generated activation functions.
2038, Stabilizing The Optimization of Neural Signed Distance Functions and Finer Shape Representation
Huizong Yang; Yuxin Sun; Ganesh Sundaramoorthi; Anthony Yezzi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on a similar PDE theory for the continuum limit, we introduce a new regularization term that still counteracts the eikonal instability but without over-regularizing.
2039, Adapting to Continuous Covariate Shift Via Online Density Ratio Estimation
Yu-Jie Zhang; Zhen-Yu Zhang; Peng Zhao; Masashi Sugiyama;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we initiate the study of a more challenging scenario --- continuous covariate shift --- in which the test data appear sequentially, and their distributions can shift continuously.
2040, Inferring Multi-agent Behaviors from Distributed and Streaming Demonstrations
Shicheng Liu; Minghui Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel ``multi-agent behavior inference from distributed and streaming demonstrations (MA-BIRDS) algorithm that allows the learners to solve the outer-level and inner-level problems in a single loop through intermittent communications.
2041, A Function Interpretation Benchmark for Evaluating Interpretability Methods
Sarah Schwettmann; Tamar Shaham; Joanna Materzynska; Neil Chowdhury; Shuang Li; Jacob Andreas; David Bau; Antonio Torralba;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present FIND: a function interpretation dataset and benchmark for evaluating interpretability methods on functions whose ground truth structure is known.
2042, Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms
Qining Zhang; Lei Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces \emph{Regret Optimal Best Arm Identification} (ROBAI) which aims to achieve these dual objectives. To solve ROBAI with both pre-determined stopping time and adaptive stopping time requirements, we present the $\mathsf{EOCP}$ algorithm and its variants respectively, which not only achieve asymptotic optimal regret in both Gaussian and general bandits, but also commit to the optimal arm in $\mathcal{O}(\log T)$ rounds with pre-determined stopping time and $\mathcal{O}(\log^2 T)$ rounds with adaptive stopping time.
2043, DiffInfinite: Large Mask-Image Synthesis Via Parallel Random Patch Diffusion in Histopathology
Marco Aversa; Gabriel Nobis; Miriam Hägele; Kai Standvoss; Mihaela Chirica; Roderick Murray-Smith; Ahmed Alaa; Lukas Ruff; Daniela Ivanova; Wojciech Samek; Frederick Klauschen; Bruno Sanguinetti; Luis Oala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present DiffInfinite, a hierarchical diffusion model that generates arbitrarily large histological images while preserving long-range correlation structural information.
2044, Aligning Synthetic Medical Images with Clinical Knowledge Using Human Feedback
Shenghuan Sun; Gregory Goldgof; Atul Butte; Ahmed Alaa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Additionally, there are numerous unpredictable ways in which generative models may fail to synthesize clinically plausible images, making it challenging to anticipate potential failures and design automated scores for their detection. To address these challenges, this paper introduces a pathologist-in-the-loop framework for generating clinically-plausible synthetic medical images.
2045, Conformal Meta-learners for Predictive Inference of Individual Treatment Effects
Ahmed Alaa; Zaid Ahmad; Mark van der Laan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop conformal meta-learners, a general framework for issuing predictive intervals for ITEs by applying the standard conformal prediction (CP) procedure on top of CATE meta-learners.
2046, [Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization
Luka Žontar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The paper presents a novel DE approach using Thompson Sampling and Bandit theory, TS-DE.
2047, Decoding The Enigma: Benchmarking Humans and AIs on The Many Facets of Working Memory
Ankur Sikarwar; Mengmi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we introduce a comprehensive Working Memory (WorM) benchmark dataset for this purpose.
2048, Monte Carlo Tree Search with Boltzmann Exploration
Michael Painter; Mohamed Baioumy; Bruno Lacerda; Nick Hawes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we highlight and address a major limitation of MENTS: optimal actions for the maximum entropy objective do not necessarily correspond to optimal actions for the original objective.
2049, Robustifying Generalizable Implicit Shape Networks with A Tunable Non-Parametric Model
Amine Ouasfi; Adnane Boukhayma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, they still suffer from generalization issues, ranging from underfitting the input point cloud, to misrepresenting samples outside of the training data distribution, or with toplogies unseen at training. We propose here a simple and efficient mechanism to remedy some of these limitations at test time.
2050, MonoUNI: A Unified Vehicle and Infrastructure-side Monocular 3D Object Detection Network with Sufficient Depth Clues
Jia Jinrang; Zhenjia Li; Yifeng Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, by taking into account the diversity of pitch angles and focal lengths, we propose a unified optimization target named normalized depth, which realizes the unification of 3D detection problems for the two sides.
2051, Conservative State Value Estimation for Offline Reinforcement Learning
Liting Chen; Jie Yan; Zhengdao Shao; Lu Wang; Qingwei Lin; Saravanakumar Rajmohan; Thomas Moscibroda; Dongmei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Conservative State Value Estimation (CSVE), a new approach that learns conservative V-function via directly imposing penalties on OOD states.
2052, Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
Yong Liu; Chenyu Li; Jianmin Wang; Mingsheng Long;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Technically, we propose Koopa as a novel Koopman forecaster composed of stackable blocks that learn hierarchical dynamics.
2053, Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation
Yatong Sun; Bin Wang; Zhu Sun; Xiaochun Yang; Yan Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To fill the gap, we theoretically unveil the relationship between SRS predictions and instance reliability, whereby two error-bounded strategies are proposed to rectify unreliable targets and input, respectively. On this basis, we devise a model-agnostic Bidirectional Data Rectification (BirDRec) framework, which can be flexibly implemented with most existing SRSs for robust training against unreliable data.
2054, Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration
Fenja Falta; Christoph Großbröhmer; Alessa Hering; Alexander Bigalke; Mattias Heinrich;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We here provide a combined benchmark for image- and point-based registration approaches.
2055, Hierarchical Integration Diffusion Model for Realistic Image Deblurring
Zheng Chen; Yulun Zhang; Ding Liu; bin xia; Jinjin Gu; Linghe Kong; Xin Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Moreover, the distribution synthesized by the diffusion model is often misaligned with the target results, leading to restrictions in distortion-based metrics. To address the above issues, we propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring.
2056, Q-DM: An Efficient Low-bit Quantized Diffusion Model
Yanjing Li; Sheng Xu; Xianbin Cao; Baochang Zhang; Xiao Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this way, we propose an efficient Q-DM to calculate low-bit DMs by considering both training and inference process in the same framework.
2057, Learning Causal Models Under Independent Changes
Sarah Mameche; David Kaltenpoth; Jilles Vreeken;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce an approach for causal discovery beyond partially directed graphs using Gaussian Process models, and give conditions under which we provably identify the correct causal model.
2058, Training-free Diffusion Model Adaption for Variable-Sized Text-to-Image Synthesis
Zhiyu Jin; Xuli Shen; Bin Li; Xiangyang Xue;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: From this perspective, we propose a scaling factor to alleviate the change of attention entropy and mitigate the defective pattern observed.
2059, Scalable Fair Influence Maximization
Xiaobin Rui; Zhixiao Wang; Jiayu Zhao; Lichao Sun; Wei Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we adopt the objective function of welfare fairness to maximize the exponentially weighted summation over the influenced fraction of all communities.
2060, VeRF: Representing Dynamic 3D Scenes As Velocity-informed Radiance Fields
Jinxi Li; Ziyang Song; Bo Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to model dynamic 3D scenes from multi-view videos.
2061, MucRays: Neural Ray-surface Distance Fields with Multi-view Consistency
Zhuoman Liu; Bo Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the problem of continuous 3D shape representations.
2062, Explaining The Uncertain: Stochastic Shapley Values for Gaussian Process Models
Siu Lun Chau; Krikamol Muandet; Dino Sejdinovic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel approach for explaining Gaussian processes (GPs) that can utilize the full analytical covariance structure present in GPs.
2063, Multi-Object Representation Learning Via Feature Connectivity and Object-Centric Regularization
Alex Foo; Wynne Hsu; Mong Li Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current works on multi-object images typically follow a generative approach that optimizes for input reconstruction and fail to scale to real-world datasets despite significant increases in model capacity. To address this limitation, we propose a novel method that leverages feature connectivity to cluster neighboring pixels likely to belong to the same object.
2064, Active Learning for Semantic Segmentation with Multi-class Label Query
Sehyun Hwang; Sohyun Lee; Hoyoung Kim; Minhyeon Oh; Jungseul Ok; Suha Kwak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a new active learning method for semantic segmentation.
2065, Information-guided Planning: An Online Approach for Partially Observable Problems
Matheus Aparecido Do Carmo Alves; Amokh Varma; Yehia Elkhatib; Leandro Soriano Marcolino;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents IB-POMCP, a novel algorithm for online planning under partial observability.
2066, Learning Dictionary for Visual Attention
Yingjie Liu; Xuan Liu; Hui Yu; XUAN TANG; xian wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel dictionary learning-based attention (\textit{Dic-Attn}) module, inspired by sparse coding in the human visual perception system.
2067, FAST: A Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation
Jia Gu; Caizhi Tang; Han Yan; Qing Cui; Longfei Li; Jun Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel strategy for estimating the heterogeneous treatment effect called the Fused and Accurate Shrinkage Tree ($\mathrm{FAST}$).
2068, Does A Sparse ReLU Network Training Problem Always Admit An Optimum ?
QUOC-TUNG LE; Remi Gribonval; Elisa Riccietti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that the existence of an optimal solution is not always guaranteed, especially in the context of sparse ReLU neural networks.
2069, Slow and Weak Attractor Computation Embedded in Fast and Strong E-I Balanced Neural Dynamics
Xiaohan Lin; Liyuan Li; Boxin Shi; Tiejun Huang; Yuanyuan Mi; Si Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we investigate the compatibility of continuous attractor neural networks (CANNs) and E-INNs.
2070, Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms
Akifumi Wachi; Wataru Hashimoto; Xun Shen; Kazumune Hashimoto;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a generalized safe exploration (GSE) problem as a unified formulation of common safe exploration problems.
2071, From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
Robin San Roman; Yossi Adi; Antoine Deleforge; Romain Serizel; Gabriel Synnaeve; Alexandre Defossez;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality from low-bitrate discrete representations.
2072, Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning
Jing Zhang; Chi Zhang; Wenjia Wang; Bingyi Jing;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these methods can be overly conservative or fail to identify OOD areas accurately. To overcome this problem, we propose a Constrained Policy optimization with Explicit Behavior density (CPED) method that utilizes a flow-GAN model to explicitly estimate the density of behavior policy.
2073, SwiFT: Swin 4D FMRI Transformer
Peter Kim; Junbeom Kwon; Sunghwan Joo; Sangyoon Bae; Donggyu Lee; Yoonho Jung; Shinjae Yoo; Jiook Cha; Taesup Moon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The modeling of spatiotemporal brain dynamics from high-dimensional data, such as 4D functional MRI, is a formidable task in neuroscience. To address this challenge, we present SwiFT (Swin 4D fMRI Transformer), a Swin Transformer architecture that can learn brain dynamics directly from 4D functional brain MRI data in a memory and computation-efficient manner.
2074, Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation
Zhangsihao Yang; Mengwei Ren; Kaize Ding; Guido Gerig; Yalin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we present a keypoint-augmented fusion layer that extracts representations preserving both short- and long-range self-attention.
2075, Causal-structure Driven Augmentations for Text OOD Generalization
Amir Feder; Yoav Wald; Claudia Shi; Suchi Saria; David Blei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose to use counterfactual data augmentation, guided by knowledge of the causal structure of the data, to simulate interventions on spurious features and to learn more robust text classifiers.
2076, LMC: Large Model Collaboration for Training-Free Open-Set Object Recognition
Haoxuan Qu; Xiaofei Hui; Yujun Cai; Jun Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To perform open-set object recognition accurately, a key challenge is how to reduce the reliance on spurious-discriminative features. In this paper, motivated by that different large models pre-trained through different paradigms can possess very rich while distinct implicit knowledge, we propose a novel framework (LMC) to tackle the above challenge via collaborating different off-the-shelf large models in a training-free manner.
2077, Separable Physics-Informed Neural Networks
Junwoo Cho; Seungtae Nam; Hyunmo Yang; Seok-Bae Yun; Youngjoon Hong; Eunbyung Park;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The number of training points (collocation points) required on these challenging PDEs grows substantially, and it is severely limited due to the expensive computational costs and heavy memory overhead. To overcome this limit, we propose a network architecture and training algorithm for PINNs.
2078, Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning
Zhongyi Cai; Ye Shi; Wei Huang; Jingya Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Notably, these two forms of data heterogeneity have been studied separately and have not been well explored within a unified FL framework. To address this gap, we propose Fed-CO2, a universal FL framework that handles both label distribution skew and feature skew within a Cooperation mechanism between the Online and Offline models.
2079, Online Inventory Problems: Beyond The I.i.d. Setting with Online Convex Optimization
Massil HIHAT; Stéphane Gaïffas; Guillaume Garrigos; Simon Bussy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose MaxCOSD, an online algorithm that has provable guarantees even for problems with non-i.i.d. demands and stateful dynamics, including for instance perishability.
2080, In-Context Decision-Making from Supervised Pretraining
Jonathan N Lee; Annie Xie; Aldo Pacchiano; Yash Chandak; Chelsea Finn; Ofir Nachum; Emma Brunskill;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the in-context learning capabilities of transformers in decision-making problems, i.e., contextual bandits and Markov decision processes.
2081, SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
Mengcheng Lan; Xinjiang Wang; Yiping Ke; Jiaxing Xu; Litong Feng; Wayne Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we demonstrate that the smoothness prior, asserting that adjacent features in a metric space share the same semantics, can significantly simplify segmentation by casting unsupervised semantic segmentation as an energy minimization problem. Under this paradigm, we propose a novel approach called SmooSeg that harnesses self-supervised learning methods to model the closeness relationships among observations as smoothness signals.
2082, Contrastive Sampling Chains in Diffusion Models
Junyu Zhang; Daochang Liu; Shichao Zhang; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, discretization error is an inevitable limitation when utilizing numerical solvers to solve SDEs. To address this limitation, we provide a theoretical analysis demonstrating that an appropriate combination of the contrastive loss and score matching serves as an upper bound of the KL divergence between the true data distribution and the model distribution.
2083, Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning
Siyuan Sun; Hongyang Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Meta-AdaM, a meta-learned adaptive optimizer with momentum, designed for few-shot learning tasks that pose significant challenges to deep learning models due to the limited number of labeled examples.
2084, How to Fine-tune The Model: Unified Model Shift and Model Bias Policy Optimization
Hai Zhang; Hang Yu; Junqiao Zhao; Di Zhang; xiao zhang; Hongtu Zhou; Chang Huang; Chen Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we theoretically derive an optimization objective that can unify model shift and model bias and then formulate a fine-tuning process.
2085, Towards Test-Time Refusals Via Concept Negation
Peiran Dong; Song Guo; Junxiao Wang; Bingjie WANG; Jiewei Zhang; Ziming Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Keeping the limitations in mind, we propose a novel framework, called $ProtoRe$, to improve the flexibility of concept negation via test-time negative concept identification along with purification in the feature space.
2086, Unbalanced Low-rank Optimal Transport Solvers
Meyer Scetbon; Michal Klein; Giovanni Palla; Marco Cuturi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A flurry of recent works in OT has addressed these computational and modelling limitations, but has resulted in two separate strains of methods:While the computational outlook was much improved by entropic regularization, more recent $O(n)$ linear-time \textit{low-rank} solvers hold the promise to scale up OT further. On the other hand, modelling rigidities have been eased owing to unbalanced variants of OT, that rely on penalization terms to promote, rather than impose, mass conservation. The goal of this paper is to merge these two strains, to achieve the promise of \textit{both} versatile/scalable unbalanced/low-rank OT solvers.
2087, VRA: Variational Rectified Activation for Out-of-distribution Detection
Mingyu Xu; Zheng Lian; Bin Liu; Jianhua Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To answer this question, we leverage the variational method to find the optimal operation and verify the necessity of suppressing abnormally low and high activations and amplifying intermediate activations in OOD detection, rather than focusing only on high activations like ReAct. This motivates us to propose a novel technique called ``Variational Rectified Activation (VRA)'', which simulates these suppression and amplification operations using piecewise functions.
2088, Exploring Diverse In-Context Configurations for Image Captioning
Xu Yang; Yongliang Wu; Mingzhuo Yang; Haokun Chen; Xin Geng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In order to explore the effects of varying configurations on VL in-context learning, we devised four strategies for image selection and four for caption assignment to configure in-context image-text pairs for image captioning.
2089, Stable Nonconvex-Nonconcave Training Via Linear Interpolation
Thomas Pethick; Wanyun Xie; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a theoretical analysis of linear interpolation as a key method for stabilizing (large-scale) neural network training.
2090, Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms
Michael Feldman; David Donoho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider several practical and effective matricization strategies which construct specific matrices from such tensors and then apply spectral methods; the strategies include tensor unfolding, partial tracing, and a new method---successive contraction.
2091, On The Ability of Graph Neural Networks to Model Interactions Between Vertices
Noam Razin; Tom Verbin; Nadav Cohen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: As a practical application of our theory, we design an edge sparsification algorithm named Walk Index Sparsification (WIS), which preserves the ability of a GNN to model interactions when input edges are removed.
2092, Experiment Planning with Function Approximation
Aldo Pacchiano; Jonathan N Lee; Emma Brunskill;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of experiment planning with function approximation in contextual bandit problems.
2093, Characterization of Overfitting in Robust Multiclass Classification
Jingyuan Xu; Weiwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper considers the following question: Given the number of classes m, the number of robust accuracy queries k, and the number of test examples in the dataset n, how much can adaptive algorithms robustly overfit the test dataset? We solve this problem by equivalently giving near-matching upper and lower bounds of the robust overfitting bias in multiclass classification problems.
2094, Risk-Averse Active Sensing for Timely Outcome Prediction Under Cost Pressure
Yuchao Qin; Mihaela van der Schaar; Changhee Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel risk-averse active sensing approach RAS that addresses the composite decision problem of when to conduct the acquisition and which measurements to make.
2095, Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions
Chengzhi Cao; Chao Yang; Ruimao Zhang; Shuang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an interpretable model to uncover the behavioral patterns of human movements by analyzing their trajectories.
2096, Concept Distillation: Leveraging Human-centered Explanations for Model Improvement
Avani Gupta; Saurabh Saini; P J Narayanan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present *Concept Distillation*, a novel method and framework for concept-sensitive training to induce human-centered knowledge into the model.
2097, LICO: Explainable Models with Language-Image COnsistency
Yiming Lei; Zilong Li; Yangyang Li; Junping Zhang; Hongming Shan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper develops a Language-Image COnsistency model for explainable image classification, termed LICO, by correlating learnable linguistic prompts with corresponding visual features in a coarse-to-fine manner.
2098, Decompose A Task Into Generalizable Subtasks in Multi-Agent Reinforcement Learning
Zikang Tian; Ruizhi Chen; Fan Wu; Rui Zhang; Ling Li; Xing Hu; Shaohui Peng; Jiaming Guo; Zidong Du; Qi Guo; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, ensuring true task-independence of subtasks poses a challenge. In this paper, we propose to \textbf{d}ecompose a \textbf{t}ask in\textbf{to} a series of \textbf{g}eneralizable \textbf{s}ubtasks (DT2GS), a novel framework that addresses this challenge by utilizing a scalable subtask encoder and an adaptive subtask semantic module.
2099, Improving Robustness with Adaptive Weight Decay
Mohammad Amin Ghiasi; Ali Shafahi; Reza Ardekani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration.
2100, Tree Variational Autoencoders
Laura Manduchi; Moritz Vandenhirtz; Alain Ryser; Julia Vogt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new generative hierarchical clustering model that learns a flexible tree-based posterior distribution over latent variables.
2101, Drift Doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection
Chengsen Wang; Qi Qi; Jingyu Wang; Haifeng Sun; Xingyu Wang; Zirui Zhuang; Jianxin Liao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To fill the gap, we propose Dynamic Decomposition with Diffusion Reconstruction (D$^3$R), a novel anomaly detection network for real-world unstable data.
2102, Scale-Space Hypernetworks for Efficient Biomedical Image Analysis
Jose Javier Gonzalez Ortiz; John Guttag; Adrian Dalca;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, properly exploring the accuracy-efficiency trade-off is prohibitively expensive with existing models. To address this, we introduce Scale-Space HyperNetworks (SSHN), a method that learns a spectrum of CNNs with varying internal rescaling factors.
2103, FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow
Jihyun Lee; Junbong Jang; Donghwan Kim; Minhyuk Sung; Tae-Kyun Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present FourierHandFlow, which is a spatio-temporally continuous representation for human hands that combines a 3D occupancy field with articulation-aware query flows represented as Fourier series.
2104, Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games
Gabriele Farina; Charilaos Pipis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we provide a positive result, by showing that it is possible, in any sequential game, to retain polynomial-time (in the game tree size) iterations while achieving sublinear regret with respect to all linear transformations of the mixed strategy space, a notion called no-linear-swap regret.
2105, On The Convergence of CART Under Sufficient Impurity Decrease Condition
Rahul Mazumder; Haoyue Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the convergence rate of CART under a regression setting.
2106, Training Chain-of-Thought Via Latent-Variable Inference
Matthew Douglas Hoffman; Du Phan; David Dohan; Pavel Sountsov; Rif A. Saurous; Sharad Vikram; Sholto Douglas; Tuan Anh Le; Charles Sutton; Aaron Parisi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead, we propose a prompt-tuning strategy that tries to maximize the marginal log-likelihood of generating a correct answer using CoT prompting, approximately averaging over all possible rationales.
2107, SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
Haobo Jiang; Mathieu Salzmann; Zheng Dang; Jin Xie; Jian Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios.
2108, Leveraging The Two-timescale Regime to Demonstrate Convergence of Neural Networks
Pierre Marion; Raphaël Berthier;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer.
2109, Optimal Testing Using Combined Test Statistics Across Independent Studies
Lasse Vuursteen; Botond Szabo; Aad van der Vaart; Harry van Zanten;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a natural and mild restriction on the meta-level combination functions of the local trials.
2110, Large Language Model Is Semi-Parametric Reinforcement Learning Agent
Danyang Zhang; Lu Chen; Situo Zhang; Hongshen Xu; Zihan Zhao; Kai Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the insights in cognitive science with respect to human memory and reasoning mechanism, a novel evolvable LLM-based (Large Language Model) agent framework is proposed as Rememberer.
2111, Generalizable Lightweight Proxy for Robust NAS Against Diverse Perturbations
Hyeonjeong Ha; Minseon Kim; Sung Ju Hwang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Although there exist several robust NAS frameworks that tackle this issue by integrating adversarial training into one-shot NAS, however, they are limited in that they only consider robustness against adversarial attacks and require significant computational resources to discover optimal architectures for a single task, which makes them impractical in real-world scenarios. To address these challenges, we propose a novel lightweight robust zero-cost proxy that considers the consistency across features, parameters, and gradients of both clean and perturbed images at the initialization state.
2112, A Definition of Continual Reinforcement Learning
David Abel; Andre Barreto; Benjamin Van Roy; Doina Precup; Hado van Hasselt; Satinder Singh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we develop a foundation for continual reinforcement learning.
2113, Beyond Confidence: Reliable Models Should Also Consider Atypicality
Mert Yuksekgonul; Linjun Zhang; James Zou; Carlos Guestrin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we investigate the relationship between how atypical~(rare) a sample or a class is and the reliability of a model's predictions.
2114, Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
Canzhe Zhao; Ruofeng Yang; Baoxiang Wang; Xuezhou Zhang; Shuai Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting.
2115, Depth-discriminative Metric Learning for Monocular 3D Object Detection
Wonhyeok Choi; Mingyu Shin; Sunghoon Im;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, we introduce a novel metric learning scheme that encourages the model to extract depth-discriminative features regardless of the visual attributes without increasing inference time and model size.
2116, PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas
Zheng Chen; Yan-Pei Cao; Yuan-Chen Guo; Chen Wang; Ying Shan; Song-Hai Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although existing neural radiance field methods can produce photorealistic views under narrow-baseline and dense image captures, they tend to overfit the training views when dealing with wide-baseline panoramas due to the difficulty in learning accurate geometry from sparse $360^{\circ}$ views. To address this problem, we propose PanoGRF, Generalizable Spherical Radiance Fields for Wide-baseline Panoramas, which construct spherical radiance fields incorporating $360^{\circ}$ scene priors.
2117, AdANNS: A Framework for Adaptive Semantic Search
Aniket Rege; Aditya Kusupati; Sharan Ranjit S; Alan Fan; Qingqing Cao; Sham Kakade; Prateek Jain; Ali Farhadi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we argue that instead of rigid representations, different stages of ANNS can leverage _adaptive representations_ of varying capacities to achieve significantly better accuracy-compute trade-offs, i.e., stages of ANNS that can get away with more approximate computation should use a lower-capacity representation of the same data point.
2118, When Does Over-parameterized SGD Take As Few Iterations to Converge As Gradient Descent?
Chaoyue Liu; Dmitriy Drusvyatskiy; Yian Ma; Damek Davis; Misha Belkin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a regularity condition within the interpolation regime which endows the stochastic gradient method with the same worst-case iteration complexity as the deterministic gradient method, while using only a single sampled gradient (or a minibatch) in each iteration.
2119, Generalized Bayesian Inference for Scientific Simulators Via Amortized Cost Estimation
Richard Gao; Michael Deistler; Jakob H Macke;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, GBI methods generally require running multiple simulations to estimate the cost function at each parameter value during inference, making the approach computationally infeasible for even moderately complex simulators. Here, we propose amortized cost estimation (ACE) for GBI to address this challenge: We train a neural network to approximate the cost function, which we define as the expected distance between simulations produced by a parameter and observed data.
2120, Topology-Aware Uncertainty for Image Segmentation
Saumya Gupta; Yikai Zhang; Xiaoling Hu; Prateek Prasanna; Chao Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To achieve this, we leverage tools from topological data analysis, specifically discrete Morse theory (DMT), to first capture the structures, and then reason about their uncertainties. To model the uncertainty, we (1) propose a joint prediction model that estimates the uncertainty of a structure while taking the neighboring structures into consideration (inter-structural uncertainty); (2) propose a novel Probabilistic DMT to model the inherent uncertainty within each structure (intra-structural uncertainty) by sampling its representations via a perturb-and-walk scheme.
2121, Exploring The Gaussian Process Nature of Wide Neural Networks: Insights from Deep Equilibrium Models
Tianxiang Gao; Xiaokai Huo; Hailiang Liu; Hongyang Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we specifically investigate the deep equilibrium model (DEQ), an infinite-depth neural network with shared weight matrices across layers.
2122, Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
Angela Yuan; Chris Junchi Li; Gauthier Gidel; Michael Jordan; Quanquan Gu; Simon Du;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Built upon standard extragradient for variational inequalities, we propose a novel algorithm called stochastic \emph{accelerated gradient-extragradient} (AG-EG), for strongly monotone variational inequalities (VI).
2123, Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification
Tianjun Ke; Haoqun Cao; Zenan Ling; Feng Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Utilizing modified logistic-softmax, we integrate the data augmentation technique into the deep kernel based Gaussian process meta-learning framework, and derive an analytical mean-field approximation for task-specific updates.
2124, Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
Krishnendu Chatterjee; Thomas Henzinger; Mathias Lechner; Abhinav Verma; Đorđe Žikelić;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel method for learning a composition of neural network policies in stochastic environments, along with a formal certificate which guarantees that a specification over the policy's behavior is satisfied with the desired probability.
2125, Text Promptable Surgical Instrument Segmentation with Vision-Language Models
Zijian Zhou; Oluwatosin Alabi; Meng Wei; Tom Vercauteren; Miaojing Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel text promptable surgical instrument segmentation approach to overcome challenges associated with diversity and differentiation of surgical instruments in minimally invasive surgeries.
2126, Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes
YIXUAN ZHANG; Quyu Kong; Feng Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we propose a novel deep spatio-temporal point process model, Deep Kernel Mixture Point Processes (DKMPP), that incorporates multimodal covariate information.
2127, Resource Tradeoffs for Deep Feature Learning: Data, Compute, Width, and Luck
Benjamin Edelman; Surbhi Goel; Sham Kakade; Eran Malach; Cyril Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work investigates the nuanced algorithm design choices for deep learning in the presence of computational-statistical gaps.
2128, Boosting Learning for LDPC Codes to Improve The Error-Floor Performance
Hee-Youl Kwak; Dae-Young Yun; Yongjune Kim; Sang-Hyo Kim; Jong-Seon No;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose training methods to optimize neural min-sum (NMS) decoders that are robust to the error-floor.
2129, Bandit Social Learning Under Myopic Behavior
Kiarash Banihashem; MohammadTaghi Hajiaghayi; Suho Shin; Aleksandrs Slivkins;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study social learning dynamics motivated by reviews on online platforms.
2130, Learning Trajectories Are Generalization Indicators
Jingwen Fu; Zhizheng Zhang; Dacheng Yin; Yan Lu; Nanning Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead of concentrating solely on the generalization error of the DNN post-training, we present a novel perspective for analyzing generalization error by investigating the contribution of each update step to the change in generalization error.
2131, MeCo: Zero-Shot NAS with One Data and Single Forward Pass Via Minimum Eigenvalue of Correlation
Tangyu Jiang; Haodi Wang; Rongfang Bie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Enlightened by the theoretical analysis, we propose a novel zero-cost proxy called MeCo, which requires only one random data for a single forward pass.
2132, Reproducibility Study of 'Proto2Proto: Can You Recognise The Car, The Way I Do?'
gerson de Kleuver; David Bikker; Wenhua Hu; Bram Veenman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The main contributions and claims of the study are: 1) Using Proto2Proto, a shallower student model is more faithful to the teacher in terms of interpretability than a baseline student model while also showing the same or better accuracy; 2) Global Explanation loss forces student prototypes to be close to teacher prototypes; 3) Patch-Prototype Correspondence loss enforces the local representations of the student to be similar to those of the teacher; 4) The proposed evaluation metrics determine the faithfulness of the student to the teacher in terms of interpretability.
2133, A Scale-Invariant Sorting Criterion to Find A Causal Order in Additive Noise Models
Alexander Reisach; Myriam Tami; Christof Seiler; Antoine Chambaz; Sebastian Weichwald;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that synthetic ANM data are characterized by another scale-invariant pattern that persists even after standardization: the explainable fraction of a variable's variance, as captured by the coefficient of determination $R^2$, tends to increase along the causal order.
2134, Bypassing Spike Sorting: Density-based Decoding Using Spike Localization from Dense Multielectrode Probes
Yizi Zhang; Tianxiao He; Julien Boussard; Charles Windolf; Olivier Winter; Eric Trautmann; Noam Roth; Hailey Barrell; Mark Churchland; Nicholas A Steinmetz; Erdem Varol; Cole Hurwitz; Liam Paninski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a spike sorting-free decoding method that directly models the distribution of extracted spike features using a mixture of Gaussians (MoG) encoding the uncertainty of spike assignments, without aiming to solve the spike clustering problem explicitly.
2135, Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities
Yale Song; Eugene Byrne; Tushar Nagarajan; Huiyu Wang; Miguel Martin; Lorenzo Torresani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce Ego4D Goal-Step, a new set of annotations on the recently released Ego4D with a novel hierarchical taxonomy of goal-oriented activity labels.
2136, HT-Step: Aligning Instructional Articles with How-To Videos
Triantafyllos Afouras; Effrosyni Mavroudi; Tushar Nagarajan; Huiyu Wang; Lorenzo Torresani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce HT-Step, a large-scale dataset containing temporal annotations of instructional article steps in cooking videos.
2137, Streaming Factor Trajectory Learning for Temporal Tensor Decomposition
Shikai Fang; Xin Yu; Shibo Li; Zheng Wang; Mike Kirby; Shandian Zhe;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: More important, we lack an effective approach to capture such evolution from streaming data, which is common in real-world applications. To address these issues, we propose Streaming Factor Trajectory Learning (SFTL) for temporal tensor decomposition.
2138, Dynamic Tensor Decomposition Via Neural Diffusion-Reaction Processes
Zheng Wang; Shikai Fang; Shibo Li; Shandian Zhe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a stratified sampling method to balance the cost of processing each mini-batch so as to improve the overall efficiency.
2139, Modulated Neural ODEs
Ilze Amanda Auzina; Çağatay Yıldız; Sara Magliacane; Matthias Bethge; Efstratios Gavves;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce Modulated Neural ODEs (MoNODEs), a novel framework that sets apart dynamics states from underlying static factors of variation and improves the existing NODE methods.
2140, Error Discovery By Clustering Influence Embeddings
Fulton Wang; Julius Adebayo; Sarah Tan; Diego Garcia-Olano; Narine Kokhlikyan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a method for identifying groups of test examples---slices---on which a model under-performs, a task now known as slice discovery.
2141, Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations
Piotr Indyk; Haike Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For the other data structure variants studied, including DiskANN with fast preprocessing'', HNSW and NSG, we present a family of instances on which the empirical query time required to achieve a reasonable'' accuracy is linear in instance size.
2142, TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
Phitchaya Phothilimtha; Sami Abu-El-Haija; Kaidi Cao; Bahare Fatemi; Charith Mendis; Bryan Perozzi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces TpuGraphs, a performance prediction dataset on full tensor programs, represented as computational graphs, running on Tensor Processing Units (TPUs).
2143, The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation
Elia Turner; Omri Barak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we first construct a systematic framework to study multiple tasks in RNNs, minimizing interference from input and output correlations with the hidden representation. This allows us to reveal how RNNs tend to share attractors and reuse dynamics, a tendency we define as the simplicity bias.
2144, OpenAssistant Conversations - Democratizing Large Language Model Alignment
Andreas Köpf; Yannic Kilcher; Dimitri von Rütte; Sotiris Anagnostidis; Zhi Rui Tam; Keith Stevens; Abdullah Barhoum; Duc Nguyen; Oliver Stanley; Richárd Nagyfi; Shahul ES; Sameer Suri; David Glushkov; Arnav Dantuluri; Andrew Maguire; Christoph Schuhmann; Huu Nguyen; Alexander Mattick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In an effort to democratize research on large-scale alignment, we release OpenAssistant Conversations, a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages in 35 different languages, annotated with 461,292 quality ratings, resulting in over 10,000 complete and fully annotated conversation trees.
2145, GALOPA: Graph Transport Learning with Optimal Plan Alignment
Yejiang Wang; Yuhai Zhao; Daniel Zhengkui Wang; Ling Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an alternative self-supervised solution that (i) goes beyond the label invariance assumption without distinguishing between positive/negative samples, (ii) can calibrate the encoder for preserving not only the structural information inside the graph, but the matching information between different graphs, (iii) learns isometric embeddings that preserve the distance between graphs, a by-product of our objective.
2146, ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning
Julia Kaltenborn; Charlotte Lange; Venkatesh Ramesh; Philippe Brouillard; Yaniv Gurwicz; Jakob Runge; Peer Nowack; David Rolnick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we introduce ClimateSet, a dataset containing the inputs and outputs of 36 climate models from the Input4MIPs and CMIP6 archives.
2147, Translating Proteins to Pictures and Back with A Bidirectional Text-to-Image Transformer
Emaad Khwaja; Yun Song; Aaron Agarunov; Bo Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present CellBERT-E, a novel bidirectional non-autoregressive transformer that can generate realistic images and sequences of protein localization in the cell.
2148, Implicit Regularization in Over-Parameterized Support Vector Machine
Yang Sui; Xin HE; Yang Bai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we design a regularization-free algorithm for high-dimensional support vector machines (SVMs) by integrating over-parameterization with Nesterov's smoothing method, and provide theoretical guarantees for the induced implicit regularization phenomenon.
2149, Spatio-Angular Convolutions for Super-resolution in Diffusion MRI
Matthew Lyon; Paul Armitage; Mauricio A Álvarez;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Diffusion MRI (dMRI) is a widely used imaging modality, but requires long scanning times to acquire high resolution datasets. By leveraging the unique geometry present within this domain, we present a novel approach to dMRI angular super-resolution that extends upon the parametric continuous convolution (PCConv) framework.
2150, On Measuring Fairness in Generative Models
Christopher Teo; Milad Abdollahzadeh; Ngai-Man (Man) Cheung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we conduct, for the first time, an in-depth study on fairness measurement, a critical component in gauging progress on fair generative models.
2151, Connecting Pre-trained Language Model and Downstream Task Via Properties of Representation
Chenwei Wu; Holden Lee; Rong Ge;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, there is little theoretical understanding of how pre-training performance is related to downstream task performance. In this paper, we analyze how this performance transfer depends on the properties of the downstream task and the structure of the representations.
2152, ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling
Yuqi Chen; Kan Ren; Yansen Wang; Yuchen Fang; Weiwei Sun; Dongsheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It is challenging yet demanding to concurrently model the relationship between input data points and capture the dynamic changes of the continuous-time system. To tackle this problem, we propose ContiFormer that extends the relation modeling of vanilla Transformer to continuous domain, which explicitly incorporates the modeling abilities of continuous dynamics of Neural ODE with the attention mechanism of Transformers.
2153, Conformal Prediction Sets for Ordinal Classification
PRASENJIT DEY; Srujana Merugu; Sivaramakrishnan R Kaveri;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a framework to adapt existing CP methods to generate contiguous sets with guaranteed coverage and minimal cardinality.
2154, $\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
Adel Nabli; Eugene Belilovsky; Edouard Oyallon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we focus on peer-to-peer asynchronous methods due to their flexibility and parallelization potentials.
2155, DiViNeT: 3D Reconstruction from Disparate Views Using Neural Template Regularization
Aditya Vora; Akshay Gadi Patil; Hao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a volume rendering-based neural surface reconstruction method that takes as few as three disparate RGB images as input.
2156, Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification
Rui Wang; Peipei Li; Huaibo Huang; Chunshui Cao; Ran He; Zhaofeng He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a novel language-driven ordering alignment method for ordinal classification.
2157, On The Size and Approximation Error of Distilled Datasets
Alaa Maalouf; Murad Tukan; Noel Loo; Ramin Hasani; Mathias Lechner; Daniela Rus;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we take a theoretical view on kernel ridge regression (KRR) based methods of dataset distillation such as Kernel Inducing Points.
2158, Implicit Contrastive Representation Learning with Guided Stop-gradient
Byeongchan Lee; SEHYUN LEE;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By exploiting the asymmetric architecture, we introduce a methodology to implicitly incorporate the idea of contrastive learning. As its implementation, we present a novel method guided stop-gradient.
2159, An Inductive Bias for Tabular Deep Learning
Jonathan Kozaczuk; Ege Beyazit; Bo Li; Vanessa Wallace; Bilal Fadlallah;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Deep learning methods have achieved state-of-the-art performance in most modeling tasks involving images, text and audio, however, they typically underperform tree-based methods on tabular data. In this paper, we hypothesize that a significant contributor to this performance gap is the interaction between irregular target functions resulting from the heterogeneous nature of tabular feature spaces, and the well-known tendency of neural networks to learn smooth functions.
2160, GAIA: Delving Into Gradient-based Attribution Abnormality for Out-of-distribution Detection
Jinggang Chen; Junjie Li; Xiaoyang Qu; Jianzong Wang; Jiguang Wan; Jing Xiao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we offer an innovative perspective on quantifying the disparities between in-distribution (ID) and OOD data---analyzing the uncertainty that arises when models attempt to explain their predictive decisions.
2161, Non-Convex Bilevel Optimization with Time-Varying Objective Functions
Sen Lin; Daouda Sow; Kaiyi Ji; Yingbin Liang; Ness Shroff;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study online bilevel optimization (OBO) where the functions can be time-varying and the agent continuously updates the decisions with online streaming data.
2162, Self-Weighted Contrastive Learning Among Multiple Views for Mitigating Representation Degeneration
Jie Xu; Shuo Chen; Yazhou Ren; Xiaoshuang Shi; Hengtao Shen; Gang Niu; Xiaofeng Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In multi-view scenarios, however, CL might cause representation degeneration when the collected multiple views have inconsistent semantic information or their representations do not capture sufficient discriminative information. To address this issue, we propose a novel framework of SEM: SElf-weighted Multi-view contrastive learning.
2163, Explain Any Concept: Segment Anything Meets Concept-Based Explanation
Ao Sun; Pingchuan Ma; Yuanyuan Yuan; Shuai Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We thus propose a lightweight per-input equivalent (PIE) scheme, enabling efficient explanation with a surrogate model.
2164, Causal Imitability Under Context-Specific Independence Relations
Fateme Jamshidi; Sina Akbari; Negar Kiyavash;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of causal imitation learning when CSI relations are known. We prove that the decision problem pertaining to the feasibility of imitation in this setting is NP-hard.
2165, Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning
James Queeney; Mouhacine Benosman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem.
2166, Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training
Hitesh Sapkota; Dingrong Wang; Zhiqiang Tao; Qi Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we propose a novel Distributionally Robust Optimization (DRO) framework to achieve an ensemble of lottery tickets towards calibrated network sparsification.
2167, MotionGPT: Human Motion As A Foreign Language
Biao Jiang; Xin Chen; Wen Liu; Jingyi Yu; Gang Yu; Tao Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks.
2168, Regularizing Neural Networks with Meta-Learning Generative Models
Shin'ya Yamaguchi; Daiki Chijiwa; Sekitoshi Kanai; Atsutoshi Kumagai; Hisashi Kashima;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel strategy for generative data augmentation called *meta generative regularization* (MGR).
2169, Accelerating Value Iteration with Anchoring
Jongmin Lee; Ernest Ryu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present the first accelerated VI for both the Bellman consistency and optimality operators.
2170, Large Language Models As Commonsense Knowledge for Large-Scale Task Planning
Zirui Zhao; Wee Sun Lee; David Hsu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper shows that LLMs can be used as both the commonsense model of the world and the heuristic policy in search algorithms such as Monte Carlo Tree Search (MCTS).
2171, Towards Semi-Structured Automatic ICD Coding Via Tree-based Contrastive Learning
Chang Lu; Chandan Reddy; Ping Wang; Yue Ning;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the application of state-of-the-art natural language processing (NLP) techniques, there are still challenges including limited availability of data due to privacy constraints and the high variability of clinical notes caused by different writing habits of medical professionals and various pathological features of patients. In this work, we investigate the semi-structured nature of clinical notes and propose an automatic algorithm to segment them into sections.
2172, Optimal Decision Trees for Separable Objectives: Pushing The Limits of Dynamic Programming
Jacobus van der Linden; Mathijs de Weerdt; Emir Demirović;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Dynamic programming methods have been shown to scale much better because they exploit the tree structure by solving subtrees as independent subproblems. However, this only works when an objective can be optimized separately for subtrees. We explore this relationship in detail and show necessary and sufficient conditions for such separability and generalize previous dynamic programming approaches into a framework that can optimize any combination of separable objectives and constraints.
2173, Orthogonal Non-negative Tensor Factorization Based Multi-view Clustering
Quanxue Gao; Jing Li; QIANQIAN WANG; Ming Yang; Wei Xia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, they can't well exploit the within-view spatial structure and between-view complementary information. To resolve this issue, we present orthogonal non-negative tensor factorization (Orth-NTF) and develop a novel multi-view clustering based on Orth-NTF with one-side orthogonal constraint.
2174, Full-Atom Protein Pocket Design Via Iterative Refinement
ZAIXI ZHANG; Zepu Lu; Hao Zhongkai; Marinka Zitnik; Qi Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To overcome the limitations, we propose a \textbf{F}ull-\textbf{A}tom \textbf{I}terative \textbf{R}efinement framework (\textbf{FAIR}) for protein pocket sequence (i.e., residue types) and 3D structure co-design.
2175, A Robust Exact Algorithm for The Euclidean Bipartite Matching Problem
Akshaykumar Gattani; Sharath Raghvendra; Pouyan Shirzadian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a new algorithm to compute a minimum-cost bipartite matching of $A$ and $B$ with a similar worst-case execution time of $\tilde{O}(n^2 \log \Delta)$.
2176, Unsupervised Anomaly Detection with Rejection
Lorenzo Perini; Jesse Davis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, selecting a proper metric and setting the rejection threshold without labels are challenging tasks. In this paper, we solve these challenges by setting a constant rejection threshold on the stability metric computed by ExCeeD.
2177, Rank-N-Contrast: Learning Continuous Representations for Regression
Kaiwen Zha; Peng Cao; Jeany Son; Yuzhe Yang; Dina Katabi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To fill the gap, we propose Rank-N-Contrast (RNC), a framework that learns continuous representations for regression by contrasting samples against each other based on their rankings in the target space.
2178, NCDL: A Framework for Deep Learning on Non-Cartesian Lattices
Joshua Horacsek; Usman Alim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, data need not reside on a non-Cartesian structure, we use non-Dyadic downsampling schemes to bring Cartesian data into a non-Cartesian space for further processing. We introduce a software library that implements the lattice tensor container (with some common machine learning operations), and demonstrate its effectiveness.
2179, Nonparametric Boundary Geometry in Physics Informed Deep Learning
Scott Cameron; Arnu Pretorius; S Roberts;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel neural operator architecture which acceptsboundary geometry, in the form of triangular meshes, as input and produces anapproximate solution to a given PDE as output.
2180, Toward Understanding Generative Data Augmentation
Chenyu Zheng; Guoqiang Wu; Chongxuan LI;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, little work has theoretically investigated the effect of generative data augmentation. To fill this gap, we establish a general stability bound in this not independently and identicallydistributed (non-i.i.d.) setting, where the learned distribution is dependent on the original train set and generally not the same as the true distribution.
2181, Fair Canonical Correlation Analysis
Zhuoping Zhou; Davoud Ataee Tarzanagh; Bojian Hou; Boning Tong; Jia Xu; Yanbo Feng; Qi Long; Li Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a framework that alleviates unfairness by minimizing the correlation disparity error associated with protected attributes.
2182, Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu; Jordan Ash; Surbhi Goel; Akshay Krishnamurthy; Cyril Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To isolate the issue, we introduce _flip-flop language modeling_ (FFLM), a parametric family of synthetic benchmarks designed to probe the extrapolative behavior of neural language models.
2183, Double Pessimism Is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage
Jose Blanchet; Miao Lu; Tong Zhang; Han Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a generic algorithm framework \underline{D}oubly \underline{P}essimistic \underline{M}odel-based \underline{P}olicy \underline{O}ptimization ($\texttt{P}^2\texttt{MPO}$) for robust offline RL, which features a novel combination of a flexible model estimation subroutine and a doubly pessimistic policy optimization step.
2184, RevColV2: Exploring Disentangled Representations in Masked Image Modeling
Qi Han; Yuxuan Cai; Xiangyu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite its success, existing MIM methods discard the decoder network during downstream applications, resulting in inconsistent representations between pre-training and fine-tuning and can hamper downstream task performance. In this paper, we propose a new architecture, RevColV2, which tackles this issue by keeping the entire autoencoder architecture during both pre-training and fine-tuning.
2185, Hardware-Efficient Transformer Training Via Piecewise Affine Operations
Atli Kosson; Martin Jaggi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that transformers can be trained with the resulting modified matrix multiplications on both vision and language tasks with little to no performance impact, and without changes to the training hyperparameters.
2186, Evaluating Cognitive Maps in Large Language Models: No Emergent Planning
Ida Momennejad; Felipe Vieira Frujeri; Hosein Hasanbeig; Hamid Palangi; Nebojsa Jojic; Robert Ness; Jonathan Larson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we make two major contributions. First, we propose CogEval, a Cognitive Science-Inspired protocol for Measurement and Evaluation for Large Language Models. Second, we use CogEval to systematically evaluate hypothesized latent abilities, cognitive maps and planning, across a number of LLMs (OpenAI GPT-4, GPT-3.5, and davinci-003, Anthropic Claude-1, Alpaca-7B, LLaMA-7B, and Bard) using tasks with established construct validity and absent from LLM training sets.
2187, AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking
Yang Yu; Qi Liu; Kai Zhang; Yuren Zhang; Chao Song; Min Hou; Yuqing Yuan; Zhihao Ye; ZAIXI ZHANG; Sanshi Lei Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we propose to replace the contrastive learning task with a new pretext task: Augmentation-Adaptive Self-Supervised Ranking (AdaptSSR), which alleviates the requirement of semantic consistency between the augmented views while pre-training a discriminative user model.
2188, Bounded Rationality in Structured Density Estimation
Tianyuan Teng; Li Kevin Wenliang; Hang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, it remains unclear how the human brain, constrained by finite cognitive resources, constructs an internal model from an infinite space of probability distributions. In this study, we explore how these learned distributions deviate from the ground truth, resulting in observable inconsistency in a novel structured density estimation task.
2189, Efficient Exploration in Continuous-time Model-based Reinforcement Learning
Lenart Treven; Jonas Hübotter; Bhavya; Florian Dorfler; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a model-based reinforcement learning algorithm that represents continuous-time dynamics using nonlinear ordinary differential equations (ODEs).
2190, Learning High-Dimensional Sparse MTP2 Gaussian Graphical Model Via Bridge-Block Decomposition
XIWEN WANG; Jiaxi Ying; Daniel Palomar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper studies the problem of learning the large-scale Gaussian graphical models that are multivariate totally positive of order two ($\text{MTP}_2$).
2191, Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards
Bo Xue; Yimu Wang; Yuanyu Wan; Jinfeng Yi; Lijun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although there exist methods for generalized linear bandits, most of them focus on bounded or sub-Gaussian rewards and are not well-suited for many real-world scenarios, such as financial markets and web-advertising. To address this issue, we propose two novel algorithms based on truncation and mean of medians.
2192, Efficient Adaptation of Large Vision Transformer Via Adapter Re-Composing
Wei Dong; Dawei Yan; Zhijun Lin; Peng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this study, we propose a novel Adapter Re-Composing (ARC) strategy that addresses efficient pre-trained model adaptation from a fresh perspective.
2193, Graph of Circuits with GNN for Exploring The Optimal Design Space
Aditya Shahane; Saripilli Swapna Manjiri; Sandeep Kumar; Ankesh Jain;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The design automation of analog circuits poses significant challenges in terms of the large design space, complex interdependencies between circuit specifications, and resource-intensive simulations. To address these challenges, this paper presents an innovative framework called the Graph of Circuits Explorer (GCX).
2194, Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels
Shu-Lin Xu; Yifan Sun; Faen Zhang; Anqi Xu; Xiu-Shen Wei; Yi Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The task becomes even more demanding when attempting few-shot fine-grained recognition, which holds practical significance in various applications. To address these challenges, we propose a novel method that embeds visual embeddings into a hyperbolic space and enhances their discriminative ability with a hierarchical cosine margins manner.
2195, UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models
Xin Li; Sima Behpour; Thang Long Doan; Wenbin He; Liang Gou; Liu Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited annotation budget.
2196, Regret Minimization Via Saddle Point Optimization
Johannes Kirschner; Alireza Bakhtiari; Kushagra Chandak; Volodymyr Tkachuk; Csaba Szepesvari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By re-parametrizing the offset DEC with the confidence radius and solving the corresponding min-max program, we propose a novel anytime variant of the Estimation-To-Decisions algorithm (\AETD).
2197, Test-Time Distribution Normalization for Contrastively Learned Visual-language Models
Yifei Zhou; Juntao Ren; Fengyu Li; Ramin Zabih; Ser Nam Lim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The question lies in how one can retrieve any semblance of negative samples information during inference in a computationally efficient way. We propose Distribution Normalization (DN), where we approximate the mean representation of a batch of test samples and use such a mean to represent what would be analogous to negative samples in the InfoNCE loss.
2198, Auditing for Human Expertise
Rohan Alur; Loren Laine; Darrick Li; Manish Raghavan; Devavrat Shah; Dennis Shung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This raises a natural question whether human experts add value which could not be captured by an algorithmic predictor. We develop a statistical framework under which we can pose this question as a natural hypothesis test.
2199, Temporally Disentangled Representation Learning Under Unknown Nonstationarity
Xiangchen Song; Weiran Yao; Yewen Fan; Xinshuai Dong; Guangyi Chen; Juan Carlos Niebles; Eric Xing; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this study, we further explored the Markov Assumption under time-delayed causally related process in \emph{nonstationary} setting and showed that under mild conditions, the independent latent components can be recovered from their nonlinear mixture up to a permutation and a component-wise transformation, \emph{without the observation of auxiliary variables}. We then introduce NTDC, a principled estimation framework, to reconstruct time-delayed latent causal variables and identify their relations from measured sequential data only.
2200, No-regret Algorithms for Fair Resource Allocation
Abhishek Sinha; Ativ Joshi; Rajarshi Bhattacharjee; Cameron Musco; Mohammad Hajiesmaili;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an efficient online resource allocation policy, called Online Fair Allocation ($\texttt{OFA}$), that achieves sublinear $c_\alpha$-approximate regret with approximation factor $c_\alpha=(1-\alpha)^{-(1-\alpha)}\leq 1.445,$ for $0\leq \alpha < 1$.
2201, Back-Modality: Leveraging Modal Transformation for Data Augmentation
Zhi Li; Yifan Liu; Yin Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Back-Modality, a novel data augmentation schema predicated on modal transformation.
2202, Implicit Manifold Gaussian Process Regression
Bernardo Fichera; Slava Borovitskiy; Andreas Krause; Aude G Billard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, in this paper we propose a Gaussian process regression technique capable of inferring implicit structure directly from data (labeled and unlabeled) in a fully differentiable way.
2203, Self-Supervised Visual Acoustic Matching
Arjun Somayazulu; Changan Chen; Kristen Grauman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a self-supervised approach to visual acoustic matching where training samples include only the target scene image and audio---without acoustically mismatched source audio for reference.
2204, A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference
Emile van Krieken; Thiviyan Thanapalasingam; Jakub Tomczak; Frank van Harmelen; Annette Ten Teije;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Approximate Neurosymbolic Inference (A-NeSI): a new framework for PNL that uses neural networks for scalable approximate inference.
2205, Fine-Grained Cross-View Geo-Localization Using A Correlation-Aware Homography Estimator
Xiaolong Wang; Runsen Xu; Zhuofan Cui; Zeyu Wan; Yu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce a novel approach to fine-grained cross-view geo-localization.
2206, Semi-Supervised Domain Generalization with Known and Unknown Classes
Lei Zhang; Ji-Fu Li; Wei Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, a more realistic scenario is that known classes may be mixed with some unknown classes in unlabeled training and testing data. To deal with such a scenario, we propose the Class-Wise Adaptive Exploration and Exploitation (CWAEE) method.
2207, Learning Non-Markovian Decision-Making from State-only Sequences
Aoyang Qin; Feng Gao; Qing Li; Song-Chun Zhu; Sirui Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Conventional imitation learning assumes access to the actions of demonstrators, but these motor signals are often non-observable in naturalistic settings. Additionally, sequential decision-making behaviors in these settings can deviate from the assumptions of a standard Markov Decision Process (MDP). To address these challenges, we explore deep generative modeling of state-only sequences with non-Markov Decision Process (nMDP), where the policy is an energy-based prior in the latent space of the state transition generator.
2208, Empowering Convolutional Neural Nets with MetaSin Activation
Farnood Salehi; Tunc Aydin; André Gaillard; Yuxuan Wang; Guglielmo Camporese;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We instead propose a novel activation with trainable parameters that is implemented as a drop-in replacement for a baseline network’s existing activations.
2209, Guarantees for Self-Play in Multiplayer Games Via Polymatrix Decomposability
Revan MacQueen; James Wright;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We show that in games that approximately decompose into a set of two-player constant-sum games (called polymatrix games) where global $\epsilon$-Nash equilibria are boundedly far from Nash-equilibria in each subgame, any no-external-regret algorithm that learns by self-play will produce a strategy with bounded vulnerability.
2210, Riemannian Residual Neural Networks
Isay Katsman; Eric Chen; Sidhanth Holalkere; Anna Asch; Aaron Lou; Ser Nam Lim; Christopher De Sa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, extending Euclidean networks is difficult and has only been done for a select few manifolds. In this work, we examine the residual neural network (ResNet) and show how to extend this construction to general Riemannian manifolds in a geometrically principled manner.
2211, Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models
David Wu; Anant Sahai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the asymptotic generalization of an overparameterized linear model for multiclass classification under the Gaussian covariates bi-level model introduced in Subramanian et al. (NeurIPS'22), where the number of data points, features, and classes all grow together.
2212, The Curious Price of Distributional Robustness in Reinforcement Learning with A Generative Model
Laixi Shi; Gen Li; Yuting Wei; Yuxin Chen; Matthieu Geist; Yuejie Chi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite recent efforts, the sample complexity of RMDPs is much less understood regardless of the uncertainty set in use; in particular, there exist large gaps between existing upper and lower bounds, and it is unclear if distributional robustness bears any statistical implications when benchmarked against standard RL. In this paper, assuming access to a generative model, we derive the sample complexity of RMDPs---when the uncertainty set is measured via either total variation or $\chi^2$ divergence over the full range of uncertainty levels---using a model-based algorithm called distributionally robust value iteration, and develop minimax lower bounds to benchmark its tightness.
2213, Variational Imbalanced Regression
Ziyan Wang; Hao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a probabilistic deep learning model, dubbed variational imbalanced regression (VIR), which not only performs well in imbalanced regression but naturally produces reasonable uncertainty estimation as a byproduct.
2214, The Geometry of Hidden Representations of Large Transformer Models
Lucrezia Valeriani; Diego Doimo; Francesca Cuturello; Alessandro Laio; Alessio Ansuini; Alberto Cazzaniga;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In these models, the data representation in the hidden layers live in the same space, and the semantic structure of the dataset emerges by a sequence of functionally identical transformations between one representation and the next. We here characterize the geometric and statistical properties of these representations, focusing on their evolution across the layers.
2215, Conditional Score Guidance for Text-Driven Image-to-Image Translation
Hyunsoo Lee; Minsoo Kang; Bohyung Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model.
2216, Explainable Brain Age Prediction Using CoVariance Neural Networks
Saurabh Sihag; Gonzalo Mateos; Corey McMillan; Alejandro Ribeiro;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we leverage coVariance neural networks (VNN) to propose an anatomically interpretable framework for brain age prediction using cortical thickness features.
2217, Fair, Polylog-Approximate Low-Cost Hierarchical Clustering
Marina Knittel; Max Springer; John Dickerson; MohammadTaghi Hajiaghayi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Ahmadian et al. [2020] established the study of fairness in hierarchical clustering, a stronger, more structured variant of its well-known flat counterpart, though their proposed algorithm that optimizes for Dasgupta's [2016] famous cost function was highly theoretical. Knittel et al. [2023] then proposed the first practical fair approximation for cost, however they were unable to break the polynomial-approximate barrier they posed as a hurdle of interest. We break this barrier, proposing the first truly polylogarithmic-approximate low-cost fair hierarchical clustering, thus greatly bridging the gap between the best fair and vanilla hierarchical clustering approximations.
2218, Characterization and Learning of Causal Graphs with Small Conditioning Sets
Murat Kocaoglu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel representation that allows us to graphically characterize k-Markov equivalence between two causal graphs. We propose a sound constraint-based algorithm called the k-PC algorithm for learning this equivalence class.
2219, Sequential Subset Matching for Dataset Distillation
JIAWEI DU; Qin Shi; Joey Tianyi Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This coupling issue, in turn, leads to the failure of the distilled dataset to extract the high-level features learned by the deep neural network (DNN) in the latter epochs. In this study, we propose a new dataset distillation strategy called Sequential Subset Matching (SeqMatch), which tackles this problem by adaptively optimizing the synthetic data to encourage sequential acquisition of knowledge during dataset distillation.
2220, Maximum Average Randomly Sampled: A Scale Free and Non-parametric Algorithm for Stochastic Bandits
Masoud Moravej Khorasani; Erik Weyer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we propose a data-dependent UCB algorithm called MARS (Maximum Average Randomly Sampled) in a non-parametric setup for multi-armed bandits with symmetric rewards.
2221, EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning
Ping Guo; Xiangpeng Wei; Yue Hu; Baosong Yang; Dayiheng Liu; Fei Huang; jun xie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Emma-X: an EM-like Multilingual pre-training Algorithm, to learn Cross-lingual universals with the aid of excessive multilingual non-parallel data.
2222, Tight Risk Bounds for Gradient Descent on Separable Data
Matan Schliserman; Tomer Koren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the generalization properties of unregularized gradient methods applied to separable linear classification---a setting that has received considerable attention since the pioneering work of Soudry et al. (2018).
2223, Natural Language-conditioned Reinforcement Learning with Task-related Language Development and Translation
Jingcheng Pang; Xin-Yu Yang; Si-Hang Yang; Xiong-Hui Chen; Yang Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To ease the learning burden of the policy, we investigate an inside-out scheme for natural language-conditioned RL by developing a task language (TL) that is task-related and easily understood by the policy, thus reducing the policy learning burden.
2224, Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
Fan Feng; Sara Magliacane;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recent works have shown the benefits of object-factored representations and hierarchical abstractions for improving sample efficiency in these settings. On the other hand, these methods do not fully exploit the benefits of factorization in terms of object attributes. In this paper we address this opportunity and introduce the Dynamic Attribute FacTored RL (DAFT-RL) framework. In DAFT-RL, we leverage object-centric representation learning to extract objects from visual inputs.
2225, SyncTREE: Fast Timing Analysis for Integrated Circuit Design Through A Physics-informed Tree-based Graph Neural Network
Yuting Hu; Jiajie Li; Florian Klemme; Gi-Joon Nam; Tengfei Ma; Hussam Amrouch; Jinjun Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper focuses on one of the most important analyses, timing analysis for interconnects.
2226, Anonymous and Copy-robust Delegations for Liquid Democracy
Ulrike Schmidt-Kraepelin; Markus Utke;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Combining the same theorem with Fulkerson's algorithm, we develop a polynomial-time algorithm for computing the outcome of the studied delegation rule.
2227, Lie Point Symmetry and Physics-Informed Networks
Tara Akhound-Sadegh; Laurence Perreault-Levasseur; Johannes Brandstetter; Max Welling; Siamak Ravanbakhsh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a mechanism for leveraging the symmetries of a given PDE to improve the neural solver.
2228, Hybrid Search for Efficient Planning with Completeness Guarantees
Kalle Kujanpää; Joni Pajarinen; Alexander Ilin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an efficient approach to augment a subgoal search method to achieve completeness in discrete action spaces.
2229, Kissing to Find A Match: Efficient Low-Rank Permutation Representation
Hannah Dröge; Zorah Lähner; Yuval Bahat; Onofre Martorell Nadal; Felix Heide; Michael Moeller;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, memory for explicitly representing permutation matrices grows quadratically with the size of the problem, prohibiting large problem instances. In this work, we propose to tackle the curse of dimensionality of large permutation matrices by approximating them using low-rank matrix factorization, followed by a nonlinearity.
2230, The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights That Matter
AJAY JAISWAL; Shiwei Liu; Tianlong Chen; Zhangyang Atlas Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we comprehensively study $\textit{induced sparse patterns}$ across multiple large pre-trained vision and language transformers.
2231, Sample-Efficient and Safe Deep Reinforcement Learning Via Reset Deep Ensemble Agents
WOOJUN KIM; Yongjae Shin; Jongeui Park; Youngchul Sung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel reset-based method that leverages deep ensemble learning to address the limitations of the vanilla reset method and enhance sample efficiency.
2232, Seeing Is Not Believing: Robust Reinforcement Learning Against Spurious Correlation
Wenhao Ding; Laixi Shi; Yuejie Chi; DING ZHAO;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we consider one critical type of robustness against spurious correlation, where different portions of the state do not have causality but have correlations induced by unobserved confounders.
2233, Online Control for Meta-optimization
Xinyi Chen; Elad Hazan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel approach based on control theory for the task of meta-optimization -- online learning of the best optimization algorithm, which generalizes hyperparameter tuning.
2234, Learning Layer-wise Equivariances Automatically Using Gradients
Tycho van der Ouderaa; Alexander Immer; Mark van der Wilk;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our goal is to allow for flexible symmetry constraints that can automatically be learned from data using gradients.
2235, Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
Balhae Kim; Hyungi Lee; Juho Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel Bayesian pseudocoreset construction method that operates on a function space.
2236, Uncovering The Hidden Dynamics of Video Self-supervised Learning Under Distribution Shifts
Pritam Sarkar; Ahmad Beirami; Ali Etemad;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we comprehensively study the behavior of six popular self-supervised methods (v-SimCLR, v-MOCO, v-BYOL, v-SimSiam, v-DINO, v-MAE) in response to various forms of natural distribution shift, i.e., ($\textit{i}$) context shift, ($\textit{ii}$) viewpoint shift, ($\textit{iii}$) actor shift, ($\textit{iv}$) source shift, ($\textit{v}$) generalizability to unknown classes (zero-shot), and ($\textit{vi}$) open-set recognition.
2237, ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation
Zhitong Gao; Shipeng Yan; Xuming He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a dual-level OOD detection framework to handle domain shift and semantic shift jointly.
2238, Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs
CHEN SHENGYUAN; Yunfeng Cai; Huang Fang; Xiao Huang; Mingming Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we proposed a differentiable framework - DiffLogic.
2239, A Bayesian Take on Gaussian Process Networks
Enrico Giudice; Jack Kuipers; Giusi Moffa;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work implements Monte Carlo and Markov Chain Monte Carlo methods to sample from the posterior distribution of network structures.
2240, Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack
Pratik Karmakar; Debabrota Basu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study design of black-box model extraction attacks that can *send minimal number of queries from* a *publicly available dataset* to a target ML model through a predictive API with an aim *to create an informative and distributionally equivalent replica* of the target.
2241, Convergence of Alternating Gradient Descent for Matrix Factorization
Rachel Ward; Tamara Kolda;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider alternating gradient descent (AGD) with fixed step size $\eta > 0$, applied to the asymmetric matrix factorization objective.
2242, Strategic Behavior in Two-sided Matching Markets with Prediction-enhanced Preference-formation
Stefania Ionescu; Yuhao Du; Kenneth Joseph; Ancsa Hannak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The present work shows that at the intersection of the two lies a previously unexplored type of strategic behavior: agents returning to the market (e.g., schools) can attack future predictions by interacting short-term non-optimally with their matches.
2243, A Path to Simpler Models Starts With Noise
Lesia Semenova; Harry Chen; Ronald Parr; Cynthia Rudin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose and study a mechanism of the data generation process, coupled with choices usually made by the analyst during the learning process, that determines the size of the Rashomon ratio.
2244, Unconstrained Pose Prior-Free Neural Radiance Field
Injae Kim; Minhyuk Choi; Hyunwoo Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose **UP-NeRF** (**U**nconstrained **P**ose-prior-free **Ne**ural **R**adiance **F**ield) to optimize NeRF with unconstrained image collections without camera pose prior.
2245, Convolutional Neural Networks Contain Structured Strong Lottery Tickets
Arthur da Cunha; Francesco D'Amore; Natale;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One of the main reasons for this gap is the limitations of the underlying mathematical tools used in formal analyses of the SLTH. In this paper, we overcome these limitations: we leverage recent advances in the multidimensional generalisation of the Random Subset-Sum Problem and obtain a variant that admits the stochastic dependencies that arise when addressing structured pruning in the SLTH.
2246, Towards Arbitrarily Expressive GNNs in $O(n^2)$ Space By Rethinking Folklore Weisfeiler-Lehman
Jiarui Feng; Lecheng Kong; Hao Liu; Dacheng Tao; Fuhai Li; Muhan Zhang; Yixin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the high expressive power, there are serious limitations in this line of research. In particular, (1) $k$-WL/FWL requires at least $O(n^k)$ space complexity, which is impractical for large graphs even when $k=3$; (2) The design space of $k$-WL/FWL is rigid, with the only adjustable hyper-parameter being $k$. To tackle the first limitation, we propose an extension, $(k, t)$-FWL. We theoretically prove that even if we fix the space complexity to $O(n^2)$ in $(k, t)$-FWL, we can construct an expressiveness hierarchy up to solving the graph isomorphism problem. To tackle the second problem, we propose $k$-FWL+, which considers any equivariant set as neighbors instead of all nodes, thereby greatly expanding the design space of $k$-FWL.
2247, Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
Kruno Lehman; Alain Durmus; Umut Simsekli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: A recent line of empirical studies has demonstrated that SGD might exhibit a heavy-tailed behavior in practical settings, and the heaviness of the tails might correlate with the overall performance. In this paper, we investigate the emergence of such heavy tails.
2248, Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks
Alexander Modell; Ian Gallagher; Emma Ceccherini; Nick Whiteley; Patrick Rubin-Delanchy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new algorithmic framework, Intensity Profile Projection, for learning continuous-time representations of the nodes of a dynamic network, characterised by a node set and a collection of instantaneous interaction events which occur in continuous time.
2249, Horospherical Decision Boundaries for Large Margin Classification in Hyperbolic Space
Xiran Fan; Chun-Hao Yang; Baba Vemuri;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel large margin classifier based on horospherical decision boundaries that leads to a geodesically convex optimization problem that can be optimized using any Riemannian gradient descent technique guaranteeing a globally optimal solution.
2250, Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning
Ming-Kun Xie; Jiahao Xiao; Hao-Zhe Liu; Gang Niu; Masashi Sugiyama; Sheng-Jun Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These limitations often result in the introduction of false positive labels or the neglect of true positive ones. To overcome these challenges, this paper proposes a novel solution called Class-Aware Pseudo-Labeling (CAP) that performs pseudo-labeling in a class-aware manner.
2251, Provably Safe Reinforcement Learning with Step-wise Violation Constraints
Nuoya Xiong; Yihan Du; Longbo Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an efficient algorithm SUCBVI, which guarantees $\widetilde{\mathcal{O}}(\sqrt{ST})$ or gap-dependent $\widetilde{\mathcal{O}}(S/\mathcal{C}_{\mathrm{gap}} + S^2AH^2)$ step-wise violation and $\widetilde{\mathcal{O}}(\sqrt{H^3SAT})$ regret.
2252, Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
Matteo Pagliardini; Daniele Paliotta; Martin Jaggi; François Fleuret;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We extend FlashAttention to accommodate a large class of attention sparsity patterns that, in particular, encompass key/query dropping and hashing-based attention.
2253, MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection
Junho Song; Keonwoo Kim; Jeonglyul Oh; Sungzoon Cho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these methods still suffer from an over-generalization issue and fail to deliver consistently high performance. To address this issue, we propose the MEMTO, a memory-guided Transformer using a reconstruction-based approach.
2254, Cross-modal Active Complementary Learning with Self-refining Correspondence
Yang Qin; Yuan Sun; Dezhong Peng; Joey Tianyi Zhou; Xi Peng; Peng Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To address the two problems, we propose a generalized Cross-modal Robust Complementary Learning framework (CRCL), which benefits from a novel Active Complementary Loss (ACL) and an efficient Self-refining Correspondence Correction (SCC) to improve the robustness of existing methods.
2255, Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
Yiwei Lu; Yaoliang Yu; Xinlin Li; Vahid Partovi Nia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although such practice works well empirically, it is largely a heuristic or ``training trick.'' We aim at shedding some light on these training tricks from the optimization perspective.
2256, Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
Dongsheng Ding; Chen-Yu Wei; Kaiqing Zhang; Alejandro Ribeiro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP).
2257, Towards Efficient and Accurate Winograd Convolution Via Full Quantization
Chen Tianqi; Weixiang Xu; Weihan Chen; Peisong Wang; Jian Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we alleviate these issues from two aspects. On the one hand, to keep the consistency among different transformation matrices after quantization, we propose to optimize them collaboratively under the unified objective of layer-wise feature map reconstruction error minimization. On the other hand, considering the significant range differences across the spatial dimension, we propose factorized-scale quantization for the output feature map in the Winograd domain, which can effectively balance the differences in values without sacrificing computational efficiency.
2258, Topological Verification for Image Retrieval Without Fine-tuning
Guoyuan An; Ju-hyeong Seon; Inkyu An; Yuchi Huo; Sung-eui Yoon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents an innovative approach to enhancing explainable image retrieval, particularly in situations where a fine-tuning set is unavailable.
2259, Long Sequence Hopfield Memory
Hamza Chaudhry; Jacob Zavatone-Veth; Dmitry Krotov; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by recent work on Dense Associative Memories, we expand the sequence capacity of these models by introducing a nonlinear interaction term, enhancing separation between the patterns.
2260, An Efficient Doubly-Robust Test for The Kernel Treatment Effect
Diego Martinez Taboada; Aaditya Ramdas; Edward Kennedy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new kernel-based test for distributional effects of the treatment.
2261, Tools for Verifying Proofs-of-Training-Data
Dami Choi; Yonadav Shavit; David Duvenaud;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the concept of a ``Proof-of-Training-Data'': any protocol that allows a model trainer to convince a Verifier of the training data that produced a set of model weights.
2262, Predict-then-Calibrate: A New Perspective of Robust Contextual LP
Chunlin Sun; Linyu Liu; Xiaocheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider a risk-sensitive version of the problem and propose a generic algorithm design paradigm called predict-then-calibrate.
2263, Exact Recovery and Bregman Hard Clustering of Node-attributed Stochastic Block Model
Maximilien Dreveton; Felipe Fernandes; Daniel Figueiredo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The contributions of this work provide insights into the fundamental limits and practical techniques for inferring community labels on node-attributed networks.
2264, Bayesian Target Optimisation for High-precision Holographic Optogenetics
Marcus Triplett; Marta Gajowa; Hillel Adesnik; Liam Paninski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, achieving precise optogenetic control of neural ensemble activity has remained fundamentally constrained by the problem of off-target stimulation (OTS): the inadvertent activation of nearby non-target neurons due to imperfect confinement of light onto target neurons. Here we propose a novel computational approach to this problem called Bayesian target optimisation.
2265, Sparse Modular Activation for Efficient Sequence Modeling
Liliang Ren; Yang Liu; Shuohang Wang; Yichong Xu; Chenguang Zhu; Cheng Xiang Zhai;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: There are two unanswered research questions regarding combining attention with SSMs: 1) How much extra attention is needed for SSMs on a per-task basis? 2) Can neural networks learn to dynamically activate their attention modules for improved quality-efficiency trade-offs? To answer these questions, we introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely and dynamically activate sub-modules for sequence elements in a differentiable manner.
2266, The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance
Jon Donnelly; Srikar Katta; Cynthia Rudin; Edward Browne;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new variable importance framework that quantifies the importance of a variable across the set of all good models and is stable across the data distribution.
2267, L-CAD: Language-based Colorization with Any-level Descriptions
zheng chang; Shuchen Weng; Peixuan Zhang; Yu Li; Si Li; Boxin Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a unified model to perform language-based colorization with any-level descriptions.
2268, BERT Lost Patience Won't Be Robust to Adversarial Slowdown
Zach Coalson; Gabriel Ritter; Rakesh Bobba; Sanghyun Hong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we systematically evaluate the robustness of multi-exit language models against adversarial slowdown.
2269, MIM4DD: Mutual Information Maximization for Dataset Distillation
Yuzhang Shang; Zhihang Yuan; Yan Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, we introduce mutual information (MI) as the metric to quantify the shared information between the synthetic and the real datasets, and devise MIM4DD numerically maximizing the MI via a newly designed optimizable objective within a contrastive learning framework to update the synthetic dataset.
2270, A Variational Perspective on High-Resolution ODEs
Hoomaan Maskan; Konstantinos Zygalakis; Alp Yurtsever;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel variational perspective using forced Euler-Lagrange equation that allows for studying high-resolution ODEs.
2271, Scalarization for Multi-Task and Multi-Domain Learning at Scale
Amelie Royer; Tijmen Blankevoort; Babak Ehteshami Bejnordi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we first devise a large-scale unified analysis of multi-domain and multi-task learning to better understand the dynamics of scalarization across varied task/domain combinations and model sizes. Following these insights, we then propose to leverage population-based training to efficiently search for the optimal scalarization weights when dealing with a large number of tasks or domains.
2272, BayesTune: Bayesian Sparse Deep Model Fine-tuning
Minyoung Kim; Timothy Hospedales;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we propose a novel Bayesian sparse fine-tuning algorithm: we place a (sparse) Laplace prior for each parameter of the FM, with the mean equal to the initial value and the scale parameter having a hyper-prior that encourages small scale.
2273, GLOBER: Coherent Non-autoregressive Video Generation Via GLOBal Guided Video DecodER
Mingzhen Sun; Weining Wang; Zihan Qin; Jiahui Sun; Sihan Chen; Jing Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Specifically, we propose a video auto-encoder, where a video encoder encodes videos into global features, and a video decoder, built on a diffusion model, decodes the global features and synthesizes video frames in a non-autoregressive manner.
2274, White-Box Transformers Via Sparse Rate Reduction
Yaodong Yu; Sam Buchanan; Druv Pai; Tianzhe Chu; Ziyang Wu; Shengbang Tong; Benjamin Haeffele; Yi Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent subspaces.
2275, Uniform Convergence with Square-Root Lipschitz Loss
Lijia Zhou; Zhen Dai; Frederic Koehler; Nati Srebro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We establish generic uniform convergence guarantees for Gaussian data in terms of the Radamacher complexity of the hypothesis class and the Lipschitz constant of the square root of the scalar loss function.
2276, PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
Hyemi Jang; Junsung Park; Dahuin Jung; Jaihyun Lew; Ho Bae; Sungroh Yoon;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Consequently, convolutions designed specifically for BSNs have been allowed only, limiting architectural flexibility. To overcome this limitation, we propose PUCA, a novel J-invariant U-Net architecture, for self-supervised denoising.
2277, Implicit Variational Inference for High-Dimensional Posteriors
Anshuk Uppal; Kristoffer Stensbo-Smidt; Wouter Boomsma; Jes Frellsen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex multimodal and correlated posteriors in high-dimensional spaces.
2278, Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management
Dhawal Gupta; Yinlam Chow; Azamat Tulepbergenov; Mohammad Ghavamzadeh; Craig Boutilier;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, RL for conversational chatbots remains challenging due to the extensive amount of online interactions required, which can be expensive and unsafe. To address this issue, we investigate the application of RL algorithms for offline learning, allowing us to circumvent the need for online interactions.
2279, DeepSimHO: Stable Pose Estimation for Hand-Object Interaction Via Physics Simulation
Rong Wang; Wei Mao; Hongdong Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address both issues, we present DeepSimHO: a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network.
2280, Topological Parallax: A Geometric Specification for Deep Perception Models
Abraham Smith; Michael Catanzaro; Gabrielle Angeloro; Nirav Patel; Paul Bendich;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: For safety and robustness of AI systems, we introduce _topological parallax_ as a theoretical and computational tool that compares a trained model to a reference dataset to determine whether they have similar multiscale geometric structure.
2281, Doubly Robust Peer-To-Peer Learning Protocol
Nicholas Franzese; Adam Dziedzic; Christopher A. Choquette-Choo; Mark R Thomas; Muhammad Ahmad Kaleem; Stephan Rabanser; Congyu Fang; Somesh Jha; Nicolas Papernot; Xiao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a peer-to-peer (P2P) learning scheme that is *doubly robust*: secure against malicious servers and robust to malicious clients.
2282, Bayesian Risk-Averse Q-Learning with Streaming Observations
Yuhao Wang; Enlu Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a robust reinforcement learning problem, where a learning agent learns from a simulated training environment.
2283, Enhancing Sharpness-Aware Optimization Through Variance Suppression
Bingcong Li; Georgios Giannakis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, existing approximate solutions of the inner maximization suffer from stochastic gradient noise, which leads to markedly perturbed update directions. The present contribution advocates variance-suppressed sharpness-aware optimization (VaSSO) to tackle this challenge by slightly biasing the gradient estimate employed for the inner maximization.
2284, Neural Sampling in Hierarchical Exponential-family Energy Based Model
Xingsi Dong; Si Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we introduce the Hierarchical Exponential-family Energy-based (HEE) model, which captures the dynamics of inference and learning.
2285, Learning Robust Statistics for Simulation-based Inference Under Model Misspecification
Daolang Huang; Ayush Bharti; Amauri Souza; Luigi Acerbi; Samuel Kaski;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose the first general approach to handle model misspecification that works across different classes of SBI methods.
2286, Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: An Eight-Month Demonstration of Seamless Brain-to-Text Communication
Chaofei Fan; Francis Willett; Nick Hahn; Donald Avansino; Foram Kamdar; Guy Wilson; Leigh Hochberg; Krishna V Shenoy; Jaimie Henderson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a method that enables self-recalibration of communication iBCIs without interrupting the user.
2287, Cognitive Model Discovery Via Disentangled RNNs
Kevin Miller; Maria Eckstein; Matt Botvinick; Zeb Kurth-Nelson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we adopt an alternative approach to learn parsimonious cognitive models directly from data.
2288, Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Andres Potapczynski; Marc Finzi; Geoff Pleiss; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple but general framework for large-scale linear algebra problems that recursively exploits compositional structure beyond what is possible with iterative routines based on matrix-vector multiplies.
2289, Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
Tyler Kastner; Murat Erdogdu; Amir-massoud Farahmand;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of learning models for risk-sensitive reinforcement learning.
2290, Adversarial Robustness Through Random Weight Sampling
Yanxiang Ma; Minjing Dong; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we introduce the Constrained Trainable Random Weight (CTRW), which adds random weight parameters to the optimization and includes a constraint guided by the upper and lower bounds to achieve better trade-offs between natural and robust accuracy.
2291, Tracking Most Significant Shifts in Nonparametric Contextual Bandits
Joe Suk; Samory Kpotufe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Quite importantly, we posit that the bandit problem, viewed local at a given context $X_t$, should not be affected by reward changes in other parts of context space $\cal X$. We therefore propose a notion of _change_ that better accounts for locality, and thus counts significantly less changes than $L$ and $V$.
2292, Collaborative Learning Via Prediction Consensus
Dongyang Fan; Celestine Mendler-Dünner; Martin Jaggi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To facilitate the exchange of expertise among agents, we propose a distillation-based method leveraging unlabeled auxiliary data, which is pseudo-labeled by the collective.
2293, Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives
Yahong Yang; Haizhao Yang; Yang Xiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper addresses the problem of nearly optimal Vapnik--Chervonenkis dimension (VC-dimension) and pseudo-dimension estimations of the derivative functions of deep neural networks (DNNs).
2294, Structure Learning with Adaptive Random Neighborhood Informed MCMC
Xitong Liang; Alberto Caron; Samuel Livingstone; Jim Griffin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel MCMC sampler, PARNI-DAG, for a fully-Bayesian approach to the problem of structure learning under observational data.
2295, $p$-Poisson Surface Reconstruction in Irrotational Flow from Point Clouds
Yesom Park; Taekyung Lee; Jooyoung Hahn; Myungjoo Kang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The aim of this paper is the reconstruction of a smooth surface from an unorganized point cloud sampled by a closed surface, with the preservation of geometric shapes, without any further information other than the point cloud.
2296, Learning Latent Causal Graphs with Unknown Interventions
Yibo Jiang; Bryon Aragam;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We establish conditions under which latent causal graphs are nonparametrically identifiable and can be reconstructed from unknown interventions in the latent space.
2297, Equivariant Few-Shot Learning from Pretrained Models
Sourya Basu; Pulkit Katdare; Prasanna Sattigeri; Vijil Chenthamarakshan; Katherine Driggs-Campbell; Payel Das; Lav Varshney;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Hence, we propose $\lambda$-\textit{equitune} that averages the features using \textit{importance weights}, $\lambda$s.
2298, Finding Counterfactually Optimal Action Sequences in Continuous State Spaces
Stratis Tsirtsis; Manuel Rodriguez;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, in many practical applications, the state of the environment is inherently continuous in nature. In this paper, we aim to fill this gap.
2299, ODPP: A Unified Algorithm Framework for Unsupervised Option Discovery Based on Determinantal Point Process
Jiayu Chen; Vaneet Aggarwal; Tian Lan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we show that diversity and coverage in unsupervised option discovery can indeed be unified under the same mathematical framework.
2300, Quantum Bayesian Optimization
Zhongxiang Dai; Gregory Kang Ruey Lau; Arun Verma; YAO SHU; Bryan Kian Hsiang Low; Patrick Jaillet;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we introduce the quantum-Gaussian process-upper confidence bound (Q-GP-UCB) algorithm.
2301, Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image
Yuki Kawana; Tatsuya Harada;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an end-to-end trainable, cross-category method for reconstructing multiple man-made articulated objects from a single RGBD image, focusing on part-level shape reconstruction and pose and kinematics estimation.
2302, Expert Load Matters: Operating Networks at High Accuracy and Low Manual Effort
Sara Sangalli; Ertunc Erdil; Ender Konukoglu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The trade-off between the model accuracy and the number of samples delegated to experts can be represented by a curve that is similar to an ROC curve, which we refer to as confidence operating characteristic (COC) curve. In this paper, we argue that deep neural networks should be trained by taking into account both accuracy and expert load and, to that end, propose a new complementary loss function for classification that maximizes the area under this COC curve.
2303, Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds
Paul Rosa; Slava Borovitskiy; Alexander Terenin; Judith Rousseau;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recently, computational tools for working with these models in geometric settings, such as when inputs lie on a Riemannian manifold, have been developed. This raises the question: can these intrinsic models be shown theoretically to lead to better performance, compared to simply embedding all relevant quantities into $\mathbb{R}^d$ and using the restriction of an ordinary Euclidean Gaussian process?To study this, we prove optimal contraction rates for intrinsic Matérn Gaussian processes defined on compact Riemannian manifolds.
2304, Minimax Risks and Optimal Procedures for Estimation Under Functional Local Differential Privacy
Lee Bonwoo; Jeongyoun Ahn; Cheolwoo Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we investigate how functional LDP preserves the statistical utility by analyzing minimax risks of univariate mean estimation as well as nonparametric density estimation.
2305, Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
Matthew Chang; Aditya Prakash; Saurabh Gupta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose to extract a factored representation of the scene that separates the agent (human hand) and the environment.
2306, An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations
Haoran Yang; Xiangyu Zhao; Yicong Li; Hongxu Chen; Guandong Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we innovatively propose a prompt-enhanced framework for GCL-based recommender systems, namely CPTPP, which can fully leverage the advantages of the original GCL protocol through prompt tuning.
2307, Non-Rigid Shape Registration Via Deep Functional Maps Prior
puhua jiang; Mingze Sun; Ruqi Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an unsupervised framework for non-rigid shape registration.
2308, Self-supervised Graph Neural Networks Via Low-Rank Decomposition
Liang Yang; Runjie Shi; Qiuliang Zhang; bingxin niu; Zhen Wang; Chuan Wang; Xiaochun Cao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: If the propagation in each ego-network is just between the nodes from the same class, the obtained representation matrix should follow the low-rank characteristic. To meet this requirement, this paper proposes the Low-Rank Decomposition-based GNNs (LRD-GNN-Matrix) by employing Low-Rank Decomposition to the attribute matrix.
2309, Locality-Aware Generalizable Implicit Neural Representation
Doyup Lee; Chiheon Kim; Minsu Cho; WOOK SHIN HAN;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the expressive power of the state-of-the-art modulation is limited due to its inability to localize and capture fine-grained details of data entities such as specific pixels and rays. To address this issue, we propose a novel framework for generalizable INR that combines a transformer encoder with a locality-aware INR decoder.
2310, Regularized Behavior Cloning for Blocking The Leakage of Past Action Information
Seokin Seo; HyeongJoo Hwang; Hongseok Yang; Kee-Eung Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, when the information about the actions executed in the past timesteps leaks into the observation histories, ILOH via BC often ends up imitating its own past actions, especially when the expert actions change slowly over time. In this paper, we address this catastrophic failure by proposing a principled regularization for BC, which we name Past Action Leakage Regularization (PALR).
2311, Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings
Sudhanshu Chanpuriya; Ryan Rossi; Anup Rao; Tung Mai; Nedim Lipka; Zhao Song; Cameron Musco;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel graph factorization model that leverages two nonnegative vectors per node to interpretably account for links between both similar and dissimilar nodes.
2312, Batch Bayesian Optimization For Replicable Experimental Design
Zhongxiang Dai; Quoc Phong Nguyen; Sebastian Tay; Daisuke Urano; Richalynn Leong; Bryan Kian Hsiang Low; Patrick Jaillet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, in these problems, practitioners may be risk-averse and hence prefer an input with both good average performance and small variability. To tackle both challenges, we propose the Batch Thompson Sampling for Replicable Experimental Design (BTS-RED) framework, which encompasses three algorithms.
2313, Deep Insights Into Noisy Pseudo Labeling on Graph Data
Botao WANG; Jia Li; Yang Liu; Jiashun Cheng; Yu Rong; Wenjia Wang; Fugee Tsung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to give deep insights of PL on graph learning models.
2314, Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
Cheng-Hao Tu; Hong-You Chen; Jike Zhong; Zheda Mai; Vardaan Pahuja; Tanya Berger-Wolf; Song Gao; Charles Stewart; Yu Su; Wei-Lun (Harry) Chao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present several effective solutions that maintain the accuracies of the missing classes and enhance overall, establishing a solid baseline for holistic transfer of pre-trained models with partial target data.
2315, Transportability for Bandits with Data from Different Environments
Alexis Bellot; Alan Malek; Silvia Chiappa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Most methods, however, typically rely solely on an agent's experimentation in a single environment (or multiple closely related environments). In this paper, we relax this assumption and consider the design of bandit algorithms from a combination of batch data and qualitative assumptions about the relatedness across different environments, represented in the form of causal models.
2316, Dense-Exponential Random Features: Sharp Positive Estimators of The Gaussian Kernel
Valerii Likhosherstov; Krzysztof M Choromanski; Kumar Avinava Dubey; Frederick Liu; Tamas Sarlos; Adrian Weller;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose parameterized, positive, non-trigonometric RFs which approximate Gaussian and softmax-kernels.
2317, Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities
Aleksandr Beznosikov; Martin Takac; Alexander Gasnikov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The three main techniques to reduce the total number of communication rounds and the cost of one such round are the similarity of local functions, compression of transmitted information, and local updates. In this paper, we combine all these approaches.
2318, Diversified Outlier Exposure for Out-of-Distribution Detection Via Informative Extrapolation
Jianing Zhu; Yu Geng; Jiangchao Yao; Tongliang Liu; Gang Niu; Masashi Sugiyama; Bo Han;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a novel framework, namely, Diversified Outlier Exposure (DivOE), for effective OOD detection via informative extrapolation based on the given auxiliary outliers.
2319, Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
Yijun Dong; Kevin Miller; Qi Lei; Rachel Ward;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we take an initial step toward a theoretical understanding of relational knowledge distillation (RKD), with a focus on semi-supervised classification problems.
2320, Spectral Co-Distillation for Personalized Federated Learning
Zihan Chen; Howard Yang; Tony Quek; Kai Fong Ernest Chong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To better capture similar (yet distinct) generic versus personalized model representations, we propose $\textit{spectral distillation}$, a novel distillation method based on model spectrum information.
2321, Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
Pengfei Wei; Lingdong Kong; Xinghua Qu; Yi Ren; Zhiqiang Xu; Jing Jiang; Xiang Yin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To better serve for adaptation, we propose several objectives to constrain the latent factors.
2322, Active Representation Learning for General Task Space with Applications in Robotics
Yifang Chen; Yingbing Huang; Simon Du; Kevin Jamieson; Guanya Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a general and versatile algorithmic and theoretic framework for \emph{active representation learning}, where the learner optimally chooses which source tasks to sample from.
2323, Sorting with Predictions
Xingjian Bai; Christian Coester;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore the fundamental problem of sorting through the lens of learning-augmented algorithms, where algorithms can leverage possibly erroneous predictions to improve their efficiency.
2324, Towards A Unified Framework of Contrastive Learning for Disentangled Representations
Stefan Matthes; Zhiwei Han; Hao Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we prove identifiability of the true latents for four contrastive losses studied in this paper, without imposing common independence assumptions.
2325, Bifurcations and Loss Jumps in RNN Training
Lukas Eisenmann; Zahra Monfared; Niclas Göring; Daniel Durstewitz;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In contrast to previous numerical algorithms for finding fixed points and common continuation methods, our algorithm provides $\textit{exact}$ results and returns fixed points and cycles up to high orders with surprisingly good scaling behavior.
2326, Convergence of Actor-Critic with Multi-Layer Neural Networks
Haoxing Tian; Alex Olshevsky; Yannis Paschalidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we are taking the natural next step and establish convergence using deep neural networks with an arbitrary number of hidden layers, thus closing a gap between theory and practice.
2327, Goal-conditioned Offline Planning from Curious Exploration
Marco Bagatella; Georg Martius;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In order to mitigate their occurrence, we propose to combine model-based planning over learned value landscapes with a graph-based value aggregation scheme.
2328, Adaptive Data Analysis in A Balanced Adversarial Model
Kobbi Nissim; Uri Stemmer; Eliad Tsfadia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This imbalance raises questions with respect to the applicability of the obtained hardness results -- an analyst who has complete knowledge of the underlying distribution $\cal{D}$ would have little need, if at all, to issue statistical queries to a mechanism which only holds a finite number of samples from $\cal{D}$. We consider more restricted adversaries, called \emph{balanced}, where each such adversary consists of two separated algorithms: The \emph{sampler} who is the entity that chooses the distribution and provides the samples to the mechanism, and the \emph{analyst} who chooses the adaptive queries, but does not have a prior knowledge of the underlying distribution.
2329, Counterfactually Fair Representation
Zhiqun Zuo; Mahdi Khalili; Xueru Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we focus on Counterfactual Fairness (CF), a fairness notion that is dependent on an underlying causal graph and first proposed by Kusner $\textit{et al.}$; it requires that the outcome an individual perceives is the same in the real world as it would be in a counterfactual world, in which the individual belongs to another social group.
2330, Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection
Yang Cao; Zeng Yihan; Hang Xu; Dan Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper aims at addressing the two problems simultaneously via a unified framework, under the condition of limited base categories.
2331, Networks Are Slacking Off: Understanding Generalization Problem in Image Deraining
Jinjin Gu; Xianzheng Ma; Xiangtao Kong; Yu Qiao; Chao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A prevailing perspective in deep learning encourages the use of highly complex training data, with the expectation that a richer image content knowledge will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discovered that this strategy does not enhance the generalization capability of these networks.
2332, CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning
Charles Guille-Escuret; Pau Rodriguez; David Vazquez; Ioannis Mitliagkas; Joao Monteiro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of OOD samples: unseen classes and adversarial perturbations.
2333, Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation
Lianghe Shi; Weiwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we adopt the effective gradual self-training method and replace vanilla self-training with adversarial self-training (AST).
2334, Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects
Chuanruo Ning; Ruihai Wu; Haoran Lu; Kaichun Mo; Hao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recognizing this limitation, we observe that despite their distinct shapes, different categories often share similar local geometries essential for manipulation, such as pullable handles and graspable edges - a factor typically underutilized in previous few-shot learning works. To harness this commonality, we introduce 'Where2Explore', an affordance learning framework that effectively explores novel categories with minimal interactions on a limited number of instances.
2335, An Optimal and Scalable Matrix Mechanism for Noisy Marginals Under Convex Loss Functions
Yingtai Xiao; Guanlin He; Danfeng Zhang; Daniel Kifer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose ResidualPlanner, a matrix mechanism for marginals with Gaussian noise that is both optimal and scalable.
2336, Learning Large-scale Neural Fields Via Context Pruned Meta-Learning
Jihoon Tack; Subin Kim; Sihyun Yu; Jaeho Lee; Jinwoo Shin; Jonathan Richard Schwarz;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce an efficient optimization-based meta-learning technique for large-scale neural field training by realizing significant memory savings through automated online context point selection.
2337, Nearly Tight Bounds For Differentially Private Multiway Cut
Mina Dalirrooyfard; Slobodan Mitrovic; Yuriy Nevmyvaka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the complexity of differential privacy for the min $s$-$t$ cut problem and show nearly tight lower and upper bounds where we achieve privacy at no cost for running time efficiency.
2338, Refining Diffusion Planner for Reliable Behavior Synthesis By Automatic Detection of Infeasible Plans
Kyowoon Lee; Seongun Kim; Jaesik Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel approach to refine unreliable plans generated by diffusion models by providing refining guidance to error-prone plans.
2339, Fast and Simple Spectral Clustering in Theory and Practice
Peter Macgregor;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a simple spectral clustering algorithm based on a vertex embedding with $O(\log(k))$ vectors computed by the power method.
2340, Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders
Lai Wei; Muhammad Qasim Elahi; Mahsa Ghasemi; Murat Kocaoglu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the lower bound, we design an algorithm that can utilize the causal structure to accelerate the learning process and take informative and rewarding interventions.
2341, Does Visual Pretraining Help End-to-End Reasoning?
Chen Sun; Calvin Luo; Xingyi Zhou; Anurag Arnab; Cordelia Schmid;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a simple and general self-supervised framework which compresses each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context.
2342, Interpretable Graph Networks Formulate Universal Algebra Conjectures
Francesco Giannini; Stefano Fioravanti; Oguzhan Keskin; Alisia Lupidi; Lucie Charlotte Magister; Pietro Lió; Pietro Barbiero;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While topological representations would enable the analysis of such properties using graph neural networks, the limited transparency and brittle explainability of these models hinder their straightforward use to empirically validate existing conjectures or to formulate new ones. To bridge these gaps, we propose a general algorithm generating AI-ready datasets based on UA's conjectures, and introduce a novel neural layer to build fully interpretable graph networks.
2343, Metis: Understanding and Enhancing Regular Expressions in Network
Zhengxin Zhang; Yucheng Huang; Guanglin Duan; Qing Li; Dan Zhao; Yong Jiang; Lianbo Ma; Xi Xiao; Hengyang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Metis, a general framework that converts REs to network device affordable models for superior accuracy and throughput by taking advantage of REs' expert knowledge and NNs' learning ability.
2344, FABind: Fast and Accurate Protein-Ligand Binding
Qizhi Pei; Kaiyuan Gao; Lijun Wu; Jinhua Zhu; Yingce Xia; Shufang Xie; Tao Qin; Kun He; Tie-Yan Liu; Rui Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose FABind, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding.
2345, Neural Processes with Stability
Huafeng Liu; Liping Jing; Jian Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide theoretical guidelines for deriving stable solutions with high generalization by introducing the notion of algorithmic stability into NPs, which can be flexible to work with various NPs and achieves less biased approximation with theoretical guarantees.
2346, Taking The Neural Sampling Code Very Seriously: A Data-driven Approach for Assessing Generative Models of The Visual System
Suhas Shrinivasan; Konstantin-Klemens Lurz; Kelli Restivo; George Denfield; Andreas Tolias; Edgar Walker; Fabian Sinz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we propose a novel and mathematical formalization of NSC, that (a) allows us to directly fit NSC generative models to recorded neuronal activity in response to natural images, (b) formulate richer and more flexible generative models, and (c) employ standard metrics to quantitatively evaluate different generative models under NSC.
2347, Truncating Trajectories in Monte Carlo Policy Evaluation: An Adaptive Approach
Riccardo Poiani; Nicole Nobili; Alberto Maria Metelli; Marcello Restelli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, it suggests that adaptive data collection strategies that spend the available budget sequentially might be able to allocate a larger portion of transitions in timesteps in which more accurate sampling is required to reduce the variance of the final estimate. Building on these findings, we present an *adaptive* algorithm called **R**obust and **I**terative **D**ata collection strategy **O**ptimization (RIDO).
2348, Optimal Preconditioning and Fisher Adaptive Langevin Sampling
Michalis Titsias;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This yields as the optimal preconditioning an inverse Fisher information covariance matrix, where the covariance matrix is computed as the outer product of log target gradients averaged under the target. We apply this result to the Metropolis adjusted Langevin algorithm (MALA) and derive a computationally efficient adaptive MCMC scheme that learns the preconditioning from the history of gradients produced as the algorithm runs.
2349, Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network
Bochen Lyu; Zhanxing Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes to investigate a new proxy model of standard linear network, rank-1 linear network, where each weight matrix is parameterized as a rank-1 form.
2350, Behavior Alignment Via Reward Function Optimization
Dhawal Gupta; Yash Chandak; Scott Jordan; Philip Thomas; Bruno da Silva;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While potential-based reward shaping has been proposed as a solution, we demonstrate its limitations in resolving sub-optimalities resulting from various design choices, and its potential to significantly degrade performance when used naively. To overcome these challenges, we propose a novel framework that employs a bi-level objective for learning a ``behavior alignment reward''.
2351, On The Statistical Consistency of Risk-Sensitive Bayesian Decision-Making
Prateek Jaiswal; Harsha Honnappa; Vinayak Rao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study data-driven decision-making problems in the Bayesian framework, where the expectation in the Bayes risk is replaced by a risk-sensitive entropic risk measure with respect to the posterior distribution.
2352, Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms
Yashaswini Murthy; Mehrdad Moharrami; R. Srikant;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, an open problem has been to obtain meaningful performance bounds for approximate PI and RL algorithms for the average-reward setting. In this paper, we solve this open problem by obtaining the first non-trivial finite time error bounds for average-reward MDPs which go to zero in the limit as policy evaluation and policy improvement errors go to zero.
2353, ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning
Mingyu Xu; Zheng Lian; Lei Feng; Bin Liu; Jianhua Tao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel framework for noisy PLL with theoretical guarantees, called ``Adjusting Label Importance Mechanism (ALIM)''.
2354, Feature Learning for Interpretable, Performant Decision Trees
Jack Good; Torin Kovach; Kyle Miller; Artur Dubrawski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the first system to alternate sparse feature learning with differentiable decision tree construction to produce small, interpretable trees with good performance.
2355, Provably Efficient Personalized Multi-Objective Decision Making Via Comparative Feedback
Han Shao; Lee Cohen; Avrim Blum; Yishay Mansour; Aadirupa Saha; Matthew Walter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a multi-objective decision making framework that accommodates different user preferences over objectives, where preferences are learned via policy comparisons.
2356, Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning Via Finite-time Convergence
Yuki Takezawa; Ryoma Sato; Han Bao; Kenta Niwa; Makoto Yamada;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this study, we propose a novel topology combining both a fast consensus rate and small maximum degree called the Base-$\left(k+1\right)$ Graph.
2357, Policy Space Diversity for Non-Transitive Games
Jian Yao; Weiming Liu; Haobo Fu; Yaodong Yang; Stephen McAleer; Qiang Fu; Wei Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A major weakness with existing diversity metrics is that a more diverse (according to their diversity metrics) population does not necessarily mean (as we proved in the paper) a better approximation to a NE. To alleviate this problem, we propose a new diversity metric, the improvement of which guarantees a better approximation to a NE.
2358, Efficient Beam Tree Recursion
Jishnu Ray Chowdhury; Cornelia Caragea;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we identify the main bottleneck in BT-RvNN's memory usage to be the entanglement of the scorer function and the recursive cell function.
2359, Fair Adaptive Experiments
Waverly Wei; Xinwei Ma; Jingshen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, when treatment is expected to be extremely beneficial to certain groups of participants, it is more appropriate to expose many of these participants to the favorable treatment. In response to these challenges, we propose a fair adaptive experiment strategy that simultaneously enhances data use efficiency, achieves an ``envy-free'' treatment assignment guarantee, and improves the overall welfare of participants.
2360, How Re-sampling Helps for Long-Tail Learning?
Jiang-Xin Shi; Tong Wei; Yuke Xiang; Yu-Feng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Unfortunately, recent studies claim that re-sampling brings negligible performance improvements in modern long-tail learning tasks. This paper aims to investigate this phenomenon systematically.
2361, Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time
Xinyuan Cao; Santosh Vempala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We give a polynomial-time algorithm for learning high-dimensional halfspaces with margins in $d$-dimensional space to within desired TV distance when the ambient distribution is an unknown affine transformation of the $d$-fold product of an (unknown) symmetric one-dimensional logconcave distribution, and the halfspace is introduced by deleting at least an $\epsilon$ fraction of the data in one of the component distributions.
2362, ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
Björn Deiseroth; Mayukh Deb; Samuel Weinbach; Manuel Brack; Patrick Schramowski; Kristian Kersting;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present AtMan that provides explanations of generative transformer models at almost no extra cost.
2363, Type-to-Track: Retrieve Any Object Via Prompt-based Tracking
Pha Nguyen; Kha Gia Quach; Kris Kitani; Khoa Luu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces a novel paradigm for Multiple Object Tracking called Type-to-Track, which allows users to track objects in videos by typing natural language descriptions.
2364, Rethinking The Backward Propagation for Adversarial Transferability
Wang Xiaosen; Kangheng Tong; Kun He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we identify that non-linear layers (e.g., ReLU, max-pooling, etc.) truncate the gradient during backward propagation, making the gradient w.r.t.input image imprecise to the loss function.
2365, DefTrack: Deformable Tracking
Xinyu Zhou; Pinxue Guo; Lingyi Hong; Jinglun Li; Wei Zhang; Weifeng Ge; Wenqiang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance. To alleviate this issue, we propose a novel tracking paradigm named deformable tracking, consisting of a deformable memory and memory deformable attention, which can adaptively assist the search region in selecting the most relevant historical information from reference features.
2366, Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
Runqi Lin; Chaojian Yu; Tongliang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, SSAT suffers from catastrophic overfitting (CO), which manifests as a highly distorted classifier that is vulnerable to multi-step adversarial attacks. In this work, we observe that some adversarial examples generated on the SSAT-trained network exhibit anomalous behaviour, that is, although these training samples are generated by the inner maximization process, the loss of them decreases instead, which we called abnormal adversarial examples (AAEs).
2367, Quantum Speedups for Stochastic Optimization
Aaron Sidford; Chenyi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of minimizing a continuous function $f$ given quantum access to a stochastic (sub-)gradient oracle.
2368, Practical Differentially Private Hyperparameter Tuning with Subsampling
Antti Koskela; Tejas Kulkarni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Commonly, these algorithms still considerably increase the DP privacy parameter $\varepsilon$ over non-tuned DP ML model training and can be computationally heavy as evaluating each hyperparameter candidate requires a new training run. We focus on lowering both the DP bounds and the computational cost of these methods by using only a random subset of the sensitive data for the hyperparameter tuning and by appropriately extrapolating the optimal values to a larger dataset.
2369, Multi-Agent First Order Constrained Optimization in Policy Space
Youpeng Zhao; Yaodong Yang; Zhenbo Lu; Wengang Zhou; Houqiang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a novel approach called Multi-Agent First Order Constrained Optimization in Policy Space (MAFOCOPS), which effectively addresses the dual objectives of attaining satisfactory performance and enforcing safety constraints.
2370, DAMEX: Dataset-aware Mixture-of-Experts for Visual Understanding of Mixture-of-datasets
Yash Jain; Harkirat Behl; Zsolt Kira; Vibhav Vineet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present Mixture-of-Experts as a solution, highlighting that MoE are much more than a scalability tool.
2371, Double Gumbel Q-Learning
David Yu-Tung Hui; Aaron Courville; Pierre-Luc Bacon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Drawing inspiration from the generalized method of moments, we present DoubleGum, a Q-Learning algorithm for discrete and continuous control that minimizes the TD errors under our distributional assumption.
2372, The Gain from Ordering in Online Learning
Vasilis Kontonis; Mingchen Ma; Christos Tzamos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: When the examples of $X$ are drawn i.i.d.\ from the uniform distribution on the sphere, we present an algorithm based on the greedy heuristic of selecting ``easiest'' examples first that achieves a $\log d$-approximation of the optimal regret.
2373, Sub-optimality of The Naive Mean Field Approximation for Proportional High-dimensional Linear Regression
Jiaze Qiu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, existing theory often does not explain empirical observations noted in the existing literature. In this paper, we take a step towards addressing these problems by deriving sharp asymptotic characterizations for the NMF approximation in high-dimensional linear regression.
2374, Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
Stefano Massaroli; Michael Poli; Dan Fu; Hermann Kumbong; David Romero; Rom Parnichkun; Aman Timalsina; Quinn McIntyre; Beidi Chen; Atri Rudra; Ce Zhang; Christopher Ré; Stefano Ermon; Yoshua Bengio;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we seek to enable constant-memory, recurrent inference in any pre-trained long convolution architecture to reduce memory footprint and increase throughput during generation.
2375, Rigorous Runtime Analysis of MOEA/D for Solving Multi-Objective Minimum Weight Base Problems
Anh Viet Do; Aneta Neumann; Frank Neumann; Andrew Sutton;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the multi-objective minimum weight base problem, an abstraction of classical NP-hard combinatorial problems such as the multi-objective minimum spanning tree problem.
2376, Robust Contrastive Language-Image Pretraining Against Data Poisoning and Backdoor Attacks
Wenhan Yang; Jingdong Gao; Baharan Mirzasoleiman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose ROCLIP, the first effective method for robust pre-training multimodal vision-language models against targeted data poisoning and backdoor attacks.
2377, EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks
Zihang Shao; Chaoran Feng; Yaxin Li; Xuanye Fang; Jiangrong Shen; Qi Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These strategies lack a complete training model and require gradient approximation. To overcome these limitations, we propose a novel learning method named Joint Excitatory Inhibitory Cycle Iteration learning for Deep Spiking Neural Networks (EICIL) that integrates both excitatory and inhibitory behaviors inspired by the signal transmission of biological neurons.
2378, An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
Marc Jourdan; Rémy Degenne; Emilie Kaufmann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose EB-TC$\varepsilon$, a novel sampling rule for $\varepsilon$-best arm identification in stochastic bandits.
2379, RePo: Resilient Model-Based Reinforcement Learning By Regularizing Posterior Predictability
Chuning Zhu; Max Simchowitz; Siri Gadipudi; Abhishek Gupta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This leaves them susceptible to spurious variations -- changes in task-irrelevant components such as background distractors or lighting conditions. In this paper, we propose a visual model-based RL method that learns a latent representation resilient to such spurious variations.
2380, A Guide Through The Zoo of Biased SGD
Yury Demidovich; Grigory Malinovsky; Igor Sokolov; Peter Richtarik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing literature on SGD with biased estimators lacks coherence since each new paper relies on a different set of assumptions, without any clear understanding of how they are connected, which may lead to confusion. We address this gap by establishing connections among the existing assumptions, and presenting a comprehensive map of the underlying relationships.
2381, Training Biological Recurrent Neural Networks on Cognitive Tasks with Long-term Dependencies
Wayne Soo; Vishwa Goudar; Xiao-Jing Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose multiple approaches based on the idea of specialized skip-connections through time to support the emergence of task-relevant dynamics, and subsequently reinstitute biological plausibility by reverting to the original architecture.
2382, Moment Matching Denoising Gibbs Sampling
Mingtian Zhang; Alex Hawkins-Hooker; Brooks Paige; David Barber;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an efficient sampling framework: (pseudo)-Gibbs sampling with moment matching, which enables effective sampling from the underlying clean model when given a noisy model that has been well-trained via DSM.
2383, Efficient Low-rank Backpropagation for Vision Transformer Adaptation
Yuedong Yang; Hung-Yueh Chiang; Guihong Li; Diana Marculescu; Radu Marculescu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This issue originates from the computationally demanding matrix multiplications required during the backpropagation process through linear layers in ViT. In this paper, we tackle this problem by proposing a new Low-rank BackPropagation via Walsh-Hadamard Transformation (LBP-WHT) method.
2384, Policy Gradient for Rectangular Robust Markov Decision Processes
Navdeep Kumar; Esther Derman; Matthieu Geist; Kfir Y. Levy; Shie Mannor;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce robust policy gradient (RPG), a policy-based method that efficiently solves rectangular robust Markov decision processes (MDPs).
2385, Robust Low-rank Training Via Approximate Orthonormal Constraints
Dayana Savostianova; Emanuele Zangrando; Gianluca Ceruti; Francesco Tudisco;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, we introduce a robust low-rank training algorithm that maintains the network's weights on the low-rank matrix manifold while simultaneously enforcing approximate orthonormal constraints.
2386, Variational Gaussian Processes for Linear Inverse Problems
Thibault RANDRIANARISOA; Botond Szabo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider both mildly and severely ill-posed inverse problems and work with the popular inducing variable variational Bayes approach proposed by Titsias [Titsias, 2009].
2387, Boundary Guided Mixing Trajectory for Semantic Control with Diffusion Models
Ye Zhu; Yu Wu; Zhiwei Deng; Olga Russakovsky; Yan Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present our BoundaryDiffusion method for efficient, effective and light-weight semantic control with frozen pre-trained DDMs, without learning any extra networks.
2388, Frequency Domain-Based Dataset Distillation
Donghyeok Shin; Seungjae Shin; Il-chul Moon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents FreD, a novel parameterization method for dataset distillation, which utilizes the frequency domain to distill a small-sized synthetic dataset from a large-sized original dataset.
2389, SLaM: Student-Label Mixing for Distillation with Unlabeled Examples
Vasilis Kontonis; Fotis Iliopoulos; Khoa Trinh; Cenk Baykal; Gaurav Menghani; Erik Vee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a principled method for knowledge distillation with unlabeled examples that we call Student-Label Mixing (SLaM) and we show that it consistently improves over prior approaches by evaluating it on several standard benchmarks.
2390, Online Learning Under Adversarial Nonlinear Constraints
Pavel Kolev; Georg Martius; Michael Muehlebach;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In many applications, learning systems are required to process continuous non-stationary data streams. We study this problem in an online learning framework and propose an algorithm that can deal with adversarial time-varying and nonlinear constraints.
2391, Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency
Xiyang Liu; Prateek Jain; Weihao Kong; Sewoong Oh; Arun Suggala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the canonical problem of linear regression under $(\varepsilon,\delta)$-differential privacy when the datapoints are sampled i.i.d.~from a distribution and a fraction of response variables are adversarially corrupted.
2392, Understanding and Improving Ensemble Adversarial Defense
Yian Deng; Tingting Mu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Guided by the theory, we propose an effective approach to further improve ensemble adversarial defense, referred to as the interactive global adversarial training (iGAT).
2393, Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization
Sanath Kumar Krishnamurthy; Ruohan Zhan; Susan Athey; Emma Brunskill;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new family of computationally efficient bandit algorithms for the stochastic contextual bandit settings, with the flexibility to be adapted for cumulative regret minimization (with near-optimal minimax guarantees) and simple regret minimization (with SOTA guarantees).
2394, A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Thomas FEL; Victor Boutin; Louis Béthune; Remi Cadene; Mazda Moayeri; Léo Andéol; Mathieu Chalvidal; Thomas Serre;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While these two steps are shared across methods, they all differ in their specific implementations. Here, we introduce a unifying theoretical framework that comprehensively defines and clarifies these two steps.
2395, State Sequences Prediction Via Fourier Transform for Representation Learning
Mingxuan Ye; Yufei Kuang; Jie Wang; Yang Rui; Wengang Zhou; Houqiang Li; Feng Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, many existing methods do not fully exploit the structural information inherent in sequential state signals, which can potentially improve the quality of long-term decision-making but is difficult to discern in the time domain. To tackle this problem, we propose State Sequences Prediction via Fourier Transform (SPF), a novel method that exploits the frequency domain of state sequences to extract the underlying patterns in time series data for learning expressive representations efficiently.
2396, Convolutional Neural Operators for Robust and Accurate Learning of PDEs
Bogdan Raonic; Roberto Molinaro; Tim De Ryck; Tobias Rohner; Francesca Bartolucci; Rima Alaifari; Siddhartha Mishra; Emmanuel de Bézenac;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Although very successfully used in conventional machine learning, convolution based neural network architectures -- believed to be inconsistent in function space -- have been largely ignored in the context of learning solution operators of PDEs. Here, we present novel adaptations for convolutional neural networks to demonstrate that they are indeed able to process functions as inputs and outputs.
2397, Optimize Planning Heuristics to Rank, Not to Estimate Cost-to-Goal
Leah Chrestien; Stefan Edelkamp; Antonin Komenda; Tomas Pevny;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work revisits the necessary and sufficient conditions of strictly optimally efficient heuristics for forward search algorithms, mainly A* and greedy best-first search, which expand only states on the returned optimal path.
2398, Efficient Training of Energy-Based Models Using Jarzinsky Equality
Davide Carbone; Mengjian Hua; Simon Coste; Eric Vanden-Eijnden;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we introduce a modification of the unadjusted Langevin algorithm (ULA) in which each walker acquires a weight that enables the estimation of the gradient of the cross-entropy at any step during GD, thereby bypassing sampling biases induced by slow mixing of ULA.
2399, Restless Bandits with Average Reward: Breaking The Uniform Global Attractor Assumption
Yige Hong; Qiaomin Xie; Yudong Chen; Weina Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a general, simulation-based framework that converts any single-armed policy into a policy for the original $N$-armed problem.
2400, Tanimoto Random Features for Scalable Molecular Machine Learning
Austin Tripp; Sergio Bacallado; Sukriti Singh; José Miguel Hernández-Lobato;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Because the Tanimoto coefficient is positive definite it can be used as a kernelin machine learning algorithms on molecules. In this paper we propose two kinds novel random features to allow this kernel to scale to large datasets,and in the process discover a novel extension of the kernel to real vectors.
2401, Improvements on Uncertainty Quantification for Node Classification Via Distance Based Regularization
Russell Hart; Linlin Yu; Yifei Lou; Feng Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To help alleviate the identified drawbacks, we propose a distance-based embedding regularization.
2402, HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds
Gang Zhang; Chen Junnan; Guohuan Gao; Jianmin Li; Xiaolin Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose HEDNet, a hierarchical encoder-decoder network for 3D object detection, which leverages encoder-decoder blocks to capture long-range dependencies among features in the spatial space, particularly for large and distant objects.
2403, On The Exploration of Local Significant Differences For Two-Sample Test
Zhijian Zhou; Jie Ni; Jia-He Yao; Wei Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the ME$_\text{MaBiD}$, an effective test for two-sample testing, and the basic idea is to exploit local information by multiple Mahalanobis kernels and introduce bi-directional hypothesis for testing.
2404, Enhancing Adversarial Robustness Via Score-Based Optimization
Boya Zhang; Weijian Luo; Zhihua Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce a novel adversarial defense scheme named ScoreOpt, which optimizes adversarial samples at test-time, towards original clean data in the direction guided by score-based priors.
2405, Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models
Weijian Luo; Tianyang Hu; Shifeng Zhang; Jiacheng Sun; Zhenguo Li; Zhihua Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we consider learning from pre-trained DMs and transferring their knowledge to other generative models in a data-free fashion.
2406, Bridging The Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
Zhimin Chen; Bing Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, their potential to enrich 3D scene representation learning is largely untapped due to the existence of the domain gap. In this work, we propose an innovative methodology called Bridge3D to address this gap by pre-training 3D models using features, semantic masks, and captions sourced from foundation models.
2407, Debiasing Conditional Stochastic Optimization
Lie He; Shiva Kasiviswanathan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the conditional stochastic optimization (CSO) problem which covers a variety of applications including portfolio selection, reinforcement learning, robust learning, causal inference, etc.
2408, Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
Chuanbo Hua; Federico Berto; Michael Poli; Stefano Massaroli; Jinkyoo Park;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present GraphSplineNets, a novel deep-learning method to speed up the simulation of physical systems by reducing the grid size and number of iteration steps of deep surrogate models.
2409, Random Cuts Are Optimal for Explainable K-Medians
Konstantin Makarychev; Liren Shan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that the RandomCoordinateCut algorithm gives the optimal competitive ratio for explainable $k$-medians in $\ell_1$.
2410, Adversarial Attacks on Online Learning to Rank with Click Feedback
Jinhang Zuo; Zhiyao Zhang; Zhiyong Wang; Shuai Li; Mohammad Hajiesmaili; Adam Wierman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper studies attack strategies against multiple variants of OLTR.
2411, Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization
Yueming LYU;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, scaling up to high-dimensional problems with good query efficiency remains challenging. This paper proposes a novel Rank-1 Lattice Targeted Sampling (RLTS) technique to address this issue.
2412, Enhancing Minority Classes By Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification
Jintong Gao; He Zhao; Zhuo Li; Dandan Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an adaptive image-mixing method based on optimal transport (OT) to incorporate both class-level and sample-level information, which is able to generate semantically reasonable and meaningful mixed images for minority classes.
2413, Multiply Robust Federated Estimation of Targeted Average Treatment Effects
Larry Han; Zhu Shen; Jose Zubizarreta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel federated approach to derive valid causal inferences for a target population using multi-site data.
2414, Diffused Redundancy in Pre-trained Representations
Vedant Nanda; Till Speicher; John Dickerson; Krishna Gummadi; Soheil Feizi; Adrian Weller;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations.
2415, Sharp Spectral Rates for Koopman Operator Learning
Vladimir Kostic; Karim Lounici; Pietro Novelli; Massimiliano Pontil;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we present for the first time non-asymptotic learning bounds for the Koopman eigenvalues and eigenfunctions.
2416, CS-Isolate: Extracting Hard Confident Examples By Content and Style Isolation
Yexiong Lin; Yu Yao; Xiaolong Shi; Mingming Gong; Xu Shen; Dong Xu; Tongliang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we find that a key reason for some hard examples being close to the decision boundary is due to the entanglement of style factors with content factors.
2417, Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL Via Alternating Stationary Distribution Correction Estimation
Daiki E. Matsunaga; Jongmin Lee; Jaeseok Yoon; Stefanos Leonardos; Pieter Abbeel; Kee-Eung Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we introduce AlberDICE,an offline MARL algorithm that alternatively performs centralized training of individual agents based on stationary distribution optimization.
2418, Hybrid Policy Optimization from Imperfect Demonstrations
Hanlin Yang; Chao Yu; peng sun; Siji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel RL algorithm called HYbrid Policy Optimization (HYPO), which uses a small number of imperfect demonstrations to accelerate an agent's online learning process.
2419, On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
Jia Lin Hau; Erick Delage; Mohammad Ghavamzadeh; Marek Petrik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we show that these popular decompositions for Conditional-Value-at-Risk (CVaR) and Entropic-Value-at-Risk (EVaR) are inherently suboptimal regardless of the discretization level.
2420, ODE-based Recurrent Model-free Reinforcement Learning for POMDPs
Xuanle Zhao; Duzhen Zhang; Han Liyuan; Tielin Zhang; Bo Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To help the agent extract more dynamics-related information, we present a novel ODE-based recurrent model combines with model-free reinforcement learning (RL) framework to solve partially observable Markov decision processes (POMDPs).
2421, Echoes Beyond Points: Unleashing The Power of Raw Radar Data in Multi-modality Fusion
Yang Liu; Feng Wang; Naiyan Wang; ZHAO-XIANG ZHANG;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel method to skip the existing radar signal processing pipeline and then incorporate the radar raw data with other sensors.
2422, Large Language Models Can Implement Policy Iteration
Ethan Brooks; Logan Walls; Richard L Lewis; Satinder Singh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we demonstrate a method for implementing policy iteration using a large language model.
2423, Sample Efficient Reinforcement Learning in Mixed Systems Through Augmented Samples and Its Applications to Queueing Networks
Honghao Wei; Xin Liu; Weina Wang; Lei Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a sample-efficient RL method that accelerates learning by generating augmented data samples.
2424, Disentanglement Via Latent Quantization
Kyle Hsu; William Dorrell; James Whittington; Chelsea Finn; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we construct an inductive bias aimed at matching the compositional nature of data.
2425, Certified Robustness Via Dynamic Margin Maximization and Improved Lipschitz Regularization
Mahyar Fazlyab; Taha Entesari; Aniket Roy; Rama Chellappa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a result, there has been an increasing interest in developing training procedures that can directly manipulate the decision boundary in the input space. In this paper, we build upon recent developments in this category by developing a robust training algorithm whose objective is to increase the margin in the output (logit) space while regularizing the Lipschitz constant of the model along vulnerable directions.
2426, Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products
Tamas Sarlos; Xingyou Song; David Woodruff; Richard Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by fast algorithms in natural language processing, we study low rank approximation in the entrywise transformed setting where we want to find a good rank $k$ approximation to $f(U \cdot V)$, where $U, V^\top \in \mathbb{R}^{n \times r}$ are given, $r = O(\log(n))$, and $f(x)$ is a general scalar function.
2427, Normalization-Equivariant Neural Networks with Application to Image Denoising
Sébastien Herbreteau; Emmanuel Moebel; Charles Kervrann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we introduce affine-constrained convolutions and channel-wise sort pooling layers as surrogates and show that these two architectural modifications do preserve normalization-equivariance without loss of performance.
2428, Cascading Bandits with Delayed Feedback and Action Frequency Control
Dairui Wang; Junyu Cao; Yan Zhang; Wei Qi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider a novel cascading bandits setting, where individual messages from a selected list are sent to a user periodically.
2429, Trial Matching: Capturing Variability with Data-constrained Spiking Neural Networks
Christos Sourmpis; Carl Petersen; Wulfram Gerstner; Guillaume Bellec;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We focus specifically on the difficulty to match the trial-to-trial variability in the data.
2430, GradOrth: A Simple Yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
Sima Behpour; Thang Long Doan; Xin Li; Wenbin He; Liang Gou; Liu Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we propose a novel approach called GradOrth to facilitate OOD detection based on one intriguing observation that the important features to identify OOD data lie in the lower-rank subspace of in-distribution (ID) data.
2431, Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
Miltiadis (Miltos) Kofinas; Erik Bekkers; Naveen Nagaraja; Efstratios Gavves;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Systems of interacting objects often evolve under the influence of underlying field effects that govern their dynamics, yet previous works have abstracted away from such effects, and assume that systems evolve in a vacuum. In this work, we focus on discovering these fields, and infer them from the observed dynamics alone, without directly observing them.
2432, Truly Scale-Equivariant Deep Nets with Fourier Layers
Md Ashiqur Rahman; Raymond A. Yeh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, they do not consider anti-aliasing as they formulate the down-scaling operation in the continuous domain. To address this shortcoming, we directly formulate down-scaling in the discrete domain with consideration of anti-aliasing.
2433, Learning Descriptive Image Captioning Via Semipermeable Maximum Likelihood Estimation
Zihao Yue; Anwen Hu; Liang Zhang; Qin Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce Semipermeable MaxImum Likelihood Estimation (SMILE), which allows richness optimization while blocks conciseness optimization, thus encouraging the model to generate longer captions with more details.
2434, Spatial-frequency Channels, Shape Bias, and Adversarial Robustness
Ajay Subramanian; Elena Sizikova; Najib Majaj; Denis Pelli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we introduce critical band masking as a task for network-human comparison and test 16 humans and 76 neural networks on 16-way ImageNet categorization in the presence of narrowband noise.
2435, IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
Zhenchao Jin; Xiaowei Hu; Lingting Zhu; Luchuan Song; Li Yuan; Lequan Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To alleviate the issues, we propose a novel \textbf{I}ntervention-\textbf{D}riven \textbf{R}elation \textbf{Net}work (\textbf{IDRNet}), which leverages a deletion diagnostics procedure to guide the modeling of contextual relations among different pixels.
2436, Circuit As Set of Points
Jialv Zou; Xinggang Wang; Jiahao Guo; Wenyu Liu; Qian Zhang; Chang Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In our work, we propose a novel perspective for circuit design by treating circuit components as point clouds and using point cloud perception methods to extract features from the circuit.
2437, SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization
Hao Dong; Ismail Nejjar; Han Sun; Eleni Chatzi; Olga Fink;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To overcome the challenges of achieving domain generalization in multi-modal scenarios, we propose SimMMDG, a simple yet effective multi-modal DG framework.
2438, Reusing Pretrained Models By Multi-linear Operators for Efficient Training
Yu Pan; Ye Yuan; Yichun Yin; Zenglin Xu; Lifeng Shang; Xin Jiang; Qun Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a method that linearly correlates each weight of the target model to all the weights of the pretrained model to further enhance acceleration ability.
2439, DeepPCR: Parallelizing Sequential Operations in Neural Networks
Federico Danieli; Miguel Sarabia; Xavier Suau Cuadros; Pau Rodriguez; Luca Zappella;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce DeepPCR, a novel algorithm which parallelizes typically sequential operations used in inference and training of neural networks.
2440, GeNIS: Generalizable Neural Implicit Surface Reconstruction from Multi-View Images
Rui Peng; Xiaodong Gu; Luyang Tang; Shihe Shen; Fanqi Yu; Ronggang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present GeNIS, an end-to-end generalizable surface reconstruction model based on neural implicit representation.
2441, BanditPAM++: Faster $k$-medoids Clustering
Mo Tiwari; Ryan Kang; Donghyun Lee; Sebastian Thrun; Ilan Shomorony; Martin Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present BanditPAM++, which accelerates BanditPAM via two algorithmic improvements.
2442, Federated Spectral Clustering Via Secure Similarity Reconstruction
Dong Qiao; Chris Ding; Jicong Fan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We in this work propose a secure kernelized factorization method for federated spectral clustering on distributed dataset.
2443, Promises and Pitfalls of Threshold-based Auto-labeling
Harit Vishwakarma; Heguang Lin; Frederic Sala; Ramya Korlakai Vinayak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is the first work to analyze TBAL systems and derive sample complexity bounds on the amount of human-labeled validation data required for guaranteeing the quality of machine-labeled data.
2444, ANPL: Compiling Natural Programs with Interactive Decomposition
Di Huang; Ziyuan Nan; Xing Hu; Yewen Pu; Pengwei Jin; Shaohui Peng; Yuanbo Wen; Rui Zhang; Zidong Du; Qi Guo; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce ANPL, a programming system that allows users to decompose user-specific tasks.
2445, On Imitation in Mean-field Games
Giorgia Ramponi; Pavel Kolev; Olivier Pietquin; Niao He; Mathieu Lauriere; Matthieu Geist;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, departing from the existing literature on IL for MFGs, we introduce a new solution concept called the Nash imitation gap.
2446, Rethinking The Symbolic System in Human Activity Visual Reasoning
Xiaoqian Wu; Yong-Lu Li; Jianhua Sun; Cewu Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To overcome the defects, we propose a new symbolic system with broad-coverage symbols and rational rules.
2447, Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction
Tianyu Liu; Qitan Lv; Jie Wang; Shuling Yang; Hanzhu Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these methods are not able to differentiate the target link and other links during message passing, hence the final subgraph representation will contain irrelevant rule information to the target link, which reduces the reasoning performance and severely hinders the applications for real-world scenarios. To tackle this problem, we propose a novel $\textit{single-source edge-wise}$ GNN model to learn the $\textbf{R}$ule-induc$\textbf{E}$d $\textbf{S}$ubgraph represen$\textbf{T}$ations $(\textbf{REST}$), which encodes relevant rules and eliminates irrelevant rules within the subgraph.
2448, On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models
Yufan Cai; Yun Lin; Chenyan Liu; Jinglian Wu; Yifan Zhang; Yiming Liu; Yeyun Gong; Jin Song Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we explore a novel approach, AdaCom, to improve the performance of small-size or medium-size comment generators by on-the-fly model reinforcement.
2449, Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion
Junliang Li; Yang Yajun; Qinghua Hu; Xin Wang; Hong Gao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce three well-known observations about public opinion field effect in media and communication studies, and propose a novel and effective heterogeneous representation learning framework to incorporate public opinion field effect and social circle influence effect.
2450, Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization
Fu Luo; Xi Lin; Fei Liu; Qingfu Zhang; Zhenkun Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, most constructive NCO methods cannot solve problems with large-scale instance sizes, which significantly diminishes their usefulness for real-world applications. In this work, we propose a novel Light Encoder and Heavy Decoder (LEHD) model with a strong generalization ability to address this critical issue.
2451, Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions
Tongxin Li; Yiheng Lin; Shaolei Ren; Adam Wierman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice.
2452, The Utility of “Even If” Semi-Factual Explanation to Optimize Positive Outcomes
Eoin Kenny; Weipeng Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: When users receive either a positive or negative outcome from an automated system, eXplainable AI (XAI) has almost exclusively focused on how to mutate negative outcomes into positive ones by crossing a decision boundary using counterfactuals (e.g., *If you earn 2k more, we will accept your loan application*). In this work, we instead focus on *positive* outcomes, and take the novel step of using XAI to optimize them (e.g., *Even if you wish to half your down-payment, we will still accept your loan application*).
2453, Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
Sébastien Lachapelle; Divyat Mahajan; Ioannis Mitliagkas; Simon Lacoste-Julien;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We tackle the problems of latent variables identification and out-of-support image generation in representation learning.
2454, Two Sides of The Same Coin: Deep Equilibrium Models and Neural ODEs Via Homotopy Continuation
Shutong Ding; Tianyu Cui; Jingya Wang; Ye Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Homotopy continuation is a classical method of solving nonlinear equations based on a corresponding ODE. Given this connection, we proposed a new implicit model called HomoODE that inherits the property of high accuracy from DEQs and the property of stability from Neural ODEs.
2455, Beyond Myopia: Learning from Positive and Unlabeled Data Through Holistic Predictive Trends
Wang Xinrui; Wenhai Wan; Chuanxing Geng; Shao-Yuan Li; Songcan Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we unveil an intriguing yet long-overlooked observation in PUL: \textit{resampling the positive data in each training iteration to ensure a balanced distribution between positive and unlabeled examples results in strong early-stage performance.
2456, Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems
Tongtong Fang; Nan Lu; Gang Niu; Masashi Sugiyama;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we generalize importance weighting (IW), a golden solver for cases (i) and (ii), to a universal solver for all cases.
2457, Online Label Shift: Optimal Dynamic Regret Meets Practical Algorithms
Dheeraj Baby; Saurabh Garg; Tzu-Ching Yen; Sivaraman Balakrishnan; Zachary Lipton; Yu-Xiang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper focuses on supervised and unsupervised online label shift,where the class marginals $Q(y)$ variesbut the class-conditionals $Q(x|y)$ remain invariant.
2458, VoxDet: Voxel Learning for Novel Instance Detection
Bowen Li; Jiashun Wang; Yaoyu Hu; Chen Wang; Sebastian Scherer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Traditional methodologies, which primarily rely on 2D representations and matching techniques, are often inadequate in handling pose variations and occlusions. To solve this, we introduce VoxDet, a pioneer 3D geometry-aware framework that fully utilizes the strong 3D voxel representation and reliable voxel matching mechanism.
2459, Demystifying Oversmoothing in Attention-Based Graph Neural Networks
Xinyi Wu; Amir Ajorlou; Zihui Wu; Ali Jadbabaie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While previous work has established that Graph Convolutional Networks (GCNs) exponentially lose expressive power, it remains controversial whether the graph attention mechanism can mitigate oversmoothing. In this work, we provide a definitive answer to this question through a rigorous mathematical analysis, by viewing attention-based GNNs as nonlinear time-varying dynamical systems and incorporating tools and techniques from the theory of products of inhomogeneous matrices and the joint spectral radius.
2460, Wasserstein Distributional Robustness of Neural Networks
Xingjian Bai; Yifan Jiang; Guangyi He; Jan Obloj;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We re-cast the problem using techniques of Wasserstein distributionally robust optimization (DRO) and obtain novel contributions leveraging recent insights from DRO sensitivity analysis.
2461, Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs
Muhammed Fatih Balin; Ümit Çatalyürek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing approaches either suffer from the neighborhood explosion phenomenon or have poor performance. To address these issues, we propose a new sampling algorithm called LAyer-neighBOR sampling (LABOR).
2462, Blockwise Parallel Transformer for Large Models
Hao Liu; Pieter Abbeel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a distinct approach, Blockwise Parallel Transformer (BPT), that leverages blockwise computation of self-attention and feedforward network fusion to minimize memory costs.
2463, Prediction and Control in Continual Reinforcement Learning
Nishanth Anand; Doina Precup;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we focus on value function estimation in continual reinforcement learning.
2464, ReContrast: Domain-Specific Anomaly Detection Via Contrastive Reconstruction
Jia Guo; shuai lu; Lize Jia; Weihang Zhang; Huiqi Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel epistemic UAD method, namely ReContrast, which optimizes the entire network to reduce biases towards the pre-trained image domain and orients the network in the target domain.
2465, Trading-off Price for Data Quality to Achieve Fair Online Allocation
Mathieu Molina; Nicolas Gast; Patrick Loiseau; Vianney Perchet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an algorithm that jointly solves both problems and show that it has a regret bounded by $\mathcal{O}(\sqrt{T})$.
2466, Reinforcement Learning with Fast and Forgetful Memory
Steven D Morad; Ryan Kortvelesy; Stephan Liwicki; Amanda Prorok;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Modern model-free approaches summarize the trajectory into a latent Markov state using models from Supervised Learning (SL), even though RL tends to exhibit different training and efficiency characteristics. To address this gap, we propose Fast and Forgetful Memory, an algorithm-agnostic memory model designed specifically for RL.
2467, Physics-Informed Deep Learning Framework for MRI Off-Resonance Correction Trained with Noise Instead of Data
Alfredo De Goyeneche Macaya; Shreya Ramachandran; Ke Wang; Ekin Karasan; Joseph Cheng; Stella X. Yu; Michael Lustig;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present a physics-informed, unrolled deep learning framework for off-resonance correction in MRI, which is trained exclusively on synthetic data.
2468, Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
Weizhe Lin; Jinghong Chen; Jingbiao Mei; Alexandru Coca; Bill Byrne;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper proposes Fine-grained Late-interaction Multi-modal Retrieval (FLMR) which significantly improves knowledge retrieval in RA-VQA.
2469, Implicit Bias of Gradient Descent for Logistic Regression at The Edge of Stability
Jingfeng Wu; Vladimir Braverman; Jason Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper studies the convergence and implicit bias of constant-stepsize GD for logistic regression on linearly separable data in the EoS regime.
2470, Learning to Ignore: Mutual-Information Regularized Multi-Agent Policy Iteration
Wang; Deheng Ye; Zongqing Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While some studies attempt to solve this problem via multi-task learning in a fixed set of team compositions, there is still a risk of overfitting to the training set, which may lead to catastrophic performance when facing dramatically varying team compositions during execution. To address this problem, we propose to use mutual information (MI) as an augmented reward to prevent individual policies from relying too much on team-related information and encourage agents to learn policies that are robust in different team compositions.
2471, Towards Characterizing The First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games
Hedi Hadiji; Sarah Sachs; Tim van Erven; Wouter Koolen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Surprisingly, the optimal number of such queries, as a function of both$\epsilon$ and $K$, is not known. We make progress on this question on two fronts. First, we fully characterise the query complexity of learning exact equilibria ($\epsilon=0$), by showing that they require a number of queries that is linearin $K$, which means that it is essentially as hard as querying the wholematrix, which can also be done with $K$ queries. Second, for $\epsilon > 0$, the currentquery complexity upper bound stands at $O(\min(\frac{\ln(K)}{\epsilon} ,K))$.
2472, TopoSRL: Topology Preserving Self-supervised Simplicial Representation Learning
Hiren Madhu; Sundeep Prabhakar Chepuri;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce $\texttt{TopoSRL}$, a novel self-supervised learning (SSL) method for simplicial complexes to effectively capture higher-order interactions and preserve topology in the learned representations.
2473, Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
Jiayuan Ye; Zhenyu Zhu; Fanghui Liu; Reza Shokri; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We analytically investigate how overparameterization of models in randomized machine learning algorithms impacts the information leakage about their training data.
2474, QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning
Di Luo; Jiayu Shen; Rumen Dangovski; Marin Soljacic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Quantum-circuit Alternating Controlled Koopman learning (QuACK), a novel framework that leverages an alternating algorithm for efficient prediction of gradient dynamics on quantum computers.
2475, Goal-Conditioned Predictive Coding As An Implicit Planner for Offline Reinforcement Learning
Zilai Zeng; Ce Zhang; Shijie Wang; Chen Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we investigate if trajectories can be condensed into powerful representations useful for policy learning.
2476, Estimating Causal Effects Identifiable from Combination of Observations and Experiments
Yonghan Jung; Ivan Diaz; Jin Tian; Elias Bareinboim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop a new, general estimator that exhibits multiply robustness properties for any g-identifiable causal functionals.
2477, Formulating Discrete Probability Flow Through Optimal Transport
Pengze Zhang; Hubery Yin; Chen Li; Xiaohua Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to establish the fundamental theory for the probability flow of discrete diffusion models.
2478, State Regularized Policy Optimization on Data with Dynamics Shift
Zhenghai Xue; Qingpeng Cai; Shuchang Liu; Dong Zheng; Peng Jiang; Kun Gai; Bo An;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we find that in many environments with similar structures and different dynamics, optimal policies have similar stationary state distributions.
2479, Robust Concept Erasure Via Kernelized Rate-Distortion Maximization
Somnath Basu Roy Chowdhury; Nicholas Monath; Kumar Avinava Dubey; Amr Ahmed; Snigdha Chaturvedi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new distance metric learning-based objective, the Kernelized Rate-Distortion Maximizer (KRaM), for performing concept erasure.
2480, GeoCLIP: Clip-Inspired Alignment Between Locations and Images for Effective Worldwide Geo-localization
Vicente Vivanco Cepeda; Gaurav Kumar Nayak; Mubarak Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, their performance is limited by the predefined classes and often results in inaccurate localizations when an image's location significantly deviates from its class center. To overcome these limitations, we propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
2481, Syn-to-Real Pose Estimation Through Geometric Reconstruction
Qiuxia Lin; Kerui Gu; Linlin Yang; Angela Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an alternative reconstruction-based approach to guide synthetic-to-real domain adaptation.
2482, Addressing The Speed-accuracy Simulation Trade-off for Adaptive Spiking Neurons
Luke Taylor; Andrew King; Nicol S Harper;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Due to the sequential nature of simulating these neural models, a commonly faced issue is the speed-accuracy trade-off: either accurately simulate a neuron using a small discretisation step (DT), which is slow, or more quickly simulate a neuron using a larger DT and incur a loss in simulation precision. Here we provide a novel solution to remedy this dilemma, by algorithmically reinterpreting the ALIF model, reducing the sequential simulation complexity and permitting a more efficient parallelisation on GPUs.
2483, Causal Component Analysis
Liang Wendong; Armin Kekić; Julius von Kügelgen; Simon Buchholz; Michel Besserve; Luigi Gresele; Bernhard Schölkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As a corollary, this interventional perspective also leads to new identifiability results for nonlinear ICA—a special case of CauCA with an empty graph—requiring strictly fewer datasets than previous results. We introduce a likelihood-based approach using normalizing flows to estimate both the unmixing function and the causal mechanisms, and demonstrate its effectiveness through extensive synthetic experiments in the CauCA and ICA setting.
2484, Construction of Hierarchical Neural Architecture Search Spaces Based on Context-free Grammars
Simon Schrodi; Danny Stoll; Binxin Ru; Rhea Sukthanker; Thomas Brox; Frank Hutter;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce a unifying search space design framework based on context-free grammars that can naturally and compactly generate expressive hierarchical search spaces that are 100s of orders of magnitude larger than common spaces from the literature.
2485, Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems Under Distribution Shift
Yuan Jiang; Zhiguang Cao; Yaoxin Wu; Wen Song; Jie Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While performing favourably on the independent and identically distributed (i.i.d.) instances, most of the existing neural methods for vehicle routing problems (VRPs) struggle to generalize in the presence of a distribution shift. To tackle this issue, we propose an ensemble-based deep reinforcement learning method for VRPs, which learns a group of diverse sub-policies to cope with various instance distributions.
2486, Diffusion-Based Probabilistic Uncertainty Estimation for Active Domain Adaptation
Zhekai Du; Jingjing Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a probabilistic framework that captures both data-level and prediction-level uncertainties beyond a point estimate.
2487, Video Prediction Models As Rewards for Reinforcement Learning
Alejandro Escontrela; Ademi Adeniji; Wilson Yan; Ajay Jain; Xue Bin Peng; Ken Goldberg; Youngwoon Lee; Danijar Hafner; Pieter Abbeel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Video Prediction Rewards (VIPER), an algorithm that leverages pretrained video prediction models as action-free reward signals for reinforcement learning.
2488, Online RL in Linearly $q^\pi$-Realizable MDPs Is As Easy As in Linear MDPs If You Learn What to Ignore
Gellért Weisz; András György; Csaba Szepesvari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions of state-action features.
2489, Detecting Hidden Confounding in Observational Data Using Multiple Environments
Rickard Karlsson; Jesse Krijthe;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Under the assumption of independent causal mechanisms underlying the data-generating process, we demonstrate a way to detect unobserved confounders when having multiple observational datasets coming from different environments. We present a theory for testable conditional independencies that are only absent when there is hidden confounding and examine cases where we violate its assumptions: degenerate & dependent mechanisms, and faithfulness violations.
2490, Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization
Zhenbo Song; ze xianghui; Jianfeng Lu; Yujiao Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel end-to-end approach that leverages the learning of dense pixel-wise flow fields in pairs of ground and satellite images to calculate the camera pose.
2491, Failure-Aware Gaussian Process Optimization with Regret Bounds
Shogo Iwazaki; Shion Takeno; Tomohiko Tanabe; Mitsuru Irie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, this failure region can be complex by several latent constraints, whose number is also unknown. For this problem, we propose a failure-aware Gaussian process upper confidence bound (F-GP-UCB), which only requires a mild assumption for the observation failure that an optimal solution lies on an interior of a feasible region.
2492, Grassmann Manifold Flows for Stable Shape Generation
Ryoma Yataka; Kazuki Hirashima; Masashi Shiraishi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide the theoretical foundations for learning distributions on the Grassmann manifold via continuous normalizing flows, with the explicit goal of generating stable shapes.
2493, Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters
Maxence Noble; Valentin De Bortoli; Arnaud Doucet; Alain Durmus;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider an entropic version of mOT with a tree-structured quadratic cost, i.e., a function that can be written as a sum of pairwise cost functions between the nodes of a tree.
2494, Accelerated Training Via Incrementally Growing Neural Networks Using Variance Transfer and Learning Rate Adaptation
Xin Yuan; Pedro Savarese; Michael Maire;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop an approach to efficiently grow neural networks, within which parameterization and optimization strategies are designed by considering their effects on the training dynamics.
2495, CBD: A Certified Backdoor Detector Based on Local Dominant Probability
Zhen Xiang; Zidi Xiong; Bo Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present the first certified backdoor detector (CBD), which is based on a novel, adjustable conformal prediction scheme using a proposed statistic named *local dominant probability*.
2496, Functional Renyi Differential Privacy for Generative Modeling
Dihong Jiang; Sun Sun; Yaoliang Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, following Hall et al. (2013) we further extend RDP to functional outputs, where the output space can be infinite-dimensional, and develop all necessary tools, *e.g.*, (subsampled) Gaussian mechanism, composition, and post-processing rules, to facilitate its practical adoption. In this work, following Hall et al. (2013) we further extend RDP to functional outputs, where the output space can be infinite-dimensional, and develop all necessary tools, *e.g.*, (subsampled) Gaussian mechanism, composition, and post-processing rules, to facilitate its practical adoption.
2497, Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation
Seunghwan An; Jong-June Jeon;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a new approach that expands the model capacity (i.e., expressive power of distributional family) without sacrificing the computational advantages of the VAE framework.
2498, STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection
Sujin Jang; Dae Ung Jo; Sung Ju Hwang; Dongwook Lee; Daehyun Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, prior approaches have only focused on minimizing global distances between cross-modal features, which may lead to suboptimal knowledge distillation results. Based on these insights, we propose a novel structural and temporal cross-modal knowledge distillation (STXD) framework for multi-view 3DOD.
2499, Demographic Parity Constrained Minimax Optimal Regression Under Linear Model
Kazuto Fukuchi; Jun Sakuma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore the minimax optimal error associated with a demographic parity-constrained regression problem within the context of a linear model.
2500, Exploiting Contextual Objects and Relations for 3D Visual Grounding
Li Yang; chunfeng yuan; Ziqi Zhang; Zhongang Qi; Yan Xu; Wei Liu; Ying Shan; Bing Li; Weiping Yang; Weiming Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The absence of annotations for context objects and relations further exacerbates the difficulties. In this paper, we propose a novel model, CORE-3DVG, to address these challenges by providing explicit learning for context objects and relations.
2501, Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning
Pier Giuseppe Sessa; Pierre Laforgue; Nicolò Cesa-Bianchi; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we provide novel multitask confidence intervals in the challenging agnostic setting, i.e., when neither the similarity between tasks nor the tasks' features are available to the learner.
2502, Neural Latent Geometry Search: Product Manifold Inference Via Gromov-Hausdorff-Informed Bayesian Optimization
Haitz Sáez de Ocáriz Borde; Alvaro Arroyo; Ismael Morales; Ingmar Posner; Xiaowen Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: More specifically, we introduce a principled method that searches for a latent geometry composed of a product of constant curvature model spaces with minimal query evaluations.
2503, Multi-Player Zero-Sum Markov Games with Networked Local Interactions
Chanwoo Park; Kaiqing Zhang; Asuman Ozdaglar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new class of Markov games (MGs), \textit{Multi-player Zero-sum Markov Games} with networked local interactions (MZNMGs), to model the local interaction structure in non-cooperative Markov games.
2504, Discovering Representations for Transfer with Successor Features and The Deep Option Keyboard
Wilka Carvalho Carvalho; Andre Saraiva; Angelos Filos; Andrew Lampinen; Loic Matthey; Richard L Lewis; Honglak Lee; Satinder Singh; Danilo Jimenez Rezende; Daniel Zoran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose the Deep Option Keyboard (Deep OK), which enables transfer with discovered state-features and task encodings.
2505, Human-Aligned Calibration for AI-Assisted Decision Making
Nina Corvelo Benz; Manuel Rodriguez;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, our goal is first to understand why and then investigate how to construct more useful confidence values.
2506, May The Force Be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations
Rui Feng; Qi Zhu; Huan Tran; Binghong Chen; Aubrey Toland; Rampi Ramprasad; Chao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For equilibrium data, we introduce zero-force regularization and forced-based denoising techniques to approximate near-equilibrium forces.
2507, Conditional Matrix Flows for Gaussian Graphical Models
Marcello Massimo Negri; Fabricio Arend Torres; Volker Roth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a general framework for variational inference in GGMs that unifies the benefits of frequentist and Bayesian frameworks.
2508, Structured Neural-PI Control with End-to-End Stability and Output Tracking Guarantees
Wenqi Cui; Yan Jiang; Baosen Zhang; Yuanyuan Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Using equilibrium-independent passivity, a property present in a wide range of physical systems, we propose neural Proportional-Integral (PI) controllers that have provable guarantees of stability and zero steady-state output tracking error.
2509, ChatGPT-Powered Hierarchical Comparisons for Image Classification
Zhiyuan Ren; Yiyang Su; Xiaoming Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, CLIP stillexhibits a bias towards certain classes and generates similar descriptions for similarclasses, disregarding their differences. To address this problem, we present anovel image classification framework via hierarchical comparisons.
2510, D4Explainer: In-distribution Explanations of Graph Neural Network Via Discrete Denoising Diffusion
Jialin Chen; Shirley Wu; Abhijit Gupta; Rex Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, prevailing explainability methods tend to constrain the generated explanations to the original graph, thereby downplaying the significance of the in-distribution property and resulting in explanations that lack reliability. To address these challenges, we propose D4Explainer, a novel approach that provides in-distribution GNN explanations for both counterfactual and model-level explanation scenarios.
2511, Estimating Koopman Operators with Sketching to Provably Learn Large Scale Dynamical Systems
Giacomo Meanti; Antoine Chatalic; Vladimir Kostic; Pietro Novelli; Massimiliano Pontil; Lorenzo Rosasco;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we boost the efficiency of different kernel-based Koopman operator estimators using random projections (sketching).
2512, Enabling Tabular Deep Learning When $d \gg N$ with An Auxiliary Knowledge Graph
Camilo Ruiz; Hongyu Ren; Kexin Huang; Jure Leskovec;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose PLATO, a method that achieves strong performance on tabular data with $d \gg n$ by using an auxiliary KG describing input features to regularize a multilayer perceptron (MLP).
2513, CoRNN: Convex Recurrent Neural Networks Towards Real-time Inference of Unit Resolution Neural Dynamics
Fatih Dinc; Adam Shai; Mark Schnitzer; Hidenori Tanaka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, efficiently reproducing the dynamics of neural populations in computational models at single-cell resolution remains a significant challenge. To address this computational challenge in the experimental pipeline, we propose CoRNN, a convex solver capable of modeling thousands of RNN units in less than a minute, and demonstrate its robustness, scalability, and interpretability through synthetic benchmarks.
2514, Identifying Causal Mechanism Shifts Among Nonlinear Additive Noise Models
Tianyu Chen; Kevin Bello; Bryon Aragam; Pradeep Ravikumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper focuses on identifying mechanism shifts in two or more related SCMs over the same set of variables---\textit{without estimating the entire DAG structure of each SCM}. Prior work under this setting assumed linear models with Gaussian noises; instead, in this work we assume that each SCM belongs to the more general class of nonlinear additive noise models (ANMs).
2515, $L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting
Xiaotong Yuan; Ping Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Exponential generalization bounds with near-optimal rates have recently been established for uniformly stable algorithms~\citep{feldman2019high,bousquet2020sharper}. We seek to extend these best known high probability bounds from deterministic learning algorithms to the regime of randomized learning.
2516, Task-driven Metric Learning for End-to-end Model Learning
Dishank Bansal; Ricky T. Q. Chen; Mustafa Mukadam; Brandon Amos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this approach disregards the information and semantics of the original prediction task, resulting in prediction models that excel only at the specific downstream task they were trained on but are highly inaccurate overall. To address this, we propose using task information to modify only the metric that the prediction model uses for training.
2517, KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training
Truong Thao Nguyen; Balazs Gerofi; Edgar Josafat Martinez-Noriega; François Trahay; Mohamed Wahib;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of training.
2518, CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
Anders Nørskov; Alexander Neergaard Zahid; Morten Mørup;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by recent advancements in voice conversion technologies, we propose a novel contrastive split-latent permutation autoencoder (CSLP-AE) framework that directly optimizes for EEG conversion.
2519, Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing
Shangshang Yang; Xiaoshan Yu; Ye Tian; Xueming Yan; Haiping Ma; Xingyi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite the excellent performance of existing Transformer-based KT approaches, they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling.
2520, Neural Image Compression: Generalization, Robustness, and Spectral Biases
Kelsey Lieberman; James Diffenderfer; Charles Godfrey; Bhavya Kailkhura;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, current research lacks comprehensive datasets and informative tools to evaluate and understand NIC performance in real-world settings. To bridge this crucial gap, first, this paper presents a comprehensive benchmark suite to evaluate the out-of-distribution (OOD) performance of image compression methods.
2521, On Differentially Private Sampling from Gaussian and Product Distributions
Badih Ghazi; Xiao Hu; Ravi Kumar; Pasin Manurangsi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the settings where $P$ is a multi-dimensional Gaussian distribution with different assumptions: known covariance, unknown bounded covariance, and unknown unbounded covariance. We present new differentially private sampling algorithms, and show that they achieve near-optimal sample complexity in the first two settings.
2522, Balancing Memorization and Generalization in RNNs for High Performance Brain-machine Interfaces
Joseph Costello; Hisham Temmar; Luis Cubillos; Matthew Mender; Dylan Wallace; Matt Willsey; Parag Patil; Cynthia Chestek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we compared RNNs to other neural network architectures in real-time, continuous decoding of finger movements using intracortical signals from nonhuman primates.
2523, RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
Siqi Shen; Chennan Ma; Chao Li; Weiquan Liu; Yongquan Fu; Songzhu Mei; Xinwang Liu; Cheng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To formulate the coordination requirements in risk-sensitive MARL, we introduce the Risk-sensitive Individual-Global-Max (RIGM) principle as a generalization of the Individual-Global-Max (IGM) and Distributional IGM (DIGM) principles.
2524, Differentiable Blocks World: Qualitative 3D Decomposition By Rendering Primitives
Tom Monnier; Jake Austin; Angjoo Kanazawa; Alexei Efros; Mathieu Aubry;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives.
2525, Private Subgraph Counting Using Alternatives to Global Sensitivity
Dung Nguyen; Mahantesh Halappanavar; Venkatesh Srinivasan; Anil Vullikanti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, all these alternatives to global sensitivity become computationally very expensive, and to date efficient polynomial time algorithms are known only for few selected subgraphs, such as triangles, $k$-triangles, and $k$-stars. In this paper, we show that good approximations to these sensitivity metrics can be still used to get private algorithms.
2526, 3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics Under Challenging Scenes
Haotian Xue; Antonio Torralba; Josh Tenenbaum; Dan Yamins; Yunzhu Li; Hsiao-Yu Tung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a framework capable of learning 3D-grounded visual intuitive physics models from videos of complex scenes with fluids.
2527, NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF
Stefan Lionar; Xiangyu Xu; Min Lin; Gim Hee Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, we identified two key limitations of MCC: 1) The Transformer decoder is inefficient in handling large number of query points; 2) The 3D representation struggles to recover high-fidelity details. In this paper, we propose a new approach NU-MCC that addresses these limitations.
2528, Information Design in Multi-Agent Reinforcement Learning
Yue Lin; Wenhao Li; Hongyuan Zha; Baoxiang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work investigates information design problems for a group of RL agents.
2529, Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
wonje choi; Woo Kyung Kim; SeungHyun Kim; Honguk Woo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the problem, we present a novel contrastive prompt ensemble (ConPE) framework which utilizes a pretrained vision-language model and a set of visual prompts, thus enables efficient policy learning and adaptation upon a wide range of environmental and physical changes encountered by embodied agents.
2530, Sheaf Hypergraph Networks
Iulia Duta; Giulia Cassarà; Fabrizio Silvestri; Pietro Lió;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Current approaches typically represent these interactions using hypergraphs. We enhance this representation by introducing cellular sheaves for hypergraphs, a mathematical construction that adds extra structure to the conventional hypergraph while maintaining their local, higher-order connectivity.
2531, Label-Only Model Inversion Attacks Via Knowledge Transfer
Bao-Ngoc Nguyen; Keshigeyan Chandrasegaran; Milad Abdollahzadeh; Ngai-Man (Man) Cheung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a new approach for label-only MI attacks.
2532, Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints
Soumyabrata Pal; Arun Suggala; Karthikeyan Shanmugam; Prateek Jain;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose an algorithm called B-LATTICE (Blocked Latent bAndiTs via maTrIx ComplEtion) that collaborates across users, while simultaneously satisfying the budget constraints, to maximize their cumulative rewards.
2533, On The Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
Achraf Azize; Marc Jourdan; Aymen Al Marjani; Debabrota Basu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user studies to name a few. Motivated by the data privacy concerns invoked by these applications, we study the problem of BAI with fixed confidence under $\epsilon$-global Differential Privacy (DP).
2534, Distributionally Robust Skeleton Learning of Discrete Bayesian Networks
Yeshu Li; Brian Ziebart;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present efficient algorithms and show the proposed methods are closely related to the standard regularized regression approach.
2535, IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers
Zhenglin Huang; Xiaoan Bao; Na Zhang; Qingqi Zhang; Xiao Tu; Biao Wu; Xi Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While prior methods have proposed that there is a trade-off between accuracy and robustness, we propose IPMix, a simple data augmentation approach to improve robustness without hurting clean accuracy.
2536, Spatiotemporal Sequence Learning As Probabilistic Program Induction
Tracey Mills; Samuel Cheyette; Josh Tenenbaum;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we experimentally test human learning in the domain of structured 2-dimensional patterns, using a task in which participants repeatedly predicted where a dot would move based on its previous trajectory.
2537, Policy Optimization in A Noisy Neighborhood: On Return Landscapes in Continuous Control
Nate Rahn; Pierluca D'Oro; Harley Wiltzer; Pierre-Luc Bacon; Marc Bellemare;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Deep reinforcement learning agents for continuous control are known to exhibit significant instability in their performance over time. In this work, we provide a fresh perspective on these behaviors by studying the return landscape: the mapping between a policy and a return.
2538, Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation
Haonan Wang; Xiaomeng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We identify two main obstacles to achieving this goal in the existing SSL framework: 1) the weakness of capturing distribution-invariant features; and 2) the tendency for unlabeled data to be overwhelmed by labeled data, leading to over-fitting to the labeled data during training. To address these issues, we propose an Aggregating & Decoupling framework.
2539, Improving Neural Network Representations Using Human Similarity Judgments
Lukas Muttenthaler; Lorenz Linhardt; Jonas Dippel; Robert Vandermeulen; Katherine Hermann; Andrew Lampinen; Simon Kornblith;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Thus, we propose a novel method that aligns the global structure of representations while preserving their local structure.
2540, GNeSF: Generalizable Neural Semantic Fields
Hanlin Chen; Chen Li; Mengqi Guo; Zhiwen Yan; Gim Hee Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing approaches still requires expensive per-scene optimization that prohibits generalization to novel scenes during inference. To circumvent this problem, we introduce a \textit{generalizable} 3D segmentation framework based on implicit representation.
2541, Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards
Semih Cayci; Atilla Eryilmaz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we establish that temporal difference (TD) learning with a dynamic gradient clipping mechanism, and correspondingly operated natural actor-critic (NAC), can be provably robustified against heavy-tailed reward distributions.
2542, Geometric Neural Diffusion Processes
Emile Mathieu; Vincent Dutordoir; Michael Hutchinson; Valentin De Bortoli; Yee Whye Teh; Richard Turner;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we extend the framework of diffusion modelsto incorporate a series of geometric priors in infinite-dimension modelling.
2543, Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning
Wei Tang; Weijia Zhang; Min-Ling Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we study an alternative scheme where a multi-instance bag is embedded into a single vector representation.
2544, Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP
Qi Qian; Yuanhong Xu; Juhua Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We theoretically prove that the gap cannot be reduced sufficiently by minimizing the contrastive loss in CLIP and the optimal proxy for vision tasks resides only in the vision space. Therefore, given unlabeled test data, we propose to learn the vision proxy directly with the help from the text proxy for zero-shot transfer.
2545, A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm
Haizhou Shi; Hao Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Various methods have been proposed for this problem, but it is still unclear how they are related and when practitioners should choose one method over another. In response, we propose a unified framework, dubbed Unified Domain Incremental Learning (UDIL), for domain incremental learning with memory.
2546, PaintSeg: Painting Pixels for Training-free Segmentation
Xiang Li; Chung-Ching Lin; Yinpeng Chen; Zicheng Liu; Jinglu Wang; Bhiksha Raj;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The paper introduces PaintSeg, a new unsupervised method for segmenting objects without any training.
2547, Mnemosyne: Learning to Train Transformers with Transformers
Deepali Jain; Krzysztof M Choromanski; Kumar Avinava Dubey; Sumeet Singh; Vikas Sindhwani; Tingnan Zhang; Jie Tan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a new class of learnable optimizers, called Mnemosyne.
2548, Episodic Multi-Task Learning with Heterogeneous Neural Processes
Jiayi Shen; Xiantong Zhen; Qi Wang; Marcel Worring;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training set-up.
2549, Non-stationary Experimental Design Under Linear Trends
David Simchi-Levi; Chonghuan Wang; Zeyu Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we address the problem of non-stationary experimental design under linear trends by considering two objectives: estimating the dynamic treatment effect and minimizing welfare loss within the experiment.
2550, Streaming PCA for Markovian Data
Syamantak Kumar; Purnamrita Sarkar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we obtain the first sharp rate for Oja's algorithm on the entire data, where we remove the logarithmic dependence on the sample size, $n$, resulting from throwing data away in downsampling strategies.
2551, PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
Qianli Shen; Wai Hoh Tang; Zhun Deng; Apostolos Psaros; Kenji Kawaguchi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a method, termed Physics-Informed Confidence Propagation (PICProp), based on bi-level optimization to compute a valid CI without making heavy assumptions.
2552, Visual Explanations of Image-Text Representations Via Multi-Modal Information Bottleneck Attribution
Tim G. J. Rudner; Ying Wang; Andrew Wilson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To improve the interpretability of vision-language models, such as CLIP, we propose a multi-modal information bottleneck (M2IB) objective that compresses irrelevant and noisy information, while preserving relevant visual and textual features.
2553, Coupled Gradient Flows for Strategic Non-Local Distribution Shift
Lauren Conger; Franca Hoffmann; Eric Mazumdar; Lillian Ratliff;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel framework for analyzing the dynamics of distribution shift in real-world systems that captures the feedback loop between learning algorithms and the distributions on which they are deployed.
2554, Sparse Additive Mechanism Shift For Disentangled Representation Learning
Michael Bereket; Theofanis Karaletsos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the Sparse Additive Mechanism Shift Variational Autoencoder, SAMS-VAE, to combine compositionality, disentanglement, and interpretability for perturbation models.
2555, Convergence Analysis of Sequential Split Learning on Heterogeneous Data
Yipeng Li; Xinchen Lyu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we derive the convergence guarantees of Sequential SL (SSL, the vanilla case of SL that conducts the model training in sequence) for strongly/general/non-convex objectives on heterogeneous data.
2556, Fully Dynamic $k$-Center Clustering with Outliers
Leyla Biabani; Annika Hennes; Morteza Monemizadeh; Melanie Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Given a point set $P\subseteq M$ from a metric space $(M,d)$ and numbers $k, z \in N$, the *metric $k$-center problem with $z$ outliers* is to find a set $C^\ast\subseteq P$ of $k$ points such that the maximum distance of all but at most $z$ outlier points of $P$ to their nearest center in ${C}^\ast$ is minimized. We consider this problem in the fully dynamic model, i.e., under insertions and deletions of points, for the case that the metric space has a bounded doubling dimension $dim$.
2557, Navigating The Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment
Carsten Lüth; Till Bungert; Lukas Klein; Paul Jaeger;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, today’s AL literature presents an inconsistent and contradictory landscape leaving practitioners uncertain about whether and how to use AL in their tasks. In this work, we make the case that this inconsistency arises from a lack of systematic and realistic evaluation of AL methods.
2558, Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
Matthias Gerstgrasser; Tom Danino; Sarah Keren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training.
2559, Statistically Valid Variable Importance Assessment Through Conditional Permutations
Ahmad CHAMMA; Bertrand Thirion; Denis Engemann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we present a Conditional Permutation Importance approach ($\textit{CPI}$) that is both model agnostic and computationally lean.
2560, On The Implicit Bias of Linear Equivariant Steerable Networks
Ziyu Chen; Wei Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the implicit bias of gradient flow on linear equivariant steerable networks in group-invariant binary classification.
2561, Data-Centric Learning from Unlabeled Graphs with Diffusion Model
Gang Liu; Eric Inae; Tong Zhao; Jiaxin Xu; Tengfei Luo; Meng Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model.
2562, Bandit Optimal Control
Y. Jennifer Sun; Stephen Newman; Elad Hazan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate LQR and LQG problems with semi-adversarial perturbations and time-varying adversarial bandit loss functions.
2563, NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning
Yun Yi; Haokui Zhang; Rong Xiao; Nannan Wang; Xiaoyu Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, graph neural network (GNN) based approaches still dominate the field of learning representation for the entire network. In this paper, we revisit Transformer and compare it with GNN to analyse the different architecture characteristics of them.
2564, Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Vladimir Feinberg; Xinyi Chen; Y. Jennifer Sun; Rohan Anil; Elad Hazan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We describe a generic method for reducing memory and compute requirements of maintaining a matrix preconditioner using the Frequent Directions (FD) sketch.
2565, RoboCLIP: One Demonstration Is Enough to Learn Robot Policies
Sumedh Sontakke; Séb Arnold; Jesse Zhang; Karl Pertsch; Erdem Bıyık; Dorsa Sadigh; Chelsea Finn; Laurent Itti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by advances in the field of Video-and-Language Models (VLMs), we present RoboCLIP, an online imitation learning method that uses a single demonstration (overcoming the large data requirement) in the form of a video demonstration or a textual description of the task to generate rewards without manual reward function design.
2566, ABCD: Attention-Based Causal Discovery
Raanan Rohekar; Shami Nisimov; Yaniv Gurwicz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a causal interpretation for self-attention in the Transformer neural network architecture.
2567, ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking
Yutong Kou; Jin Gao; Liang Li; Gang Wang; Weiming Hu; Yizheng Wang; Bing Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Recently, the transformer has enabled the speed-oriented trackers to approach state-of-the-art (SOTA) performance with high-speed thanks to the smaller input size or the lighter feature extraction backbone, though they still substantially lag behind their corresponding performance-oriented versions. In this paper, we demonstrate that it is possible to narrow or even close this gap while achieving high tracking speed based on the smaller input size.
2568, Transfer Learning with Affine Model Transformation
Shunya Minami; Kenji Fukumizu; Yoshihiro Hayashi; Ryo Yoshida;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents a general class of transfer learning regression called affine model transfer, following the principle of expected-square loss minimization.
2569, A Theory of Unsupervised Translation Motivated By Understanding Animal Communication
Shafi Goldwasser; David Gruber; Adam Tauman Kalai; Orr Paradise;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a theoretical framework for analyzing UMT when no parallel translations are available and when it cannot be assumed that the source and target corpora address related subject domains or posses similar linguistic structure.
2570, Weakly Coupled Deep Q-Networks
Ibrahim El Shar; Daniel Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose weakly coupled deep Q-networks (WCDQN), a novel deep reinforcement learning algorithm that enhances performance in structured problems known as weakly coupled Markov decision processes (WCMDP).
2571, Crystal Structure Prediction By Joint Equivariant Diffusion
Rui Jiao; Wenbing Huang; Peijia Lin; Jiaqi Han; Pin Chen; Yutong Lu; Yang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While CSP can be addressed by employing currently-prevailing generative models (**e.g.** diffusion models), this task encounters unique challenges owing to the symmetric geometry of crystal structures---the invariance of translation, rotation, and periodicity. To incorporate the above symmetries, this paper proposes DiffCSP, a novel diffusion model to learn the structure distribution from stable crystals.
2572, On The Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm
Qi CHEN; Changjian Shui; Ligong Han; Mario Marchand;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on the objective, we introduce a unified theoretical framework for CML in both static and shifting environments, providing guarantees for various task-specific learning algorithms.
2573, Discrete-Smoothness in Online Algorithms with Predictions
Yossi Azar; Debmalya Panigrahi; Noam Touitou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The ideal learning-augmented algorithm is comparable to the optimum when given perfect predictions (consistency), to the best online approximation for arbitrary predictions (robustness), and should interpolate between these extremes as a smooth function of the prediction error. In this paper, we quantify these guarantees in terms of a general property that we call discrete-smoothness, and achieve discrete-smooth algorithms for online covering, specifically the facility location and set cover problems.
2574, BPT: Foundation Model for Intracranial Neural Signal
Daoze Zhang; Zhizhang Yuan; YANG YANG; Junru Chen; Jingjing Wang; Yafeng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a foundation model named BPT for modeling intracranial recordings, which learns powerful representations of intracranial neural signals by pre-training, providing a large-scale, off-the-shelf model for medicine.
2575, Brain-like Flexible Visual Inference By Harnessing Feedback Feedforward Alignment
Tahereh Toosi; Elias Issa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose that top-down effects emerge through alignment between feedforward and feedback pathways, each optimizing its own objectives. To achieve this co-optimization, we introduce Feedback-Feedforward Alignment (FFA), a learning algorithm that leverages feedback and feedforward pathways as mutual credit assignment computational graphs, enabling alignment.
2576, A Smooth Binary Mechanism for Efficient Private Continual Observation
Rasmus Pagh; Joel Daniel Andersson;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We address the efficiency problem by presenting a simple alternative to the binary mechanism in which 1) generating the noise takes constant average time per value, 2) the variance is reduced by a factor about 4 compared to the binary mechanism, and 3) the noise distribution at each step is identical.
2577, A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment
Yixuan Xu; Steven Jecmen; Zimeng Song; Fei Fang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present a practical, one-size-fits-all method for randomized paper assignment intended to perform well across different motivations for randomness.
2578, On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
Laura F. Nern; Harsh Raj; Maurice André Georgi; Yash Sharma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While pretraining has been shown to enhance the performance of models in practice, the transfer of robustness properties from pretraining to downstream tasks remains poorly understood. In this study, we demonstrate that the robustness of a linear predictor on downstream tasks can be constrained by the robustness of its underlying representation, regardless of the protocol used for pretraining.
2579, Optimal Transport Model Distributional Robustness
Van-Anh Nguyen; Trung Le; Anh Bui; Thanh-Toan Do; Dinh Phung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we explore an optimal transport-based distributional robustness framework on model spaces.
2580, Flow Matching for Scalable Simulation-Based Inference
Jonas Wildberger; Maximilian Dax; Simon Buchholz; Stephen Green; Jakob H Macke; Bernhard Schölkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building on recent advances in generative modeling, we here present flow matching posterior estimation (FMPE), a technique for SBI using continuous normalizing flows.
2581, Exploring and Interacting with The Set of Good Sparse Generalized Additive Models
Zhi Chen; Chudi Zhong; Margo Seltzer; Cynthia Rudin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Approximating and exploring the Rashomon set, i.e., the set of all near-optimal models, addresses this practical challenge by providing the user with a searchable space containing a diverse set of models from which domain experts can choose. We present algorithms to efficiently and accurately approximate the Rashomon set of sparse, generalized additive models with ellipsoids for fixed support sets and use these ellipsoids to approximate Rashomon sets for many different support sets.
2582, SALSA VERDE: A Machine Learning Attack on LWE with Sparse Small Secrets
Cathy Li; Emily Wenger; Zeyuan Allen-Zhu; Francois Charton; Kristin E. Lauter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building on these, we propose VERDE, an improved ML attack that can recover sparse binary, ternary, and small Gaussian secrets.
2583, Neural Circuits for Fast Poisson Compressed Sensing in The Olfactory Bulb
Jacob Zavatone-Veth; Paul Masset; William Tong; Joseph D. Zak; Venkatesh Murthy; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we propose a rate-based Poisson compressed sensing circuit model for the olfactory bulb.
2584, Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
Jameel Abdul Samadh; Mohammad Hanan Gani; Noor Hussein; Muhammad Uzair Khattak; Muhammad Muzammal Naseer; Salman Khan; Fahad Shahbaz Khan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While effective, this overlooks the key cause for performance degradation to unseen domains - distribution shift. In this work, we explicitly handle this problem by aligning the out-of-distribution (OOD) test sample statistics to those of the source data using prompt tuning.
2585, Online POMDP Planning with Anytime Deterministic Guarantees
Moran Barenboim; Vadim Indelman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite their effectiveness, these algorithms offer only probabilistic and often asymptotic guarantees toward the optimal solution due to their dependence on sampling. To address these limitations, we derive a deterministic relationship between a simplified solution that iseasier to obtain and the theoretically optimal one.
2586, Convolution Monge Mapping Normalization for Learning on Biosignals
Théo Gnassounou; Rémi Flamary; Alexandre Gramfort;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a new method called Convolutional Monge Mapping Normalization ($\texttt{CMMN}$), which consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data.
2587, Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation
Jinpeng Chen; Runmin Cong; Yuxuan LUO; Horace Ip; Sam Kwong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This leads to an overrepresentation of these foreground classes in the single-step training set, causing the classification biased towards these classes. To address this issue, we present STAR, which preserves the main characteristics of each past class by storing a compact prototype and necessary statistical data, and aligns the class distribution of single-step training samples with the complete dataset by replaying these prototypes and repeating background pixels with appropriate frequency.
2588, Imitation Learning from Vague Feedback
Xin-Qiang Cai; Yu-Jie Zhang; Chao-Kai Chiang; Masashi Sugiyama;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By modeling the underlying demonstration pool as a mixture of expert and non-expert data, we show that the expert policy distribution can be recovered when the proportion $\alpha$ of expert data is known.
2589, List and Certificate Complexities in Replicable Learning
Peter Dixon; A. Pavan; Jason Vander Woude; N. V. Vinodchandran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate replicable learning algorithms. Informally a learning algorithm is replicable if the algorithm outputs the same canonical hypothesis over multiple runs with high probability, even when different runs observe a different set of samples from the unknown data distribution.
2590, HiNeRV: Video Compression with Hierarchical Encoding Based Neural Representation
Ho Man Kwan; Ge Gao; Fan Zhang; Andrew Gower; David Bull;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose HiNeRV, an INR that combines bilinear interpolation with novel hierarchical positional encoding.
2591, Reusable Slotwise Mechanisms
Trang Nguyen; Amin Mansouri; Kanika Madan; Khuong Duy Nguyen; Kartik Ahuja; Dianbo Liu; Yoshua Bengio;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce Reusable Slotwise Mechanisms, or RSM, a framework that models object dynamics by leveraging communication among slots along with a modular architecture capable of dynamically selecting reusable mechanisms for predicting the future states of each object slot.
2592, When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation
Xinhong Ma; Yiming Wang; Hao Liu; Tianyu Guo; Yunhe Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the existing visual prompt tuning methods are unsuitable for source-free domain adaptive semantic segmentation due to the following two reasons: (1) Commonly used visual prompts like input tokens or pixel-level perturbations cannot reliably learn informative knowledge beneficial for semantic segmentation. (2) Visual prompts require sufficient labeled data to fill the gap between the pre-trained model and downstream tasks. To alleviate these problems, we propose a universal unsupervised visual prompt tuning (Uni-UVPT) framework, which is applicable to various transformer-based backbones.
2593, Smooth, Exact Rotational Symmetrization for Deep Learning on Point Clouds
Sergey Pozdnyakov; Michele Ceriotti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Some application domains require incorporating exactly physical constraints, including chemical and materials modeling which we focus on in this paper.
2594, MMGP: A Mesh Morphing Gaussian Process-based Machine Learning Method for Regression of Physical Problems Under Nonparametrized Geometrical Variability
Fabien Casenave; Brian Staber; Xavier Roynard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a machine learning method that do not rely on graph neural networks.
2595, Survival Permanental Processes for Survival Analysis with Time-Varying Covariates
Hideaki Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a non-parametric Bayesian survival model to analyze the nonlinear dependence of time-to-event outcomes on time-varying covariates.
2596, DiffSketcher: Text Guided Vector Sketch Synthesis Through Latent Diffusion Models
XiMing Xing; Qian Yu; Chuang Wang; Haitao Zhou; Dong Xu; Jing Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present DiffSketch, an innovative algorithm that creates \textit{vectorized} free-hand sketches using natural language input.
2597, PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems
Jihui Jin; Etienne Ollivier; Richard Touret; Matthew McKinley; Karim Sabra; Justin Romberg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this article, we propose a simple learned weighted average model that embeds linearizations of the forward model around various reference points into the model itself, explicitly incorporating known physics.
2598, Counting Distinct Elements in The Turnstile Model with Differential Privacy Under Continual Observation
Palak Jain; Iden Kalemaj; Sofya Raskhodnikova; Satchit Sivakumar; Adam Smith;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present an item-level differentially private mechanism that, for all turnstile streams with maximum flippancy $w$, continually outputs the number of distinct elements with an $O(\sqrt{w} \cdot \mathsf{poly}\log T)$ additive error, without requiring prior knowledge of $w$.
2599, A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications
Yanbo Chen; Weiwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an explanatory model, called the manifold attack model, that formalizes popular beliefs and explains the existing empirical results.
2600, Differentiable Random Partition Models
Thomas Sutter; Alain Ryser; Joram Liebeskind; Julia Vogt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, assigning elements, such as samples in a dataset or neurons in a network layer, to an unknown and discrete number of subsets is inherently non-differentiable, prohibiting end-to-end gradient-based optimization of parameters. We overcome this limitation by proposing a novel two-step method for inferring partitions, which allows its usage in variational inference tasks.
2601, Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning
Yifan Zang; Jinmin He; Kai Li; Haobo Fu; Qiang Fu; Junliang Xing; Jian Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel formulation of Group-oriented Multi-Agent Reinforcement Learning (GoMARL), which learns automatic grouping without any domain knowledge for efficient cooperation.
2602, Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization
Yuxin Guo; Shijie Ma; Hu Su; Zhiqing Wang; Yuhao Zhao; Wei Zou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel Semi-Supervised Learning framework for AVSL, namely Dual Mean-Teacher (DMT), comprising two teacher-student structures to circumvent the confirmation bias issue.
2603, Adversarially Robust Learning with Uncertain Perturbation Sets
Tosca Lechner; Vinayak Pathak; Ruth Urner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show there are classes for which perturbation-set unaware learning without query access is possible, but abstention is required.
2604, Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements
Gaurav Shrivastava; Ser Nam Lim; Abhinav Shrivastava;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel robust framework for low-level vision tasks, including denoising, object removal, frame interpolation, and super-resolution, that does not require any external training data corpus.
2605, Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity
Joel Ye; Jennifer Collinger; Leila Wehbe; Robert Gaunt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We thus develop Neural Data Transformer 2 (NDT2), a spatiotemporal Transformer for neural spiking activity, and demonstrate pretraining can leverage motor BCI datasets that span sessions, subjects, and experimental tasks.
2606, Bicriteria Multidimensional Mechanism Design with Side Information
Siddharth Prasad; Maria-Florina Balcan; Tuomas Sandholm;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we adopt a prior-free perspective that makes no assumptions on the correctness, accuracy, or source of the side information.
2607, Causal Discovery from Observational and Interventional Data Across Multiple Environments
Adam Li; Amin Jaber; Elias Bareinboim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Leveraging the S-Markov property, we introduce a new constraint-based causal discovery algorithm, S-FCI, that can learn from a mixture of observational and interventional data from different domains.
2608, Fast Projected Newton-like Method for Precision Matrix Estimation Under Total Positivity
Jian-Feng CAI; José Vinícius de Miranda Cardoso; Daniel Palomar; Jiaxi Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Current algorithms are designed using the block coordinate descent method or the proximal point algorithm, which becomes computationally challenging in high-dimensional cases due to the requirement to solve numerous nonnegative quadratic programs or large-scale linear systems. To address this issue, we propose a novel algorithm based on the two-metric projection method, incorporating a carefully designed search direction and variable partitioning scheme.
2609, Conservative Offline Policy Adaptation in Multi-Agent Games
Chengjie Wu; Pingzhong Tang; Jun Yang; Yujing Hu; Tangjie Lv; Changjie Fan; Chongjie Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by recent progress in offline reinforcement learning, this work studies offline policy adaptation, which aims to utilize the target agent's behavior data to exploit its weakness or enable effective cooperation. We investigate its distinct challenges of distributional shift and risk-free deviation, and propose a novel learning objective, conservative offline adaptation, that optimizes the worst-case performance against any dataset consistent proxy models.
2610, Self-Consistent Velocity Matching of Probability Flows
Lingxiao Li; Samuel Hurault; Justin Solomon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a discretization-free scalable framework for solving a large class of mass-conserving partial differential equations (PDEs), including the time-dependent Fokker-Planck equation and the Wasserstein gradient flow.
2611, Clustering The Sketch: Dynamic Compression for Embedding Tables
Thomas Ahle; Henry Tsang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We suggest Clustered Compositional Embeddings (CCE) which combines clustering-based compression like quantization to codebooks with dynamic methods like The Hashing Trick and Compositional Embeddings [Shi et al., 2020].
2612, On The Explainable Properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Mathieu Serrurier; Franck Mamalet; Thomas FEL; Louis Béthune; Thibaut Boissin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we demonstrate that, on the contrary, the saliency maps of 1-Lipschitz neural networks, learnt with the dual loss of an optimal transportation problem, exhibit desirable XAI properties:They are highly concentrated on the essential parts of the image with low noise, significantly outperforming state-of-the-art explanation approaches across various models and metrics.
2613, Lookup Table Meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping
Feng Zhang; Ming Tian; Zhiqiang Li; Bin Xu; Qingbo Lu; Changxin Gao; Nong Sang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, this paper aims to address this issue by exploring a novel strategy that integrates global and local operators by utilizing closed-form Laplacian pyramid decomposition and reconstruction.
2614, SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
Zhuoyan Luo; Yicheng Xiao; Yong Liu; Shuyan Li; Yitong Wang; Yansong Tang; Xiu Li; Yujiu Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the lack of a global view of video content leads to difficulties in effectively utilizing inter-frame relationships and understanding textual descriptions of object temporal variations. To address this issue, we propose Semantic-assisted Object Cluster (SOC), which aggregates video content and textual guidance for unified temporal modeling and cross-modal alignment.
2615, Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
Thanh-Dat Truong; Hoang-Quan Nguyen; Bhiksha Raj; Khoa Luu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel Fairness Continual Learning approach to the semantic segmentation problem.
2616, First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
Aleksandr Beznosikov; Sergey Samsonov; Marina Sheshukova; Alexander Gasnikov; Alexey Naumov; Eric Moulines;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a unified approach for the theoretical analysis of first-order gradient methods for stochastic optimization and variational inequalities.
2617, SE(3) Equivariant Augmented Coupling Flows
Laurence Midgley; Vincent Stimper; Javier Antorán; Emile Mathieu; Bernhard Schölkopf; José Miguel Hernández-Lobato;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work proposes a coupling flow that preserves SE(3) and permutation equivariance by performing coordinate splits along additional augmented dimensions.
2618, Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
Haotao Wang; Ziyu Jiang; Yuning You; Yan Han; Gaowen Liu; Jayanth Srinivasa; Ramana Kompella; Zhangyang Atlas Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces the Mixture-of-Expert (MoE) idea to GNNs, aiming to enhance their ability to accommodate the diversity of training graph structures, without incurring computational overheads.
2619, Regularization Properties of Adversarially-trained Linear Regression
Antonio Ribeiro; Dave Zachariah; Francis Bach; Thomas Schön;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We provide a comparative analysis between the solution of adversarial training in linear regression and other regularization methods.
2620, Neural Modulation for Flash Memory: An Unsupervised Learning Framework for Improved Reliability
Jonathan Zedaka; Elisha Halperin; Evgeny Blaichman; Amit Berman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel approach for modeling and preventing errors by utilizing the capabilities of generative and unsupervised machine learning methods.
2621, Invariant Learning Via Probability of Sufficient and Necessary Causes
Mengyue Yang; Yonggang Zhang; Zhen Fang; Yali Du; Furui Liu; Jean-Francois Ton; Jianhong Wang; Jun Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To associate PNS with OOD generalization, we propose PNS risk and formulate an optimization problem to learn representation with a high PNS value.
2622, Opening The Vocabulary of Egocentric Actions
Dibyadip Chatterjee; Fadime Sener; Shugao Ma; Angela Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel open vocabulary action recognition task.
2623, (More) Sample-Efficient Offline RL with Options
Xiaoyan Hu; Ho-fung Leung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide the first analysis of the sample complexity for offline RL with options, where the agent learns from a dataset without further interaction with the environment.
2624, On Single-Index Models Beyond Gaussian Data
Aaron Zweig; Loucas PILLAUD-VIVIEN; Joan Bruna;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In essence, these tools exploit the stability and spherical symmetry of Gaussian distributions. In this work, we explore extensions of this picture beyond the Gaussian setting, where both stability or symmetry might be violated.
2625, Towards Symmetry-Aware Generation of Periodic Materials
Youzhi Luo; Chengkai Liu; Shuiwang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose SyMat, a novel material generation approach that can capture physical symmetries of periodic material structures.
2626, Meta Privacy-Preserving Action Recognition
Duo Peng; Li Xu; Qiuhong Ke; Ping Hu; Jun Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite recent efforts in this task, it is still challenging to deal with novel privacy attributes and novel privacy attack models that are unavailable during the training phase. In this paper, from the perspective of meta-learning (learning to learn), we propose a novel Meta Privacy-Preserving Action Recognition (MPPAR) framework to improve both generalization abilities above (i.e., generalize to *novel privacy attributes* and *novel privacy attack models*) in a unified manner.
2627, Switching Temporary Teachers for Semi-Supervised Semantic Segmentation
Jaemin Na; Jung-Woo Ha; Hyung Jin Chang; Joon Chung; Wonjun Hwang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces Dual Teacher, a simple yet effective approach that employs dual temporary teachers aiming to the student to alleviate the coupling problem.
2628, Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks Via Subtask Decomposition
Suyoung Lee; Myungsik Cho; Youngchul Sung;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Nevertheless, these methods often struggle to generalize beyond tasks with parametric variations. To overcome this challenge, we propose Subtask Decomposition and Virtual Training (SDVT), a novel meta-RL approach that decomposes each non-parametric task into a collection of elementary subtasks and parameterizes the task based on its decomposition.
2629, MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
LILI YU; Daniel Simig; Colin Flaherty; Armen Aghajanyan; Luke Zettlemoyer; Mike Lewis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We proposed Megabyte, a multi-scale decoder architecture that enables end-to-end differentiable modeling of sequences of over one million bytes.
2630, Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks
Jules Berman; Benjamin Peherstorfer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work introduces Neural Galerkin schemes that update randomized sparse subsets of network parameters at each time step.
2631, Latent Exploration for Reinforcement Learning
Alberto Silvio Chiappa; Alessandro Marin Vargas; Ann Huang; Alexander Mathis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we propose LATent TIme-Correlated Exploration (Lattice), a method to inject temporally-correlated noise into the latent state of the policy network, which can be seamlessly integrated with on- and off-policy algorithms.
2632, MMD-Fuse: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting
Felix Biggs; Antonin Schrab; Arthur Gretton;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose novel statistics which maximise the power of a two-sample test based on the Maximum Mean Discrepancy (MMD), byadapting over the set of kernels used in defining it.
2633, Generalised F-Mean Aggregation for Graph Neural Networks
Ryan Kortvelesy; Steven D Morad; Amanda Prorok;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present GenAgg, a generalised aggregation operator, which parametrises a function space that includes all standard aggregators.
2634, Global Identifiability of $\ell_1$-based Dictionary Learning Via Matrix Volume Optimization
Jingzhou Hu; Kejun Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel formulation for dictionary learning that minimizes the determinant of the dictionary matrix, also known as its volume, subject to the constraint that each row of the sparse coefficient matrix has unit $\ell_1$ norm.
2635, Partial Multi-Label Learning with Probabilistic Graphical Disambiguation
Jun-Yi Hang; Min-Ling Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To provide a principled way for disambiguation, we make a first attempt to explore the probabilistic graphical model for PML problem, where a directed graph is tailored to describe the generative process of partial multi-label data.
2636, From Parameter-Efficient to Memory-Efficient Fine-Tuning
Baohao Liao; Shaomu Tan; Christof Monz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we first investigate what is a key factor for the success of existing PEFT methods, and realize that it's essential to preserve the PLM's starting point when initializing a PEFT method. With this finding, we propose memory-efficient fine-tuning (MEFT) that inserts adapters into a PLM, preserving the PLM's starting point and making it reversible without additional pre-training.
2637, Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization
Thomas FEL; Thibaut Boissin; Victor Boutin; Agustin PICARD; Paul Novello; Julien Colin; Drew Linsley; Tom ROUSSEAU; Remi Cadene; Laurent Gardes; Thomas Serre;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite its success, its widespread adoption has been limited due to issues in scaling to deeper neural networks and the reliance on tricks to generate interpretable images. Here, we describe MACO, a simple approach to address these shortcomings.
2638, Kernel Quadrature with Randomly Pivoted Cholesky
Ethan Epperly; Elvira Moreno;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents new quadrature rules for functions in a reproducing kernel Hilbert space using nodes drawn by a sampling algorithm known as randomly pivoted Cholesky.
2639, A Graphon-signal Analysis of Graph Neural Networks
Ron Levie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present an approach for analyzing message passing graph neural networks (MPNNs) based on an extension of graphon analysis to a so called graphon-signal analysis.
2640, SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration
JINGYANG XIANG; Siqi Li; Jun Chen; Guang Dai; Shipeng Bai; Yukai Ma; Yong Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To overcome them, this paper proposes a novel \emph{\textbf{S}oft \textbf{U}niform \textbf{B}lock \textbf{P}runing} (SUBP) approach to train a uniform 1$\times$N sparse structured network from scratch.
2641, Block Coordinate Plug-and-Play Methods for Blind Inverse Problems
Weijie Gan; shirin shoushtari; Yuyang Hu; Jiaming Liu; Hongyu An; Ulugbek Kamilov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new convergence theory for BC-PnP compatible with blind inverse problems by considering nonconvex data-fidelity terms and expansive denoisers.
2642, Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Jimmy Di; Jack Douglas; Jayadev Acharya; Gautam Kamath; Ayush Sekhari;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced.
2643, Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models
Chirag Raman; Alec Nonnemaker; Amelia Villegas-Morcillo; Hayley Hung; Marco Loog;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a post hoc saliency-based explanation framework for counterfactual reasoning in probabilistic multivariate time-series forecasting (regression) settings.
2644, Debiasing Pretrained Generative Models By Uniformly Sampling Semantic Attributes
Walter Gerych; Kevin Hickey; Luke Buquicchio; Kavin Chandrasekaran; Abdulaziz Alajaji; Elke A. Rundensteiner; Emmanuel Agu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It is imperative to debias generative models so they synthesize an equal number of instances for each group, while not requiring retraining of the model to avoid prohibitive expense. We thus propose a *distribution mapping module* that produces samples from a *fair noise distribution*, such that the pretrained generative model produces *semantically uniform* outputs - an equal number of instances for each group - when conditioned on these samples.
2645, Emergent and Predictable Memorization in Large Language Models
Stella Biderman; USVSN PRASHANTH; Lintang Sutawika; Hailey Schoelkopf; Quentin Anthony; Shivanshu Purohit; Edward Raff;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The prevalence of such undesirable memorization can pose issues for model trainers, and may even require discarding an otherwise functional model. We therefore seek to predict which sequences will be memorized before a large model's full train-time by extrapolating the memorization behavior of lower-compute trial runs.
2646, Improving The Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
Rachel Redberg; Antti Koskela; Yu-Xiang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper revamps the objective perturbation mechanism with tighter privacy analyses and new computational tools that boost it to perform competitively with DP-SGD on unconstrained convex generalized linear problems.
2647, Utilitarian Algorithm Configuration
Devon Graham; Kevin Leyton-Brown; Tim Roughgarden;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the first nontrivial procedure for configuring heuristic algorithms to maximize the utility provided to their end users while also offering theoretical guarantees about performance.
2648, Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition
Meena Jagadeesan; Michael Jordan; Jacob Steinhardt; Nika Haghtalab;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, these trends take the perspective of a single model-provider in isolation, while in reality providers often compete with each other for users. In this work, we demonstrate that competition can fundamentally alter the behavior of these scaling trends, even causing overall predictive accuracy across users to be non-monotonic or decreasing with scale.
2649, Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
Junqi Gao; Zhichang Guo; Yao Li; Biqing Qi; Dong Li; Yuming Xing; Dazhi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we experimentally and theoretically demonstrated that neural networks trained on the same dataset have more consistent performance in High-Sample-Density-Regions (HSDR) of each class instead of low sample density regions.
2650, On The Adversarial Robustness of Out-of-distribution Generalization Models
Xin Zou; Weiwei Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by the theoretical results, we design two algorithms to improve the OOD adversarial robustness.
2651, Bayes Beats Cross Validation: Efficient and Accurate Ridge Regression Via Expectation Maximization
Shu Yu Tew; Mario Boley; Daniel Schmidt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel method for tuning the regularization hyper-parameter, $\lambda$, of ridge regression that is up to one order of magnitude faster than the fast leave-one-out cross validation algorithm (LOOCV).
2652, Efficient Model-Free Exploration in Low-Rank MDPs
Zak Mhammedi; Adam Block; Dylan J Foster; Alexander Rakhlin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose the first provably sample-efficient algorithm for exploration in Low-Rank MDPs that is both computationally efficient and model-free, allowing for general function approximation while requiring no structural assumptions beyond a reachability condition that we show is substantially weaker than that assumed in prior work.
2653, Conditional Independence Testing Under Model Misspecification
Felipe Maia Polo; Yuekai Sun; Moulinath Banerjee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Namely, we propose new approximations or upper bounds for the testing errors of three regression-based tests that depend on misspecification errors.
2654, Incomplete Multimodality-Diffused Emotion Recognition
Yuanzhi Wang; Yong Li; Zhen Cui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an Incomplete Multimodality-Diffused emotion recognition (IMDer) method to mitigate the challenge of MER under incomplete multimodalities.
2655, Pretraining Task Diversity and The Emergence of Non-Bayesian In-context Learning for Regression
Allan Raventós; Mansheej Paul; Feng Chen; Surya Ganguli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This raises a foundational question: can ICL solve fundamentally _new_ tasks that are very different from those seen during pretraining? To probe this question, we examine ICL’s performance on linear regression while varying the diversity of tasks in the pretraining dataset.
2656, SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection
Daehyun Kim; Sungyong Baik; Tae Hyun Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As such, we propose to transform the distribution of features at each location of a given image to different distributions.
2657, Learning to Discover Skills Through Guidance
HYUNSEUNG KIM; BYUNG KUN LEE; Sejik Park; Hojoon Lee; Dongyoon Hwang; Kyushik Min; Jaegul Choo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we have identified that the effectiveness of these rewards declines as the environmental complexity rises. Therefore, we present a novel USD algorithm, skill discovery with guidance (DISCO-DANCE), which (1) selects the guide skill which possesses the highest potential to reach unexplored states, (2) guides other skills to follow guide skill, then (3) the guided skills are dispersed to maximize their discriminability in unexplored states.
2658, Participatory Personalization in Classification
Hailey Joren; Chirag Nagpal; Katherine Heller; Berk Ustun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a model-agnostic algorithm to learn participatory systems for supervised learning tasks where models are personalized with categorical group attributes.
2659, MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers
Yu Zhang; Yepeng Liu; Duoqian Miao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Almost all studies split an image into single-granularity patches, with very few studies exploring the multi-granularity splitting of an image. Enlightened by this, we propose a two-stage multi-granularity framework, MG-ViT, to balance ViT's performance and computational cost.
2660, The Contextual Lasso: Sparse Linear Models Via Deep Neural Networks
Ryan Thompson; Amir Dezfouli; robert kohn;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To attain sparse coefficients, we train the network with a novel lasso regularizer in the form of a projection layer that maps the network's output onto the space of $\ell_1$-constrained linear models.
2661, Regularity As Intrinsic Reward for Free Play
Cansu Sancaktar; Justus Piater; Georg Martius;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose regularity as a novel reward signal for intrinsically-motivated reinforcement learning.
2662, Score-based Source Separation with Applications to Digital Communication Signals
Tejas Jayashankar; Gary C.F. Lee; Alejandro Lancho; Amir Weiss; Yury Polyanskiy; Gregory Wornell;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a new method for separating superimposed sources using diffusion-based generative models.
2663, Subspace Identification for Multi-Source Domain Adaptation
Zijian Li; Ruichu Cai; Guangyi Chen; Boyang Sun; Zhifeng Hao; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These requirements are challenging to satisfy in real-world applications. To mitigate the need for these strict assumptions, we propose a subspace identification theory that guarantees the disentanglement of domain-invariant and domain-specific variables under less restrictive constraints regarding domain numbers and transformation properties and thereby facilitating domain adaptation by minimizing the impact of domain shifts on invariant variables.
2664, Sampling from Structured Log-Concave Distributions Via A Soft-Threshold Dikin Walk
Oren Mangoubi; Nisheeth K. Vishnoi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Interest in this problem derives from its applications to Bayesian inference and differential privacy. We present a generalization of the Dikin walk to this setting that requires at most $O((md + d L^2 R^2) \times md^{\omega-1} \log(\frac{w}{\delta}))$ arithmetic operations to sample from $\pi$ within error $\delta>0$ in the total variation distance from a $w$-warm start.
2665, POMDP Planning for Object Search in Partially Unknown Environment
Yongbo Chen; Hanna Kurniawati;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Efficiently searching for target objects in complex environments, that contain various types of furniture, such as shelves, tables, and beds, is crucial for mobile robots, but it poses significant challenges due to various factors such as localization errors, limited field of view, and visual occlusion. To address this problem, we propose a Partially Observable Markov Decision Process (POMDP) formulation with a growing state space for object search in a 3D region.
2666, A Batch-to-Online Transformation Under Random-Order Model
Jing Dong; Yuichi Yoshida;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a transformation framework that can be utilized to develop online algorithms with low $\epsilon$-approximate regret in the random-order model from offline approximation algorithms.
2667, Online Nonstochastic Model-Free Reinforcement Learning
Udaya Ghai; Arushi Gupta; Karan Singh; Wenhan Xia; Elad Hazan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we explore robust model-free reinforcement learning algorithms for environments that may be dynamic or even adversarial.
2668, Optimal Time Complexities of Parallel Stochastic Optimization Methods Under A Fixed Computation Model
Alexander Tyurin; Peter Richtarik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new protocol that generalizes the classical oracle framework approach.
2669, Fast Approximation of Similarity Graphs with Kernel Density Estimation
Peter Macgregor; He Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, typical constructions of a similarity graph have high time complexity, and a quadratic space dependency with respect to $|X|$. We address this limitation and present a new algorithmic framework that constructs a sparse approximation of the fully connected similarity graph while preserving its cluster structure.
2670, Recurrent Temporal Revision Graph Networks
Yizhou Chen; Anxiang Zeng; Qingtao Yu; Kerui Zhang; Cao Yuanpeng; Kangle Wu; Guangda Huzhang; Han Yu; Zhiming Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, such subsampling leads to incomplete and biased neighbor information. To address this limitation, we propose a novel framework for temporal neighbor aggregation that uses the recurrent neural network with node-wise hidden states to integrate information from all historical neighbors for each node to acquire the complete neighbor information.
2671, Parameterizing Context: Unleashing The Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing
Yongrui Chen; Shenyu Zhang; Guilin Qi; Xinnan Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite recent advancements that partially alleviate these issues through semi-supervised data augmentation and retention of a few past examples, the performance is still limited by the volume of unsupervised data and stored examples. To overcome these challenges, this paper introduces a novel method integrating \textit{parameter-efficient fine-tuning} (PEFT) and \textit{in-context tuning} (ICT) for training a continual table semantic parser.
2672, Partial Counterfactual Identification of Continuous Outcomes with A Curvature Sensitivity Model
Valentyn Melnychuk; Dennis Frauen; Stefan Feuerriegel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing methods for counterfactual inference with continuous outcomes aim at point identification and thus make strong and unnatural assumptions about the underlying structural causal model. In this paper, we relax these assumptions and aim at partial counterfactual identification of continuous outcomes, i.e., when the counterfactual query resides in an ignorance interval with informative bounds.
2673, Model-Free Reinforcement Learning with The Decision-Estimation Coefficient
Dylan J Foster; Noah Golowich; Jian Qian; Alexander Rakhlin; Ayush Sekhari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we show that by combining Estimation-to-Decisions witha specialized form of optimistic estimation introduced byZhang (2022), it is possible to obtain guaranteesthat improve upon those of Foster et al. (2021) byaccommodating more lenient notions of estimation error.
2674, ProteinNPT: Improving Protein Property Prediction and Design with Non-parametric Transformers
Pascal Notin; Ruben Weitzman; Debora Marks; Yarin Gal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present ProteinNPT, a non-parametric transformer variant tailored for protein sequences and particularly suited to label-scarce and multi-task optimization settings.
2675, Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Model
Yule Wang; Zijing Wu; Chengrui Li; Anqi Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Thus, those solutions lead to poor quality in dynamics structures and overall performance after alignment. To tackle this problem, we propose a method leveraging the expressiveness of diffusion model to relieve such issues.
2676, FeCAM: Exploiting The Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
Dipam Goswami; Yuyang Liu; Bartłomiej Twardowski; Joost van de Weijer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes.
2677, Resetting The Optimizer in Deep RL: An Empirical Study
Kavosh Asadi; Rasool Fakoor; Shoham Sabach;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We focus on the task of approximating the optimal value function in deep reinforcement learning.
2678, Towards Anytime Classification in Early-Exit Architectures By Enforcing Conditional Monotonicity
Metod Jazbec; James Allingham; Dan Zhang; Eric Nalisnick;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, we demonstrate that current early-exit networks are not directly applicable to anytime settings, as the quality of predictions for individual data points is not guaranteed to improve with longer computation. To address this shortcoming, we propose an elegant post-hoc modification, based on the Product-of-Experts, that encourages an early-exit network to become gradually confident.
2679, Strategic Data Sharing Between Competitors
Nikita Tsoy; Nikola Konstantinov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite this opportunity, firms face a dilemma when considering data sharing with competitors—while collaboration can improve a company’s machine learning model, it may also benefit competitors and hence reduce profits. In this work, we introduce a general framework for analyzing this data-sharing trade-off.
2680, Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression
Ayoub El Hanchi; Murat Erdogdu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the performance of empirical risk minimization on the $p$-norm linear regression problem for $p \in (1, \infty)$.
2681, No-Regret Online Prediction with Strategic Experts
Omid Sadeghi; Maryam Fazel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our goal is to design algorithms that satisfy the following two requirements: 1) \emph{Incentive-compatible}: Incentivize the experts to report their beliefs truthfully, and 2) \emph{No-regret}: Achieve sublinear regret with respect to the true beliefs of the best fixed set of $m$ experts in hindsight.
2682, A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning
Ganyu Wang; Qingsong Zhang; Xiang Li; Boyu Wang; Bin Gu; Charles Ling;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, there are still two key problems that have yet to be resolved. First, the convergence rate of ZOO-based VFL is significantly slower compared to gradient-based VFL, resulting in low efficiency in model training and more communication round, which hinders its application on large neural networks. Second, although ZOO-based VFL has demonstrated resistance to state-of-the-art (SOTA) attacks, its privacy guarantee lacks a theoretical explanation. To address these challenges, we propose a novel cascaded hybrid optimization approach that employs a zeroth-order (ZO) gradient on the most critical output layer of the clients, with other parts utilizing the first-order (FO) gradient.
2683, Two Heads Are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning
Jiahui Li; Kun Kuang; Baoxiang Wang; Xingchen Li; Long Chen; Fei Wu; Jun Xiao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a exploration method that incorporate the curiosity-based and influence-based exploration (COIN) which is simple but effective in various situations.
2684, Every Parameter Matters: Ensuring The Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction
Hanhan Zhou; Tian Lan; Guru Prasadh Venkataramani; Wenbo Ding;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a unifying framework for heterogeneous FL algorithms with online model extraction and provide a general convergence analysis.
2685, When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Tianwei Ni; Michel Ma; Benjamin Eysenbach; Pierre-Luc Bacon;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the underlying reason for their strong performance remains unclear: is it because they learn effective memory, or because they perform effective credit assignment? By introducing formal definitions of memory length and credit assignment length, we design configurable toy examples to measure these distinct quantities.
2686, 3D-Aware Visual Question Answering About Parts, Poses and Occlusions
Xingrui Wang; Zhuowan Li; Wufei Ma; Adam Kortylewski; Alan Yuille;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce the task of 3D-aware VQA, which focuses on challenging questions that require a compositional reasoning over the 3D structure of visual scenes.
2687, Active Bipartite Ranking
James Cheshire; Vincent Laurent; Stephan Clémençon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop an active learning framework for the bipartite ranking problem.
2688, DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning
Xunhan Hu; Jian Zhao; Wengang Zhou; Ruili Feng; Houqiang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing methods struggle to distinguish and exploit important individual experiences, as they lack an effective way to decompose the team reward into individual rewards. To address this challenge, we propose DIFFER, a powerful theoretical framework for decomposing individual rewards to enable fair experience replay in MARL.
2689, Training Energy-Based Normalizing Flow with Score-Matching Objectives
Chen-Hao Chao; Wei-Fang Sun; Yen-Chang Hsu; Zsolt Kira; Chun-Yi Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we establish a connection between the parameterization of flow-based and energy-based generative models, and present a new flow-based modeling approach called energy-based normalizing flow (EBFlow).
2690, NAS-X: Neural Adaptive Smothing Via Twisting
Dieterich Lawson; Michael Li; Scott Linderman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Neural Adaptive Smoothing via Twisting (NAS-X), a method for learning and inference in sequential latent variable models that uses smoothing sequential Monte Carlo (SMC) within a reweighted wake-sleep (RWS) framework.
2691, On The Importance of Feature Separability in Predicting Out-Of-Distribution Error
RENCHUNZI XIE; Hongxin Wei; Lei Feng; Yuzhou Cao; Bo An;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While previous methods emphasize the connection between distribution difference and OOD accuracy, we show that a large domain gap not necessarily leads to a low test accuracy. In this paper, we investigate this problem from the perspective of feature separability empirically and theoretically.
2692, Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control
Chao Li; Chen GONG; Qiang He; Xinwen Hou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our new analysis reveals that the sample efficiency of previous ensemble DRL algorithms may be limited by sub-policies that are not as diverse as they could be. Motivated by these findings, our study introduces a new ensemble RL algorithm, termed \textbf{T}rajectories-awar\textbf{E} \textbf{E}nsemble exploratio\textbf{N} (TEEN).
2693, Combinatorial Group Testing with Selfish Agents
Georgios Chionas; Dariusz Kowalski; Piotr Krysta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the Combinatorial Group Testing (CGT) problem in a novel game-theoretic framework, with a solution concept of Adversarial Equilibrium (AE).
2694, One Objective to Rule Them All: A Maximization Objective Fusing Estimation and Planning for Exploration
Zhihan Liu; Miao Lu; WEI XIONG; Han Zhong; Hao Hu; Shenao Zhang; Sirui Zheng; Zhuoran Yang; Zhaoran Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, to cope with general function approximators, most of them involve impractical algorithmic components to incentivize exploration, such as data-dependent level-set constraints or complex sampling procedures. To address this challenge, we propose an easy-to-implement framework called Maximize to Explore (MEX), which optimizes a single objective that integrates the estimation and planning components in RL while balancing exploration and exploitation automatically.
2695, Tuning Multi-mode Token-level Prompt Alignment Across Modalities
Dongsheng Wang; Miaoge Li; Xinyang Liu; MingSheng Xu; Bo Chen; Hanwang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To address the limitation, we propose a multi-mode token-level tuning framework that leverages the optimal transportation to learn and align a set of prompt tokens across modalities.
2696, Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of D-dimensional Points
Alexander Kozachinskiy; Valentino Delle Rose; Cristobal Rojas; Mircea Petrache; Pablo Barceló;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It has also been observed that it underlies the design of several graph neural network architectures, whose capabilities and performance can be understood in terms of the expressive power of this test. Motivated by recent developments in machine learning applications to datasets involving three-dimensional objects, we study when the WL test is {\em complete} for clouds of Euclidean points represented by complete distance graphs, i.e., when it can distinguish, up to isometry, any arbitrary such cloud.
2697, Probabilistic Inference in Reinforcement Learning Done Right
Jean Tarbouriech; Tor Lattimore; Brendan O'Donoghue;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we undertake a rigorous Bayesian treatment of the posterior probability of state-action optimality and clarify how it flows through the MDP.
2698, Gradient-Free Kernel Stein Discrepancy
Matthew Fisher; Chris Oates;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper focuses on posterior approximation using Stein discrepancies, and introduces a collection of non-canonical Stein discrepancies that are gradient-free, meaning that derivatives of the statistical model are not required.
2699, NeRF-IBVS: Visual Servo Based on NeRF for Visual Localization and Navigation
Yuanze Wang; Yichao Yan; Dianxi Shi; Wenhan Zhu; Jianqiang Xia; Tan Jeff; Songchang Jin; KE GAO; XIAOBO LI; Xiaokang Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel visual localization method that achieves accurate localization while using only a few posed images compared to other localization methods.
2700, Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation
Jia-Xing Zhong; Ta-Ying Cheng; Yuhang He; Kai Lu; Kaichen Zhou; Andrew Markham; Niki Trigoni;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes. In view of the tightly coupled relationship between segmentation and motion estimates, we present an SE(3) equivariant architecture and a training strategy to tackle this task in an unsupervised manner.
2701, (Almost) Provable Error Bounds Under Distribution Shift Via Disagreement Discrepancy
Elan Rosenfeld; Saurabh Garg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We derive a new, (almost) guaranteed upper bound on the error of deep neural networks under distribution shift using unlabeled test data.
2702, Inner Product-based Neural Network Similarity
Wei Chen; Zichen Miao; Qiang Qiu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a new paradigm for reducing NN representational similarity to filter subspace distance.
2703, Diffusion Representation for Asymmetric Kernels Via Magnetic Transform
Mingzhen He; FAN He; Ruikai Yang; Xiaolin Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Via theoretical proof, we successfully establish a diffusion representation framework with the magnetic transform, named MagDM.
2704, Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States
Valerii Iakovlev; Markus Heinonen; Harri Lähdesmäki;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel grid-independent model for learning partial differential equations (PDEs) from noisy and partial observations on irregular spatiotemporal grids.
2705, LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation
Jiajun Tang; Haofeng Zhong; Shuchen Weng; Boxin Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the ilLumination-Aware conditional Image Repainting (LuminAIRe) task to address the unrealistic lighting effects in recent conditional image repainting (CIR) methods.
2706, Diffused Task-Agnostic Milestone Planner
Mineui Hong; Minjae Kang; Songhwai Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take a step further to leverage the sequence modeling method in wider areas such as long-term planning, vision-based control, and multi-task decision-making.
2707, Intervention Generalization: A View from Factor Graph Models
Gecia Bravo-Hermsdorff; David Watson; Jialin Yu; Jakob Zeitler; Ricardo Silva;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take a close look at how to warrant a leap from past experiments to novel conditions based on minimal assumptions about the factorization of the distribution of the manipulated system, communicated in the well-understood language of factor graph models.
2708, Test-time Training for Matching-based Video Object Segmentation
Juliette Bertrand; Georgios Kordopatis Zilos; Yannis Kalantidis; Georgios Tolias;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We focus on matching-based VOS under distribution shifts such as video corruptions, stylization, and sim-to-real transfer.
2709, Loss Decoupling for Continual Learning
Yan-Shuo Liang; Wu-Jun Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a simple yet effective method, called loss decoupling (LODE), for continual learning.
2710, Optimal Transport-Guided Conditional Score-Based Diffusion Model
Xiang Gu; Liwei Yang; Jian Sun; Zongben Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To tackle the applications with partially paired or even unpaired dataset, we propose a novel Optimal Transport-guided Conditional Score-based diffusion model (OTCS) in this paper.
2711, The Behavior and Convergence of Local Bayesian Optimization
Kaiwen Wu; Kyurae Kim; Roman Garnett; Jacob Gardner;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We first study the behavior of the local approach, and find that the statistics of individual local solutions of Gaussian process sample paths are surprisingly good compared to what we would expect to recover from global methods. We then present the first rigorous analysis of such a Bayesian local optimization algorithm recently proposed by M�ller et al. (2021), and derive convergence rates in both the noisy and noiseless settings.
2712, Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
Emmanuel Abbe; Elisabetta Cornacchia; Aryo Lotfi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here we show a separation result in the number of training steps with standard (bounded) learning rates on a common sample distribution: if the data distribution is a mixture of sparse and dense inputs, there exists a regime in which a 2-layer ReLU neural network trained by a curriculum noisy-GD (or SGD) algorithm that uses sparse examples first, can learn parities of sufficiently large degree, while any fully connected neural network of possibly larger width or depth trained by noisy-GD on the unordered samples cannot learn without additional steps.
2713, Spike-driven Transformer
Man Yao; JiaKui Hu; Zhaokun Zhou; Li Yuan; Yonghong Tian; Bo Xu; Guoqi Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we incorporate the spike-driven paradigm into Transformer by the proposed Spike-driven Transformer with four unique properties: (1) Event-driven, no calculation is triggered when the input of Transformer is zero; (2) Binary spike communication, all matrix multiplications associated with the spike matrix can be transformed into sparse additions; (3) Self-attention with linear complexity at both token and channel dimensions; (4) The operations between spike-form Query, Key, and Value are mask and addition.
2714, Accelerating Motion Planning Via Optimal Transport
An T. Le; Georgia Chalvatzaki; Armin Biess; Jan Peters;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In response to these issues, we introduce Motion Planning via Optimal Transport (MPOT) - a \textit{gradient-free} method that optimizes a batch of smooth trajectories over highly nonlinear costs, even for high-dimensional tasks, while imposing smoothness through a Gaussian Process dynamics prior that serves as cost. To facilitate batch trajectory optimization, we introduce an original zero-order and highly-parallelizable update rule -- the Sinkhorn Step, which uses the regular polytope family for its search directions; each regular polytope, centered on trajectory waypoints, serves as a local neighborhood, effectively acting as a trust region, where the Sinkhorn Step ``transports'' local waypoints toward low-cost regions.
2715, Generalization Bounds for Neural Ordinary Differential Equations and Deep Residual Networks
Pierre Marion;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we consider a large family of parameterized ODEs with continuous-in-time parameters, which include time-dependent neural ODEs.
2716, Towards Data-Algorithm Dependent Generalization: A Case Study on Overparameterized Linear Regression
Jing Xu; Jiaye Teng; Yang Yuan; Andrew Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In many scenarios, their failure can be attributed to obscuring the crucial interplay between the training algorithm and the underlying data distribution. To address this issue, we propose a concept named compatibility, which quantitatively characterizes generalization in a both data-relevant and algorithm-relevant manner.
2717, Generalizable One-shot Neural Head Avatar
Xueting Li; Shalini De Mello; Sifei Liu; Koki Nagano; Umar Iqbal; Jan Kautz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image.
2718, Self-supervised Object-centric Learning for Videos
Görkay Aydemir; Weidi Xie; Fatma Guney;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose the first fully unsupervised method for segmenting multiple objects in real-world sequences.
2719, GUST: Combinatorial Generalization By Unsupervised Grouping with Neuronal Coherence
Hao Zheng; Hui Lin; Rong Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the grouping ability and therefore combinatorial generalization are still challenging artificial neural networks. Inspired by the evidence that successful grouping is indicated by neuronal coherence in the human brain, we introduce GUST (Grouping Unsupervisely by Spike Timing network), an iterative network architecture with biological constraints to bias the network towards a dynamical state of neuronal coherence that softly reflects the grouping information in the temporal structure of its spiking activity.
2720, One-for-All: Bridge The Gap Between Heterogeneous Architectures in Knowledge Distillation
Zhiwei Hao; Jianyuan Guo; Kai Han; Yehui Tang; Han Hu; Yunhe Wang; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures.
2721, FLSL: Feature-level Self-supervised Learning
Qing Su; Anton Netchaev; Hai Li; Shihao Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By employing transformer for joint embedding and clustering, we propose a two-level feature clustering SSL method, coined Feature-Level Self-supervised Learning (FLSL).
2722, Sparse Deep Learning for Time Series Data: Theory and Applications
Mingxuan Zhang; Yan Sun; Faming Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, most existing research has focused on problems where the observations are independent and identically distributed (i.i.d.), and there has been little work on the problems where the observations are dependent, such as time series data and sequential data in natural language processing. This paper aims to address this gap by studying the theory for sparse deep learning with dependent data.
2723, Investigating How ReLU-networks Encode Symmetries
Georg Bökman; Fredrik Kahl;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we investigate whether equivariance of a network implies that all layers are equivariant.
2724, Hyperbolic VAE Via Latent Gaussian Distributions
Seunghyuk Cho; Juyong Lee; Dongwoo Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a Gaussian manifold variational auto-encoder (GM-VAE) whose latent space consists of a set of Gaussian distributions.
2725, FedL2P: Federated Learning to Personalize
Royson Lee; Minyoung Kim; Da Li; Xinchi Qiu; Timothy Hospedales; Ferenc Huszar; Nicholas Lane;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we consider the federated meta-learning problem of learning personalization strategies.
2726, Meta-learning Families of Plasticity Rules in Recurrent Spiking Networks Using Simulation-based Inference
Basile Confavreux; Poornima Ramesh; Pedro Goncalves; Jakob H Macke; Tim Vogels;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we develop a simulation-based inference (SBI) method for sequentially filtering plasticity rules through an increasingly fine mesh of constraints that can be modified on-the-fly.
2727, Pseudo-Likelihood Inference
Theo Gruner; Fabio Muratore; Boris Belousov; Daniel Palenicek; Jan Peters;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Pseudo-Likelihood Inference (PLI), a new method that brings neural approximation into ABC, making it competitive on challenging Bayesian system identification tasks.
2728, Squared Neural Families: A New Class of Tractable Density Models
Russell Tsuchida; Cheng Soon Ong; Dino Sejdinovic;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We develop and investigate a new class of probability distributions, which we call a Squared Neural Family (SNEFY), formed by squaring the 2-norm of a neural network and normalising it with respect to a base measure.
2729, Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data
Saptarshi Roy; Raymond K. W. Wong; Yang Ni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this article, we introduce a functional linear structural equation model for causal structure learning when the underlying graph involving the multivariate functions may have cycles.
2730, Debiased and Denoised Entity Recognition from Distant Supervision
Haobo Wang; Yiwen Dong; Ruixuan Xiao; Fei Huang; Gang Chen; Junbo Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we innovatively identify two types of biases that were omitted by prior work, and these biases lead to inferior performance of the distant-supervised NER setup. First, we characterize the noise concealed in the distant labels as highly structural rather than fully randomized. Second, the self-training framework would ubiquitously introduce an inherent bias that causes erroneous behavior in both sample selection and eventually prediction. To cope with these problems, we propose a novel self-training framework, dubbed DesERT.
2731, Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms
Sijia Zhou; Yunwen Lei; Ata Kaban;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce an assumption of sub-exponential stability parameter, which allows a general treatment that we instantiate in two applications: stochastic gradient descent and randomized coordinate descent.
2732, Decision Tree for Locally Private Estimation with Public Data
Yuheng Ma; Han Zhang; Yuchao Cai; Hanfang Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we introduce an efficient algorithm called Locally differentially Private Decision Tree (LPDT) for LDP regression.
2733, GRAND-SLAMIN’ Interpretable Additive Modeling with Structural Constraints
Shibal Ibrahim; Gabriel Afriat; Kayhan Behdin; Rahul Mazumder;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a flexible GRAND-SLAMIN framework that can learn GAMs with interactions under sparsity with/without additional structural interpretability constraints in a differentiable end-to-end fashion.
2734, Invariant Anomaly Detection Under Distribution Shifts: A Causal Perspective
João Carvalho; Mengtao Zhang; Robin Geyer; Carlos Cotrini; Joachim M Buhmann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, by leveraging tools from causal inference we attempt to increase the resilience of anomaly detection models to different kinds of distribution shifts.
2735, GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces
Josephine Lamp; Mark Derdzinski; Christopher Hannemann; Joost van der Linden; Lu Feng; Tianhao Wang; David Evans;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we present GlucoSynth, a novel privacy-preserving GAN framework to generate synthetic glucose traces.
2736, Logarithmic Bayes Regret Bounds
Alexia Atsidakou; Branislav Kveton; Sumeet Katariya; Constantine Caramanis; Sujay Sanghavi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We derive the first finite-time logarithmic regret bounds for Bayesian bandits.
2737, Does Invariant Graph Learning Via Environment Augmentation Learn Invariance?
Yongqiang Chen; Yatao Bian; Kaiwen Zhou; Binghui Xie; Bo Han; James Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we find that it is fundamentally impossible to learn invariant graph representations via environment augmentation without additional assumptions.
2738, Unbounded Differentially Private Quantile and Maximum Estimation
David Durfee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we consider the problem of differentially private computation ofquantiles for the data, especially the highest quantiles such as maximum, butwith an unbounded range for the dataset.
2739, Transfer Learning for Atomistic Simulations Using GNNs and Kernel Mean Embeddings
John Falk; Luigi Bonati; Pietro Novelli; Michele Parrinello; Massimiliano Pontil;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, deep learning pipelines are notoriously data-hungry while generating reference calculations is computationally demanding. To overcome this difficulty, we propose a transfer learning algorithm that leverages the ability of graph neural networks (GNNs) in describing chemical environments together with kernel mean embeddings.
2740, Honesty Is The Best Policy: Defining and Mitigating AI Deception
Francis Ward; Francesca Toni; Francesco Belardinelli; Tom Everitt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a formal definition of deception in structural causal games, grounded in the philosophyliterature, and applicable to real-world machine learning systems.
2741, Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
Mhairi Dunion; Trevor McInroe; Kevin Sebastian Luck; Josiah Hanna; Stefano Albrecht;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose an auxiliary task for RL algorithms that learns a disentangled representation of high-dimensional observations with correlated features by minimising the conditional mutual information between features in the representation.
2742, Recaptured Raw Screen Image and Video Demoiréing Via Channel and Spatial Modulations
Huanjing Yue; Yijia Cheng; Xin Liu; Jingyu Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We observe that the moiré patterns in raw domain is simpler than those in sRGB domain, and the moiré patterns in raw color channels have different properties. Therefore, we propose an image and video demoiréing network tailored for raw inputs.
2743, SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models
XIAOSONG MA; Jie ZHANG; Song Guo; Wenchao Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose SwapPrompt, a novel framework that can effectively leverage the self-supervised contrastive learning to facilitate the test-time prompt adaptation.
2744, STREAMER: Streaming Representation Learning and Event Segmentation in A Hierarchical Manner
Ramy Mounir; Sujal Vijayaraghavan; Sudeep Sarkar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel self-supervised approach for hierarchical representation learning and segmentation of perceptual inputs in a streaming fashion.
2745, Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation
Peiwen Yuan; Xinglin Wang; Jiayi Shi; Bin Sun; Yiwei Li; Prof. Kan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: There is a danger that the nonuniform score distribution will weaken the robustness of TDEM through our theoretical analysis. To tackle these problems, we propose Better Correlation and Robustness (BCR), a distribution-balanced self-supervised learning framework for TDEM.
2746, Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments Via Random Walk Stochastic ADMM
Ziba Parsons; Fei Dou; Houyi Du; Zheng Song; Jin Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper explores the challenges of implementing Federated Learning (FL) in practical scenarios featuring isolated nodes with data heterogeneity, which can only be connected to the server through wireless links in an infrastructure-less environment. To overcome these challenges, we propose a novel mobilizing personalized FL approach, which aims to facilitate mobility and resilience.
2747, Generative Neural Fields By Mixtures of Neural Implicit Functions
Tackgeun You; Jungtaek Kim; Mijeong Kim; Bohyung Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel approach for learning the generative neural fields represented by linear combinations of implicit basis networks.
2748, Neural Graph Generation from Graph Statistics
Kiarash Zahirnia; Oliver Schulte; Mark Coates; Yaochen Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We describe a new setting for learning a deep graph generative model (GGM) from aggregate graph statistics, rather than from the graph adjacency matrix.
2749, LayoutPrompter: Awaken The Design Ability of Large Language Models
Jiawei Lin; Jiaqi Guo; Shizhao Sun; Zijiang Yang; Jian-Guang Lou; Dongmei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose LayoutPrompter to address the aforementioned issues by simply prompting GPT-3 text-davinci-003 model with a few demonstration examples.
2750, Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent
Lingjiong Zhu; Mert Gurbuzbalaban; Anant Raj; Umut Simsekli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we make a novel connection between learning theory and applied probability and introduce a unified guideline for proving Wasserstein stability bounds for stochastic optimization algorithms.
2751, Accurate Interpolation for Scattered Data Through Hierarchical Residual Refinement
Shizhe Ding; Boyang Xia; Dongbo Bu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These residuals, which provide observations of an underlying residual function, can guide predicting interpolation functions, but have not been exploited by the existing approaches. To fill this gap, we propose Hierarchical INTerpolation Network (HINT), which utilizes the residuals on observed points to guide target function estimation in a hierarchical fashion.
2752, On The Convergence of Shallow Transformers
Yongtao Wu; Fanghui Liu; Grigorios Chrysos; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we aim to build the global convergence theory of shallow Transformers under a realistic setting from the perspective of architectures, initialization, and scaling under a finite width regime.
2753, A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization
Kansei Ushiyama; Shun Sato; Takayasu Matsuo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consequently, even if we derive insights from continuous DEs, we still need to perform individualized and tedious calculations for the analysis of each method. This paper aims to bridge this gap by introducing a new concept called ``weak discrete gradient'' (wDG), which consolidates the conditions required for discrete versions of gradients in the DE approach arguments.
2754, Semantic Segmentation of Sparse Irregular Point Clouds for Leaf/wood Discrimination
Yuchen BAI; Jean-Baptiste Durand; Grégoire Vincent; Florence Forbes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we introduce a neural network model based on the Pointnet ++ architecture which makes use of point geometry only (excluding any spectral information).
2755, Real-World Image Super-Resolution As Multi-Task Learning
Wenlong Zhang; Xiaohui Li; Guangyuan SHI; Xiangyu Chen; Yu Qiao; Xiaoyun Zhang; Xiao-Ming Wu; Chao Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-task learning perspective.
2756, Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances
Shahriar Talebi; Amirhossein Taghvaei; Mehran Mesbahi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper examines learning the optimal filtering policy, known as the Kalman gain, for a linear system with unknown noise covariance matrices using noisy output data.
2757, New Bounds for Hyperparameter Tuning of Regression Problems Across Instances
Maria-Florina Balcan; Anh Nguyen; Dravyansh Sharma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For tuning the regularization parameters of logistic regression, we introduce a new approach to studying the learning guarantee via an approximation of the validation loss function class.
2758, Rethinking Gauss-Newton for Learning Over-parameterized Models
Michael Arbel; Romain Menegaux; Pierre Wolinski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We find that, while GN is consistently faster than GD in finding a global optimum, the performance of the learned model on a test dataset is heavily influenced by both the learning rate and the variance of the randomly initialized network's weights.
2759, 3D Indoor Instance Segmentation in An Open-World
Mohamed El Amine Boudjoghra; Salwa Al Khatib; Jean Lahoud; Hisham Cholakkal; Rao Anwer; Salman Khan; Fahad Shahbaz Khan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we introduce an open-world 3D indoor instance segmentation method, where an auto-labeling scheme is employed to produce pseudo-labels during training and induce separation to separate known and unknown category labels.
2760, Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills
Denis Blessing; Onur Celik; Xiaogang Jia; Moritz Reuss; Maximilian Li; Rudolf Lioutikov; Gerhard Neumann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we proposeInformation Maximizing Curriculum, a curriculum-based approach that assignsa weight to each data point and encourages the model to specialize in the data itcan represent, effectively mitigating the mode-averaging problem by allowing themodel to ignore data from modes it cannot represent.
2761, Bias in Evaluation Processes: An Optimization-Based Model
L. Elisa Celis; Amit Kumar; Anay Mehrotra; Nisheeth K. Vishnoi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We consider evaluation processes that estimate the distribution of the utility of an individual for a task and model it as a solution to a loss minimization problem subject to an information constraint.
2762, Bounding The Invertibility of Privacy-preserving Instance Encoding Using Fisher Information
Kiwan Maeng; Chuan Guo; Sanjay Kariyappa; G. Edward Suh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a theoretically-principled measure for the invertibility of instance encoding based on Fisher information that is broadly applicable to a wide range of popular encoders.
2763, Masked Image Residual Learning for Scaling Deeper Vision Transformers
Guoxi Huang; Hongtao Fu; Adrian G. Bors;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To ease the training of deeper ViTs, we introduce a self-supervised learning framework called $\textbf{M}$asked $\textbf{I}$mage $\textbf{R}$esidual $\textbf{L}$earning ($\textbf{MIRL}$), which significantly alleviates the degradation problem, making scaling ViT along depth a promising direction for performance upgrade.
2764, A State Representation for Diminishing Rewards
Ted Moskovitz; Samo Hromadka; Ahmed Touati; Diana Borsa; Maneesh Sahani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, in the natural world, sequential tasks are rarely independent, and instead reflect shifting priorities based on the availability and subjective perception of rewarding stimuli. Reflecting this disjunction, in this paper we study the phenomenon of diminishing marginal utility and introduce a novel state representation, the $\lambda$ representation ($\lambda$R) which, surprisingly, is required for policy evaluation in this setting and which generalizes the SR as well as several other state representations from the literature.
2765, Order Matters in The Presence of Dataset Imbalance for Multilingual Learning
Dami Choi; Derrick Xin; Justin Gilmer; Hamid Dadkhahi; Ankush Garg; Orhan Firat; Chih-Kuan Yeh; Andrew Dai; Behrooz Ghorbani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we empirically study the optimization dynamics of multi-task learning.
2766, Dual Self-Awareness Value Decomposition Framework Without Individual Global Max for Cooperative MARL
Zhiwei Xu; Bin Zhang; dapeng li; Guangchong Zhou; Zeren Zhang; Guoliang Fan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a dual self-awareness value decomposition framework, inspired by the notion of dual self-awareness in psychology, that entirely rejects the IGM premise.
2767, AbDiffuser: Full-atom Generation of In-vitro Functioning Antibodies
Karolis Martinkus; Jan Ludwiczak; WEI-CHING LIANG; Julien Lafrance-Vanasse; Isidro Hotzel; Arvind Rajpal; Yan Wu; Kyunghyun Cho; Richard Bonneau; Vladimir Gligorijevic; Andreas Loukas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences.
2768, AVIS: Autonomous Visual Information Seeking with Large Language Models
Ziniu Hu; Ahmet Iscen; Chen Sun; Kai-Wei Chang; Yizhou Sun; Cordelia Schmid; David Ross; Alireza Fathi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose an autonomous information seeking visual question answering framework, AVIS.
2769, IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval
Haixin Wang; Hao Wu; Jinan Sun; Shikun Zhang; Chong Chen; Xian-Sheng Hua; Xiao Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the problem of unsupervised domain adaptive hashing, which leverage knowledge from a label-rich source domain to expedite learning to hash on a label-scarce target domain.
2770, Fragment-based Pretraining and Finetuning on Molecular Graphs
Kha-Dinh Luong; Ambuj K Singh;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose pretraining GNNs at the fragment level, which serves as a promising middle ground to overcome the limitations of node-level and graph-level pretraining.
2771, Hierarchical Clustering with Dot Products Recovers Hidden Tree Structure
Annie Gray; Alexander Modell; Patrick Rubin-Delanchy; Nick Whiteley;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure.
2772, Smoothing The Landscape Boosts The Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
Alex Damian; Eshaan Nichani; Rong Ge; Jason Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we close the gap between the upper and lower bounds by showing that online SGD on a smoothed loss learns $w^\star$ with $n \gtrsim d^{k^\star/2}$ samples.
2773, Causes and Effects of Unanticipated Numerical Deviations in Neural Network Inference Frameworks
Alex Schlögl; Nora Hofer; Rainer Böhme;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We identify the influencing factors in a typical ML framework and experimentally isolate the distinct causes of numerical deviations.
2774, PUe: Biased Positive-Unlabeled LearningEnhancement By Causal Inference
Xutao Wang; Hanting Chen; Tianyu Guo; Yunhe Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a PU learning enhancement (PUe) algorithm based on causal inference theory, which employs normalized propensity scores and normalized inverse probability weighting (NIPW) techniques to reconstruct the loss function, thus obtaining a consistent, unbiased estimate of the classifier and enhancing the model's performance.
2775, Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks
Ziyi Huang; Henry Lam; Haofeng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building upon the recent neural tangent kernel theory, we create statistically guaranteed schemes to principally \emph{quantify}, and \emph{remove}, the procedural uncertainty of over-parameterized neural networks with very low computation effort.
2776, Explaining Predictive Uncertainty with Information Theoretic Shapley Values
David Watson; Joshua O'Hara; Niek Tax; Richard Mudd; Ido Guy;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We adapt the popular Shapley value framework to explain various types of predictive uncertainty, quantifying each feature's contribution to the conditional entropy of individual model outputs.
2777, Bayesian Optimization with Cost-varying Variable Subsets
Sebastian Tay; Chuan Sheng Foo; Daisuke Urano; Richalynn Leong; Bryan Kian Hsiang Low;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the problem of Bayesian optimization with cost-varying variable subsets (BOCVS) where in each iteration, the learner chooses a subset of query variables and specifies their values while the rest are randomly sampled.
2778, Language Model Alignment with Elastic Reset
Michael Noukhovitch; Samuel Lavoie; Florian Strub; Aaron Courville;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Elastic Reset, a new algorithm that achieves higher reward with less drift without explicitly modifying the training objective.
2779, Towards A Richer 2D Understanding of Hands at Scale
Tianyi Cheng; Ayda Hassen; Dandan Shan; Richard Higgins; David Fouhey;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To help AI systems obtain a better understanding of hand interactions, we introduce a new model that produces a rich understanding of hand interaction.
2780, The Exact Sample Complexity Gain from Invariances for Kernel Regression
Behrooz Tahmasebi; Stefanie Jegelka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In practice, encoding invariances into models improves sample complexity. In this work, we study this phenomenon from a theoretical perspective.
2781, Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks
Hao-Kai Zhang; Chenghong Zhu; Mingrui Jing; Xin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we develop a no-go theorem for learning an unknown quantum state with QNNs even starting from a high-fidelity initial state.
2782, When Is Agnostic Reinforcement Learning Statistically Tractable?
Zeyu Jia; Gene Li; Alexander Rakhlin; Ayush Sekhari; Nati Srebro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Towards that end, we introduce a new complexity measure, called the \emph{spanning capacity}, that depends solely on the set \(\Pi\) and is independent of the MDP dynamics.
2783, Conformalized Matrix Completion
Yu Gui; Rina Barber; Cong Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a distribution-free method for predictive inference in the matrix completion problem.
2784, Balancing Risk and Reward: An Automated Phased Release Strategy
Yufan Li; Jialiang Mao; Iavor Bojinov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Performing phased releases in a principled way requires selecting the proportion of units assigned to the new release in a way that balances the risk of an adverse effect with the need to iterate and learn from the experiment rapidly. In this paper, we formalize this problem and propose an algorithm that automatically determines the release percentage at each stage in the schedule, balancing the need to control risk while maximizing ramp-up speed.
2785, Offline Imitation Learning with Variational Counterfactual Reasoning
Zexu Sun; Bowei He; Jinxin Liu; Shuai Zhang; Xu Chen; Chen Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To effectively remove spurious features that would otherwise bias the agent and hinder generalization, we propose a framework named \underline{O}ffline \underline{I}mitation \underline{L}earning with \underline{C}ounterfactual data \underline{A}ugmentation (OILCA).
2786, Globally Injective and Bijective Neural Operators
Takashi Furuya; Michael Puthawala; Matti Lassas; Maarten V. de Hoop;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recently there has been great interest in operator learning, where networks learn operators between function spaces from an essentially infinite-dimensional perspective. In this work we present results for when the operators learned by these networks are injective and surjective.
2787, Strategic Classification Under Unknown Personalized Manipulation
Avrim Blum; Omar Montasser; Han Shao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We formalize the learning problem in an interaction model where the learner first deploys a classifier and the agent manipulates the feature vector within their manipulation set to game the deployed classifier.
2788, HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
Junkun Yuan; Xinyu Zhang; Hao Zhou; Jian Wang; Zhongwei Qiu; Zhiyin Shao; Shaofeng Zhang; Sifan Long; Kun Kuang; Kun Yao; Junyu Han; Errui Ding; Lanfen Lin; Fei Wu; Jingdong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
2789, DELTA: Diverse Client Sampling for Fasting Federated Learning
Lin Wang; Yongxin Guo; Tao Lin; Xiaoying Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing sampling methods are either biased or can be further optimized for faster convergence. In this paper, we present DELTA, an unbiased sampling scheme designed to alleviate these issues.
2790, Probabilistic Weight Fixing: Large-scale Training of Neural Network Weight Uncertainties for Quantisation
Chris Subia-Waud; Srinandan Dasmahapatra;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a probabilistic framework based on Bayesian neural networks (BNNs) and a variational relaxation to identify which weights can be moved to which cluster centre and to what degree based on their individual position-specific learned uncertainty distributions.
2791, TempME: Towards The Explainability of Temporal Graph Neural Networks Via Motif Discovery
Jialin Chen; Rex Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is a critical challenge for advancing the explainability and trustworthiness of current TGNNs. To address this challenge, we propose a novel approach, called Temporal Motifs Explainer (TempME), which uncovers the most pivotal temporal motifs guiding the prediction of TGNNs.
2792, Learning World Models with Identifiable Factorization
Yuren Liu; Biwei Huang; Zhengmao Zhu; Honglong Tian; Mingming Gong; Yang Yu; Kun Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose IFactor, a general framework to model four distinct categories of latent state variables that capture various aspects of information within the RL system, based on their interactions with actions and rewards.
2793, Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
Jiaqi Liu; Jian Lou; Kui Ren; Zhan Qin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of $(\epsilon,\delta)$-certified machine unlearning for the minimax model.
2794, DDF-HO: Hand-Held Object Reconstruction Via Conditional Directed Distance Field
Chenyangguang Zhang; Yan Di; Ruida Zhang; Guangyao Zhai; Fabian Manhardt; Federico Tombari; Xiangyang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Existing works utilizing Signed Distance Fields (SDF) reveal limitations in comprehensively capturing the complex hand-object interactions, since SDF is only reliable within the proximity of the target, and hence, infeasible to simultaneously encode local hand and object cues. To address this issue, we propose DDF-HO, a novel approach leveraging Directed Distance Field (DDF) as the shape representation.
2795, Causal Fairness for Outcome Control
Drago Plecko; Elias Bareinboim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study a specific decision-making task called outcome control in which an automated system aims to optimize an outcome variable $Y$ while being fair and equitable.
2796, Revisit The Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale
Zhiwei Hao; Jianyuan Guo; Kai Han; Han Hu; Chang Xu; Yunhe Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we identify the \emph{small data pitfall} that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K.
2797, A Competitive Algorithm for Agnostic Active Learning
Yihan Zhou; Eric Price;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We take a different approach to agnostic active learning, getting an algorithm that is \emph{competitive} with the optimal algorithm for any binary hypothesis class $H$ and distribution $\mathcal{D}_X$ over $X$.
2798, No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling
Eric Neyman; Tim Roughgarden;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Imposing this constraint creates a (to our knowledge) novel semi-adversarial setting in which the adversary retains a large amount of flexibility. In this setting, we present an algorithm based on online mirror descent that learns expert weights in a way that attains $O(\sqrt{T} \log T)$ expected regret as compared with the best weights in hindsight.
2799, Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning
Jianzhun Shao; Yun Qu; Chen Chen; Hongchang Zhang; Xiangyang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Offline multi-agent reinforcement learning is challenging due to the coupling effect of both distribution shift issue common in offline setting and the high dimension issue common in multi-agent setting, making the action out-of-distribution (OOD) and value overestimation phenomenon excessively severe. To mitigate this problem, we propose a novel multi-agent offline RL algorithm, named CounterFactual Conservative Q-Learning (CFCQL) to conduct conservative value estimation.
2800, Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs
Kevin Course; Prasanth Nair;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of inferring latent stochastic differential equations (SDEs) with a time and memory cost that scales independently with the amount of data, the total length of the time series, and the stiffness of the approximate differential equations.
2801, Module-wise Training of Neural Networks Via The Minimizing Movement Scheme
Skander Karkar; Ibrahim Ayed; Emmanuel de Bézenac; Patrick Gallinari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, it suffers from a stagnation problem, whereby early layers overfit and deeper layers stop increasing the test accuracy after a certain depth. We propose to solve this issue by introducing a simple module-wise regularization inspired by the minimizing movement scheme for gradient flows in distribution space.
2802, A Cross-Moment Approach for Causal Effect Estimation
Yaroslav Kivva; Saber Salehkaleybar; Negar Kiyavash;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a method to estimate the causal effect using cross moments between the treatment, the outcome, and the proxy variable.
2803, The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution By LLMs
Laura Ruis; Akbir Khan; Stella Biderman; Sara Hooker; Tim Rocktäschel; Edward Grefenstette;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present our findings as the starting point for further research into evaluating how LLMs interpret language in context and to drive the development of more pragmatic and useful models of human discourse.
2804, Self-Adaptive Motion Tracking Against On-body Displacement of Flexible Sensors
Chengxu Zuo; Fang Jiawei; Shihui Guo; Yipeng Qin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This displacement issue causes complicated patterns and significant challenges to subsequent machine learning algorithms. Our work proposes a novel self-adaptive motion tracking network to address this challenge.
2805, Characteristic Circuit
Zhongjie Yu; Martin Trapp; Kristian Kersting;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce characteristic circuits (CCs), a family of tractable probabilistic models providing a unified formalization of distributions over heterogeneous data in the spectral domain.
2806, Evaluating The Robustness of Interpretability Methods Through Explanation Invariance and Equivariance
Jonathan Crabbé; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we consider neural networks whose predictions are invariant under a specific symmetry group.
2807, Uni3DETR: Unified 3D Detection Transformer
Zhenyu Wang; Ya-Li Li; Xi Chen; Hengshuang Zhao; Shengjin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Uni3DETR, a unified 3D detector that addresses indoor and outdoor 3D detection within the same framework.
2808, Variational Inference with Gaussian Score Matching
Chirag Modi; Robert Gower; Charles Margossian; Yuling Yao; David Blei; Lawrence Saul;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, wepresent a new approach to VI.
2809, Debias Coarsely, Sample Conditionally: Statistical Downscaling Through Optimal Transport and Probabilistic Diffusion Models
Zhong Yi Wan; Ricardo Baptista; Anudhyan Boral; Yi-Fan Chen; John Anderson; Fei Sha; Leonardo Zepeda-Nunez;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a two-stage probabilistic framework for statistical downscaling between unpaired data.
2810, Global Optimality in Bivariate Gradient-based DAG Learning
Chang Deng; Kevin Bello; Pradeep Ravikumar; Bryon Aragam;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we prove that a simple path-following optimization scheme globally converges to the global minimum of the population loss in the bivariate setting.
2811, PAC Learning Linear Thresholds from Label Proportions
Anand Brahmbhatt; Rishi Saket; Aravindan Raghuveer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we show that it is indeed possible to efficiently learn LTFs using LTFs when given access to random bags of some label proportion in which feature-vectors are, conditioned on their labels, independently sampled from a Gaussian distribution $N(µ, Σ)$.
2812, Robustified ANNs Reveal Wormholes Between Human Category Percepts
Guy Gaziv; Michael Lee; James J DiCarlo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Because human category reports (aka human percepts) are thought to be insensitive to those same small-norm perturbations -- and locally stable in general -- this argues that ANNs are incomplete scientific models of human visual perception. Consistent with this, we show that when small-norm image perturbations are generated by standard ANN models, human object category percepts are indeed highly stable.
2813, Diffusion Model for Graph Inverse Problems: Towards Effective Source Localization on Complex Networks
Xin Yan; Qiang He; Hui Fang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Besides, while comprehending how information diffuses through a graph is crucial, there is a scarcity of research on reconstructing the paths of information propagation. To tackle these challenges, we propose a probabilistic model called DDMSL (Discrete Diffusion Model for Source Localization).
2814, Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization
Jinbiao Chen; Zizhen Zhang; Te Ye; Zhiguang Cao; Siyuan Chen; Jiahai Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: For the fine-tuning process, an efficient hierarchical method is proposed to systematically tackle all the subproblems.
2815, Language Models Are Weak Learners
Hariharan Manikandan; Yiding Jiang; J. Zico Kolter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we illustrate that prompt-based large language models can operate effectively as said weak learners.
2816, GeoPhy: Differentiable Phylogenetic Inference Via Geometric Gradients of Tree Topologies
Takahiro Mimori; Michiaki Hamada;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we propose a novel fully differentiable formulation of phylogenetic inference by representing topological distributions in continuous geometric spaces.
2817, Quantifying The Cost of Learning in Queueing Systems
Daniel Freund; Thodoris Lykouris; Wentao Weng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we argue that an asymptotic metric, which focuses on late-stage performance, is insufficient to capture the intrinsic statistical complexity of learning in queueing systems which typically occurs in the early stage.
2818, Towards A Fuller Understanding of Neurons with Clustered Compositional Explanations
Biagio La Rosa; Leilani Gilpin; Roberto Capobianco;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a generalization, called Clustered Compositional Explanations, that combines Compositional Explanations with clustering and a novel search heuristic to approximate a broader spectrum of the neuron behavior.
2819, Recovering Simultaneously Structured Data Via Non-Convex Iteratively Reweighted Least Squares
Christian Kümmerle; Johannes Maly;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new algorithm for the problem of recovering data that adheres to multiple, heterogenous low-dimensional structures from linear observations.
2820, Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields
Seungtae Nam; Daniel Rho; Jong Hwan Ko; Eunbyung Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present mip-Grid, a novel approach that integrates anti-aliasing techniques into grid-based representations for radiance fields, mitigating the aliasing artifacts while enjoying fast training time.
2821, Passive Learning of Active Causal Strategies in Agents and Language Models
Andrew Lampinen; Stephanie Chan; Ishita Dasgupta; Andrew Nam; Jane Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We formally illustrate that learning a strategy of first experimenting, then seeking goals, can allow generalization from passive learning in principle.
2822, Uncovering and Quantifying Social Biases in Code Generation
Yan Liu; Xiaokang Chen; Yan Gao; Zhe Su; Fengji Zhang; Daoguang Zan; Jian-Guang Lou; Pin-Yu Chen; Tsung-Yi Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we explore the social bias problem in pre-trained code generation models.
2823, Outlier-Robust Gromov Wasserstein for Graph Data
Lemin Kong; Jiajin Li; Jianheng Tang; Anthony Man-Cho So;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the GW distance is known to be highly sensitive to outliers, which can result in large inaccuracies if the outliers are given the same weight as other samples in the objective function. To mitigate this issue, we introduce a new and robust version of the GW distance called RGW.
2824, Retaining Beneficial Information from Detrimental Data for Neural Network Repair
Long-Kai Huang; Peilin Zhao; Junzhou Huang; Sinno Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Simply erasing the information of the identified data from the model can have a negative impact on its performance, especially when accurate data is mistakenly identified as detrimental and removed. To overcome this challenge, we propose a novel approach that leverages the knowledge obtained from a retained clean set.
2825, Flow: Per-instance Personalized Federated Learning
Kunjal Panchal; Sunav Choudhary; Nisarg Parikh; Lijun Zhang; Hui Guan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these personalized models may achieve lower accuracy than the global model on some clients, resulting in limited performance improvement compared to that of without personalization. To overcome this limitation, we propose a novel per-instance personalization FL algorithm, Flow.
2826, An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits
Kiarash Banihashem; MohammadTaghi Hajiaghayi; Suho Shin; Max Springer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present an oracle-efficient relaxation for for the adversarial contextual bandits problem, where the contexts are sequentially drawn i.i.d from a known distribution and the cost sequence is chosen by an online adversary.
2827, Unsupervised Behavior Extraction Via Random Intent Priors
Hao Hu; Jianing Ye; Yiqin Yang; Ziqing Mai; Chongjie Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose UBER, an unsupervised approach to deep reinforcement learning (RL) that leverages random intent priors to extract useful behaviors from offline reward-free datasets.
2828, HiBug: On Human-Interpretable Model Debug
Muxi Chen; YU LI; Qiang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose HiBug, an automated framework for interpretable model debugging.
2829, Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
TaeHo Yoon; Kibeom Myoung; Keon Lee; Jaewoong Cho; Albert No; Ernest Ryu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present censored generation with a pre-trained diffusion model using a reward model trained on minimal human feedback.
2830, Online Pricing for Multi-User Multi-Item Markets
Yigit Efe Erginbas; Soham Phade; Thomas Courtade; Kannan Ramchandran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This presents a complex problem, as the provider must intelligently offer the items to those users who value them the most without exceeding their highest acceptable prices. In this study, we tackle this challenge by designing online algorithms that can efficiently offer and price items while learning user valuations from accept/reject feedback.
2831, Multi-Modal Inverse Constrained Reinforcement Learning from A Mixture of Demonstrations
Guanren Qiao; Guiliang Liu; Pascal Poupart; Zhiqiang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, in practice, demonstrations often comprise a mixture of trajectories collected from various expert agents respecting different constraints, making it challenging to explain expert behaviors with a unified constraint function. To tackle this issue, we propose a Multi-Modal Inverse Constrained Reinforcement Learning (MMICRL) algorithm for simultaneously estimating multiple constraints corresponding to different types of experts.
2832, Train 'n Trade: Foundations of Parameter Markets
Tzu-Heng Huang; Harit Vishwakarma; Frederic Sala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While recent advances in aligning and interpolating models suggest that doing so may be possible, a number of fundamental questions must be answered to create viable parameter markets. In this work, we address these basic questions, propose a framework containing the infrastructure necessary for market operations to take place, study strategies for exchanging parameters, and offer means for agents to monetize parameters.
2833, Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness
Chung-En Tsai; Ying-Ting Lin; Yen-Huan Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work introduces the first small-loss and gradual-variation regret bounds for online portfolio selection, marking the first instances of data-dependent bounds for online convex optimization with non-Lipschitz, non-smooth losses.
2834, Make The U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation
Zhongqi Yue; QIANRU SUN; Hanwang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose to make the U in UDA matter by giving equal status to the two domains.
2835, Recovering from Out-of-sample States Via Inverse Dynamics in Offline Reinforcement Learning
Ke Jiang; Jia-Yu Yao; Xiaoyang Tan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we deal with the state distributional shift problem commonly encountered in offline reinforcement learning during test, where the agent tends to take unreliable actions at out-of-sample (unseen) states.
2836, What Makes Data Suitable for A Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement
Yotam Alexander; Nimrod De La Vega; Noam Razin; Nadav Cohen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The question of what makes a data distribution suitable for deep learning is a fundamental open problem. Focusing on locally connected neural networks (a prevalent family of architectures that includes convolutional and recurrent neural networks as well as local self-attention models), we address this problem by adopting theoretical tools from quantum physics.
2837, Validated Image Caption Rating Dataset
Lothar D Narins; Andrew Scott; Aakash Gautam; Anagha Kulkarni; Mar Castanon; Benjamin Kao; Shasta Ihorn; Yue-Ting Siu; James M. Mason; Alexander Blum; Ilmi Yoon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new high-quality validated image caption rating (VICR) dataset.
2838, Data-Driven Network Neuroscience: On Data Collection and Benchmark
David Huang; Sophi Shilpa Gururajapathy; Yunhan Yang; Jiaxing Xu; Yiping Ke; Miao Qiao; Alan Wang; Haribalan Kumar; Josh McGeown; Eryn Kwon;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents a comprehensive and quality collection of functional human brain network data for potential research in the intersection of neuroscience, machine learning, and graph analytics.
2839, Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data
Wai Tong Chung; Bassem Akoush; Pushan Sharma; Alex Tamkin; Ki Sung Jung; Jacqueline Chen; Jack Guo; Davy Brouzet; Mohsen Talei; Bruno Savard; Alexei Poludnenko; Matthias Ihme;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we present BLASTNet 2.0, a 2.2~TB network-of-datasets containing 744 full-domain samples from 34 high-fidelity direct numerical simulations, which addresses the current limited availability of 3D high-fidelity reacting and non-reacting compressible turbulent flow simulation data.
2840, Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation
Wei Jin; Haitao Mao; Zheng Li; Haoming Jiang; Chen Luo; Hongzhi Wen; Haoyu Han; Hanqing Lu; Zhengyang Wang; Ruirui Li; Zhen Li; Monica Cheng; Rahul Goutam; Haiyang Zhang; Karthik Subbian; Suhang Wang; Yizhou Sun; Jiliang Tang; Bing Yin; Xianfeng Tang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation. With the above tasks, we benchmark a range of algorithms on our proposed dataset, drawing new insights for further research and practice.
2841, M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark
Yongxin Shi; Chongyu Liu; Dezhi Peng; Cheng Jian; Jiarong Huang; Lianwen Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is primarily due to the lack of consideration for these issues in the current benchmarks, which hinders the development and evaluation of historical document analysis and recognition (HDAR) methods in complex real-world scenarios. To address this gap, this paper introduces a complex multi-style Chinese historical document analysis benchmark, named M5HisDoc.
2842, Synthcity: A Benchmark Framework for Diverse Use Cases of Tabular Synthetic Data
Zhaozhi Qian; Rob Davis; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we develop Synthcity, an open-source Python library that allows researchers and practitioners to perform one-click benchmarking of synthetic data generators across data modalities and use cases.
2843, UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction
Yansong Ning; Hao Liu; Hao Wang; Zhenyu Zeng; Hui Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents UUKG, the unified urban knowledge graph dataset for knowledge-enhanced urban spatiotemporal predictions.
2844, NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding
Ming Hu; Lin Wang; Siyuan Yan; Don Ma; Qingli Ren; Peng Xia; Wei Feng; Peibo Duan; Lie Ju; Zongyuan Ge;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The existing video datasets pose several limitations: 1) these datasets are small-scale in size to support comprehensive investigations of nursing activity; 2) they primarily focus on single procedures, lacking expert-level annotations for various nursing procedures and action steps; and 3) they lack temporally localized annotations, which prevents the effective localization of targeted actions within longer video sequences. To mitigate these limitations, we propose NurViD, a large video dataset with expert-level annotation for nursing procedure activity understanding.
2845, NeuroEvoBench: Benchmarking Neuroevolution for Large-Scale Machine Learning Applications
Robert Lange; Yujin Tang; Yingtao Tian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Along the way, we investigate core scientific questions including resource allocation, fitness shaping, normalization techniques, regularization, and scalability of EO.
2846, OceanBench: The Sea Surface Height Edition
J. Emmanuel Johnson; Quentin Febvre; Anastasiia Gorbunova; Sam Metref; Maxime Ballarotta; Julien Le Sommer; ronan fablet;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we demonstrate the OceanBench framework through a first edition dedicated to SSH interpolation challenges.
2847, RD-Suite: A Benchmark for Ranking Distillation
Zhen Qin; Rolf Jagerman; Rama Kumar Pasumarthi; Honglei Zhuang; He Zhang; Aijun Bai; Kai Hui; Le Yan; Xuanhui Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To that end, we propose a systematic and unified benchmark, Ranking Distillation Suite (RD-Suite), which is a suite of tasks with 4 large real-world datasets, encompassing two major modalities (textual and numeric) and two applications (standard distillation and distillation transfer).
2848, COOM: A Game Benchmark for Continual Reinforcement Learning
Tristan Tomilin; Meng Fang; Yudi Zhang; Mykola Pechenizkiy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we present COOM (\textbf{C}ontinual D\textbf{OOM}), a continual learning benchmark for embodied pixel-based RL.
2849, Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization
Kamil Dreczkowski; Antoine Grosnit; Haitham Bou Ammar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces a modular framework for Mixed-variable and Combinatorial Bayesian Optimization (MCBO) to address the lack of systematic benchmarking and standardized evaluation in the field.
2850, A Large Scale Annotated Dataset of Ventricular Tachycardia Alarms from ICU Monitors
Li-wei Lehman; Benjamin Moody; Harsh Deep; Hasan Saeed; Lucas McCullum; Feng Wu; Diane Perry; Tristan Struja; Qiao Li; Gari Clifford; Roger Mark;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new de-identified federated VT database consisting of a total of 10,939 labelling decisions from six human experts in reviewing over 5,000 waveform recordings with VT alarms automatically generated by bedside monitors in the intensive care units (ICUs).
2851, Temporal Graph Benchmark for Machine Learning on Temporal Graphs
Shenyang Huang; Farimah Poursafaei; Jacob Danovitch; Matthias Fey; Weihua Hu; Emanuele Rossi; Jure Leskovec; Michael Bronstein; Guillaume Rabusseau; Reihaneh Rabbany;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs.
2852, RPPG-Toolbox: Deep Remote PPG Toolbox
Xin Liu; Girish Narayanswamy; Akshay Paruchuri; Xiaoyu Zhang; Jiankai Tang; Yuzhe Zhang; Soumyadip Sengupta; Shwetak Patel; Yuntao Wang; Daniel McDuff;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a comprehensive toolbox, rPPG-Toolbox, unsupervised and supervised rPPG models with support for public benchmark datasets, data augmentation and systematic evaluation: https://github.com/ubicomplab/rPPG-Toolbox.
2853, IMP-MARL: A Suite of Environments for Large-scale Infrastructure Management Planning Via MARL
Pascal Leroy; Pablo G. Morato; Jonathan Pisane; Athanasios Kolios; Damien Ernst;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform for benchmarking the scalability of cooperative MARL methods in real-world engineering applications.
2854, ChessGPT: Bridging Policy Learning and Language Modeling
Xidong Feng; Yicheng Luo; Ziyan Wang; Hongrui Tang; Mengyue Yang; Kun Shao; David Mguni; Yali Du; Jun Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we argue that a powerful autonomous agent should cover both sources.
2855, Renku: A Platform for Sustainable Data Science
Rok Roškar; Chandrasekhar Ramakrishnan; Michele Volpi; Fernando Perez-Cruz; Lilian Gasser; Firat Ozdemir; Patrick Paitz; Mohammad Alisafaee; Philipp Fischer; Ralf Grubenmann; Eliza Harris; Tasko Olevski; Carl Remlinger; Luis Salamanca; Elisabet Capon Garcia; Lorenzo Cavazzi; Jakub Chrobasik; Darlin Cordoba Osnas; Alessandro Degano; Jimena Dupre; Wesley Johnson; Eike Kettner; Laura Kinkead; Sean Murphy; Flora Thiebaut; Olivier Verscheure; Dario Wirtz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We argue that making dataset preparation more accessible and dataset usage easier to record and document would have significant benefits for the ML community: it would allow for greater diversity in datasets by inviting modification to published sources, simplify use of alternative datasets and, in doing so, make results more transparent and robust, while allowing for all contributions to be adequately credited. We present a platform, Renku, designed to support and encourage such sustainable development and use of data, datasets, and code, and we demonstrate its benefits through a few illustrative projects which span the spectrum from dataset creation to dataset consumption and showcasing.
2856, SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking
Soukayna Mouatadid; Paulo Orenstein; Genevieve Flaspohler; Miruna Oprescu; Judah Cohen; Franklyn Wang; Sean Knight; Maria Geogdzhayeva; Sam Levang; Ernest Fraenkel; Lester Mackey;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Recently, machine learning methods have shown promise in advancing the state of the art but only at the cost of complex data curation, integrating expert knowledge with aggregation across multiple relevant data sources, file formats, and temporal and spatial resolutions. To streamline this process and accelerate future development, we introduce SubseasonalClimateUSA, a curated dataset for training and benchmarking subseasonal forecasting models in the United States.
2857, ToolQA: A Dataset for LLM Question Answering with External Tools
Yuchen Zhuang; Yue Yu; Kuan Wang; Haotian Sun; Chao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, current evaluation methods do not distinguish between questions that can be answered using LLMs' internal knowledge and those that require external information through tool use. To address this issue, we introduce a new dataset called ToolQA, which is designed to faithfully evaluate LLMs' ability to use external tools for question answering.
2858, DynaDojo: An Extensible Platform for Benchmarking Sample Efficiency in Dynamical System Identification
Logan Bhamidipaty; Tommy Bruzzese; Rami Ratl Mrad; Caryn Tran; Maxinder S. Kanwal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In response, we present DynaDojo, a novel machine-learning benchmark platform specifically designed for dynamical system identification.
2859, SoundCam: A Dataset for Tasks in Tracking and Identifying Humans from Real Room Acoustics
Mason Wang; Samuel Clarke; Jui-Hsien Wang; Ruohan Gao; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present SoundCam, the largest dataset of unique RIRs from in-the-wild rooms released to date publicly.
2860, LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
Yazhe Niu; YUAN PU; Zhenjie Yang; Xueyan Li; Tong Zhou; Jiyuan Ren; Shuai Hu; Hongsheng Li; Yu Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce LightZero, the first unified benchmark for deploying MCTS/MuZero in general sequential decision scenarios.
2861, Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML Based Modeling
Sachin Chauhan; Zeel Bharatkumar Patel; Sayan Ranu; Rijurekha Sen; Nipun Batra;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To complement the existing sparse static sensor network, we propose a mobile sensor network utilizing lower-cost PM2.5 sensors mounted on public buses in the Delhi-NCR region of India. Through this exercise, we introduce a novel dataset comprising PM2.5 and PM10 measurements.
2862, SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics
Atul Kumar Sinha; Daniele Paliotta; Bálint Máté; John Raine; Tobias Golling; François Fleuret;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Our contribution is \textsc{SUPA}, the SUrrogate PArticle propagation simulator, an algorithm and software package for generating data by simulating simplified particle propagation, scattering and shower development in matter.
2863, Hokoff: Real Game Dataset from Honor of Kings and Its Offline Reinforcement Learning Benchmarks
Yun Qu; Boyuan Wang; Jianzhun Shao; Yuhang Jiang; Chen Chen; Zhenbin Ye; Liu Linc; Yang Feng; Lin Lai; Hongyang Qin; Minwen Deng; Juchao Zhuo; Deheng Ye; Qiang Fu; YANG GUANG; Wei Yang; Lanxiao Huang; Xiangyang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing datasets often fall short in their simplicity and lack of realism. To address this gap, we propose Hokoff, a comprehensive set of pre-collected datasets that covers both offline RL and offline MARL, accompanied by a robust framework, to facilitate further research.
2864, RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation
MD WAHIDUZZAMAN KHAN; Hongwei Sheng; Hu Zhang; Heming Du; Sen Wang; Minas Coroneo; Farshid Hajati; Sahar Shariflou; Michael Kalloniatis; Jack Phu; Ashish Agar; Zi Huang; S.Mojtaba Golzan; Xin Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The static images naturally lose the dynamic characteristics of retina fluctuation, resulting in diminished dataset richness, and the usage of bench-top devices further restricts dataset scalability due to its limited accessibility. Considering these limitations, we introduce the first video-based retinal dataset by employing handheld devices for data acquisition.
2865, Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design
AkshatKumar Nigam; Robert Pollice; Gary Tom; Kjell Jorner; John Willes; Luca Thiede; Anshul Kundaje; Alan Aspuru-Guzik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we develop a set of practical benchmark tasks relying on physical simulation of molecular systems mimicking real-life molecular design problems for materials, drugs, and chemical reactions.
2866, SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots
Jong Wook Bae; Jungho Kim; Junyong Yun; Changwon Kang; Jeongseon Choi; Chanhyeok Kim; Junho Lee; Jungwook Choi; Jun Won Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel dataset of pedestrian trajectories, referred to as Social Interactive Trajectory (SiT) dataset, which can be used to train pedestrian detection, tracking, and trajectory prediction models needed to design social navigation robots.
2867, LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Kaiyu Yang; Aidan Swope; Alex Gu; Rahul Chalamala; Peiyang Song; Shixing Yu; Saad Godil; Ryan J Prenger; Animashree Anandkumar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, existing methods are difficult to reproduce or build on, due to private code, data, and large compute requirements. This has created substantial barriers to research on machine learning methods for theorem proving. This paper removes these barriers by introducing LeanDojo: an open-source Lean playground consisting of toolkits, data, models, and benchmarks.
2868, Auslan-Daily: Australian Sign Language Translation for Daily Communication and News
Xin Shen; Shaozu Yuan; Hongwei Sheng; Heming Du; Xin Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Auslan, as a sign language specific to Australia, still lacks a dedicated large-scale dataset for SLT. To fill this gap, we curate an Australian Sign Language translation dataset, dubbed Auslan-Daily, which is collected from the Auslan educational TV series and Auslan TV programs.
2869, AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from The Web
Michael Schlichtkrull; Zhijiang Guo; Andreas Vlachos;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper we introduce AVeriTeC, a new dataset of 4,568 real-world claims covering fact-checks by 50 different organizations.
2870, TWIGMA: A Dataset of AI-Generated Images with Metadata From Twitter
Yiqun Chen; James Zou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce TWIGMA (TWItter Generative-ai images with MetadatA), a comprehensive dataset encompassing over 800,000 gen-AI images collected from Jan 2021 to March 2023 on Twitter, with associated metadata (e.g., tweet text, creation date, number of likes).
2871, SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark
Zeyu Zhang; Robert Pless; Nadia Shakoor; Austin Carnahan; Abby Stylianou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Computational approaches to measuring the phenotype (the observable plant features) are required to address the problem at a large scale, but machine learning approaches to extract phenotypes from sensor data have been hampered by limited access to (a) sufficiently large, organized multi-sensor datasets, (b) field trials that have a large scale and significant number of genotypes, (c) full genetic sequencing of those phenotypes, and (d) datasets sufficiently organized so that algorithm centered researchers can directly address the real biological problems. To address this, we present SGxP, a novel benchmark dataset from a large-scale field trial consisting of the complete genotype of over 300 sorghum varieties, and time sequences of imagery from several field plots growing each variety, taken with RGB and laser 3D scanner imaging.
2872, AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator
Elysia Smyers; Sydney Katz; Anthony Corso; Mykel J Kochenderfer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce AVOIDDS, a realistic object detection benchmark for the vision-based aircraft detect-and-avoid problem.
2873, Hypotheses Paradise: An Open and Strong Baseline for Speech Recognition with Large Language Models
CHEN CHEN; Yuchen Hu; Chao-Han Huck Yang; Sabato Marco Siniscalchi; Pin-Yu Chen; Eng-Siong Chng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditory system. Inspired by this observation, we introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction, where N-best decoding hypotheses provide informative elements for true transcription prediction.
2874, BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting
Patrick Emami; Abhijeet Sahu; Peter Graf;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This has hindered exploring the pretrain-then-finetune paradigm for STLF. To help address this, we present BuildingsBench, which consists of 1) Buildings-900K, a large-scale dataset of 900K simulated buildings representing the U.S. building stock, and 2) an evaluation platform with over 1,900 real residential and commercial buildings from 7 open datasets.
2875, How to Data in Datathons
Carlos Mougan; Richard Plant; Clare Teng; Marya Bazzi; Alvaro Cabrejas Egea; Ryan Chan; David Salvador Jasin; Martin Stoffel; Kirstie Whitaker; JULES MANSER;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Drawing on our own experiences and insights from organizing $\geq80$ datathon challenges with $\geq60$ partnership organizations since 2016, we provide a guide that serves as a resource for organizers to navigate the data-related complexities of datathons.
2876, A Dataset of Relighted 3D Interacting Hands
Gyeongsik Moon; Shunsuke Saito; Weipeng Xu; Rohan Joshi; Julia Buffalini; Harley Bellan; Nicholas Rosen; Jesse Richardson; Mallorie Mize; Philippe De Bree; Tomas Simon; Bo Peng; Shubham Garg; Kevyn McPhail; Takaaki Shiratori;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose Re:InterHand, a dataset of relighted 3D interacting hands that achieve the two goals.
2877, LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering
Jingying Gao; Qi Wu; Alan Blair; Maurice Pagnucco;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: VQA tasks and large vision-and-language models aim to tackle reasoning problems, but the accuracy, consistency and fabrication of the generated answers is hard to evaluate in the absence of a VQA dataset that can offer formal, comprehensive and systematic complex logical reasoning questions. To address this gap, we present LoRA, a novel Logical Reasoning Augmented VQA dataset that requires formal and complex description logic reasoning based on a food-and-kitchen knowledge base.
2878, Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Predictive Models in Emergency Medicine
Aman Kansal; Emma Chen; Julie Chen; Boyang Tom Jin; Julia Reisler; David Kim; Pranav Rajpurkar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the Multimodal Clinical Benchmark for Emergency Care (MC-BEC), a comprehensive benchmark for evaluating foundation models in Emergency Medicine using a dataset of 121,978 continuously monitored Emergency Department visits from 2020-2022.
2879, MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
Kai Zhang; Lingbo Mo; wenhu chen; Huan Sun; Yu Su;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Thus, they still require lots of manual tuning to produce desirable outcomes in practice. To address this issue, we introduce MagicBrush, the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing.
2880, The ToMCAT Dataset
Adarsh Pyarelal; Eric Duong; Caleb Shibu; Paulo Soares; Savannah Boyd; Payal Khosla; Valeria A. Pfeifer; Diheng Zhang; Eric Andrews; Rick Champlin; Vincent Raymond; Meghavarshini Krishnaswamy; Clayton Morrison; Emily Butler; Kobus Barnard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a rich, multimodal dataset consisting of data from 40 teams of three humans conducting simulated urban search-and-rescue (SAR) missions in a Minecraft-based testbed, collected for the Theory of Mind-based Cognitive Architecture for Teams (ToMCAT) project.
2881, Uncovering Neural Scaling Law in Molecular Representation Learning
Dingshuo Chen; Yanqiao Zhu; Jieyu Zhang; Yuanqi Du; Zhixun Li; Qiang Liu; Shu Wu; Liang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the widespread interests in advancing model-centric techniques, how the quantity and quality of molecular data affect the learned representation remains an open question in this field. In light of this, we investigate the neural scaling behaviors of MRL from a data-centric perspective across various dimensions, including (1) data modality, (2) data distribution, (3) pre-training intervention, and (4) model capacity.
2882, SEVA: Leveraging Sketches to Evaluate Alignment Between Human and Machine Visual Abstraction
Kushin Mukherjee; Holly Huey; Xuanchen Lu; Yael Vinker; Rio Aguina-Kang; Ariel Shamir; Judith Fan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we introduce SEVA, a new benchmark dataset containing 90K human-generated sketches of 128 object concepts produced under different time constraints, and thus systematically varying in sparsity.
2883, Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning
Jialong Wu; Haoyu Ma; Chaoyi Deng; Mingsheng Long;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of downstream visual control tasks.
2884, Label-efficient Segmentation Via Affinity Propagation
Wentong Li; Yuqian Yuan; Song Wang; Wenyu Liu; Dongqi Tang; Jian liu; Jianke Zhu; Lei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we formulate the affinity modeling task as an affinity propagation process, and consequently propose both local and global pairwise affinity terms to generate accurate soft pseudo labels.
2885, Tame A Wild Camera: In-the-Wild Monocular Camera Calibration
Shengjie Zhu; Abhinav Kumar; Masa Hu; Xiaoming Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Alternatively, we introduce a novel monocular 3D prior, the incidence field, defined as the incidence rays between points in 3D space and pixels in the 2D imaging plane.
2886, Embracing The Chaos: Analysis and Diagnosis of Numerical Instability in Variational Flows
Zuheng Xu; Trevor Campbell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the impact of numerical instability on the reliability of sampling, density evaluation, and evidence lower bound (ELBO) estimation in variational flows.
2887, Nearest Neighbour with Bandit Feedback
Stephen Pasteris; Chris Hicks; Vasilios Mavroudis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we adapt the nearest neighbour rule to the contextual bandit problem.
2888, Expanding Small-Scale Datasets with Guided Imagination
Yifan Zhang; Daquan Zhou; Bryan Hooi; Kai Wang; Jiashi Feng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we present a Guided Imagination Framework (GIF) that leverages cutting-edge generative models like DALL-E2 and Stable Diffusion (SD) to imagine'' and create informative new data from the input seed data.
2889, One-step Differentiation of Iterative Algorithms
Jerome Bolte; Edouard Pauwels; Samuel Vaiter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study one-step differentiation, also known as Jacobian-free backpropagation, a method as easy as automatic differentiation and as performant as implicit differentiation for fast algorithms (e.g. superlinear optimization methods).
2890, LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embedding
Ningyi Liao; Siqiang Luo; Xiang Li; Jieming Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the scalability issues of heterophilous GNN and propose a scalable model, LD2, which simplifies the learning process by decoupling graph propagation and generating expressive embeddings prior to training.
2891, The Target-Charging Technique for Privacy Accounting Across Interactive Computations
Edith Cohen; Xin Lyu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose the \emph{Target Charging Technique} (TCT), a unified privacy analysis framework for interactive settings where a sensitive dataset is accessed multiple times using differentially private algorithms.
2892, A Theory of Multimodal Learning
Zhou Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: An intriguing finding from the practice of multimodal learning is that a model trained on multiple modalities can outperform a finely-tuned unimodal model, even on unimodal tasks. This paper provides a theoretical framework that explains this phenomenon, by studying generalization properties of multimodal learning algorithms.
2893, Federated Learning with Manifold Regularization and Normalized Update Reaggregation
Xuming An; Li Shen; Han Hu; Yong Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose FedMRUR by adopting the manifold model fusion scheme and a new global optimizer to alleviate the negative impacts.
2894, MeGraph: Capturing Long-Range Interactions By Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy
Honghua Dong; Jiawei Xu; Yu Yang; Rui Zhao; Shiwen Wu; Chun Yuan; Xiu Li; Chris Maddison; Lei Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building a graph hierarchy via graph pooling methods is a promising approach to address this challenge; however, hierarchical information propagation cannot entirely take over the role of local information aggregation. To balance locality and hierarchy, we integrate the local and hierarchical structures, represented by intra- and inter-graphs respectively, of a multi-scale graph hierarchy into a single mega graph.
2895, Credit Assignment Through Disinhibitory Control of Hebbian Plasticity
Julian Rossbroich; Friedemann Zenke;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These purely functionally motivated models assume distinct neuronal compartments to represent local error signals that determine the sign of synaptic plasticity. However, this explicit error modulation is inconsistent with phenomenological plasticity models in which the sign depends primarily on postsynaptic activity. Here we resolve this discrepancy with a plausible microcircuit model and Hebbian learning rule derived within an adaptive control theory framework.
2896, A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
Ranran Shen; Pan Peng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We address the problem of designing a sublinear-time spectral clustering oracle for graphs that exhibit strong clusterability.
2897, Structure from Duplicates: Neural Inverse Graphics from A Single Image
Tianhang Cheng; Wei-Chiu Ma; Kaiyu Guan; Antonio Torralba; Shenlong Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These duplicates, when seen together, provide additional and strong cues for us to effectively reason about 3D. Inspired by this observation, we introduce Structure from Duplicates (SfD), a novel inverse graphics framework that reconstructs geometry, material, and illumination from a single image containing multiple identical objects.
2898, A Theory of Link Prediction Via Relational Weisfeiler-Leman
Xingyue Huang; Miguel Romero; Ismail Ceylan; Pablo Barceló;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The theoretical findings presented in this paper explain the benefits of some widely employed practical design choices, which are validated empirically.
2899, Physics Driven Correction for Inverse Estimation
ruiyuan kang; Tingting Mu; Panagiotis Liatsis; Dimitrios Kyritsis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work focuses on detecting and correcting failed state estimations before adopting them in SAE inverse problems, by utilizing simulations and performance metrics guided by physical laws. We suggest to flag a machine learning estimation when its physical model error exceeds a tolerance threshold, and propose a novel approach, GEESE, to correct it through optimization, aiming at delivering both low error and high efficiency.
2900, Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera
Lujie Xia; Ziluo Ding; Rui Zhao; Jiyuan Zhang; Lei Ma; Zhaofei Yu; Tiejun Huang; Ruiqin Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams.
2901, A Benchmark of Categorical Encoders for Binary Classification
Federico Matteucci; Vadim Arzamasov; Klemens Böhm;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The study shows the profound influence of dataset selection, experimental factors, and aggregation strategies on the benchmark's conclusions~---~aspects disregarded in previous encoder benchmarks.
2902, VisAlign: Dataset for Measuring The Degree of Alignment Between AI and Humans in Visual Perception
Jiyoung Lee; Seungho Kim; Seunghyun Won; Joonseok Lee; Marzyeh Ghassemi; James Thorne; Jaeseok Choi; O-Kil Kwon; Edward Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we focus on the models' visual perception alignment with humans, further referred to as AI-human visual alignment.
2903, Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Jing Lin; Ailing Zeng; Shunlin Lu; Yuanhao Cai; Ruimao Zhang; Haoqian Wang; Lei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Motion-X, a large-scale 3D expressive whole-body motion dataset.
2904, WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes
Satoshi Tsutsui; Winnie Pang; Bihan Wen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While multiple datasets containing WBC images have been proposed, they mostly focus on cell categorization, often lacking the necessary morphological details to explain such categorizations, despite the importance of explainable artificial intelligence (XAI) in medical domains. This paper seeks to address this limitation by introducing comprehensive annotations for WBC images.
2905, Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark
Xiao-Yang Liu; Zeliang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To avoid hasty advertisements of quantum supremacy by tech giants or quantum startups and eliminate the cost of dedicating a team to the classical simulation task, we advocate an open-source approach to maintain a trustable benchmark performance. In this paper, we take a reinforcement learning approach for the classical simulation of quantum circuits and demonstrate its great potential by reporting an estimated simulation time of less than 4 days, a speedup of 5.40x over the state-of-the-art method.
2906, SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery
Nina Montana-Brown; Shaheer U. Saeed; Ahmed Abdulaal; Thomas Dowrick; Yakup Kilic; Sophie Wilkinson; Meghavi Mashar; Chloe He; Alkisti Stavropoulou; Emma Thomson; Zachary MC Baum; Simone Foti; Brian Davidson; Yipeng Hu; Matthew Clarkson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce \texttt{SARAMIS}, the first large-scale dataset of anatomically derived 3D rendering assets of the human abdominal anatomy.
2907, WildfireSpreadTS: A Dataset of Multi-modal Time Series for Wildfire Spread Prediction
Sebastian Gerard; Yu Zhao; Josephine Sullivan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a multi-temporal, multi-modal remote-sensing dataset for predicting how active wildfires will spread at a resolution of 24 hours.
2908, Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition
Wei He; Kai Han; Ying Nie; Chengcheng Wang; Yunhe Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Currently, most invasive species datasets are limited in scale and cover a narrow range of species, which restricts the development of deep-learning based invasion biometrics systems. To fill the gap of this area, we introduced Species196, a large-scale semi-supervised dataset of 196-category invasive species.
2909, EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images
Seongsu Bae; Daeun Kyung; Jaehee Ryu; Eunbyeol Cho; Gyubok Lee; Sunjun Kweon; Jungwoo Oh; Lei Ji; Eric Chang; Tackeun Kim; Edward Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce EHRXQA, a novel multi-modal question answering dataset for structured EHRs and chest X-ray images.
2910, RaLEs: A Benchmark for Radiology Language Evaluations
Juan M Zambrano Chaves; Nandita Bhaskhar; Maayane Attias; Jean-Benoit Delbrouck; Daniel Rubin; Andreas Loening; Curtis Langlotz; Akshay Chaudhari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we characterize the radiology report as a distinct domain and introduce RaLEs, the Radiology Language Evaluations, as a benchmark for natural language understanding and generation in radiology.
2911, On The Need for A Language Describing Distribution Shifts: Illustrations on Tabular Datasets
Jiashuo Liu; Tianyu Wang; Peng Cui; Hongseok Namkoong;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To encourage researchers to develop a refined language for distribution shifts, we build an empirical testbed where we characterize the type of shift we benchmark performance over.
2912, CAPP-130 : A Dataset of Chinese Application Privacy Policy Summarization and Interpretations
Jinfei Liu; pengyun zhu; Long Wen; Feng Xue; Jian Lou; Zhibo Wang; Kui Ren;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, research on Chinese application privacy policy summarization is currently almost nonexistent, and there is a lack of a high-quality corpus suitable for addressing readability issues. To tackle these challenges, we introduce a fine-grained CAPP-130 corpus and a TCSI-pp framework.
2913, A Dataset for Analyzing Streaming Media Performance Over HTTP/3 Browsers
Sapna Chaudhary; Mukulika Maity; Sandip Chakraborty; Naval Shukla;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present an HTTP/3-supported browser dataset collection tool named H3B.
2914, Quilt-1M: One Million Image-Text Pairs for Histopathology
Wisdom Ikezogwo; Saygin Seyfioglu; Fatemeh Ghezloo; Dylan Geva; Fatwir Sheikh Mohammed; Pavan Kumar Anand; Ranjay Krishna; Linda Shapiro;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: From YouTube, we curate Quilt: a large-scale vision-language dataset consisting of $768,826$ image and text pairs.
2915, Benchmarking Encoder-Decoder Architectures for Biplanar X-ray to 3D Bone Shape Reconstruction
Mahesh Shakya; Bishesh Khanal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To move closer toward clinical translation, we propose a benchmarking framework that evaluates tasks relevant to real-world clinical scenarios, including reconstruction of fractured bones, bones with implants, robustness to population shift, and error in estimating clinical parameters.
2916, NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
Anwar Said; Roza Bayrak; Tyler Derr; Mudassir Shabbir; Daniel Moyer; Catie Chang; Xenofon Koutsoukos;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce NeuroGraph, a collection of graph-based neuroimaging datasets that span multiple categories of behavioral and cognitive traits.
2917, Degraded Polygons Raise Fundamental Questions of Neural Network Perception
Leonard Tang; Dan Ley;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: From adversarial attacks to image corruptions, state-of-the-art machine vision significantly suffers in a variety of settings that humansreadily handle. Motivated by these phenomena, in this work we introduce another,orthogonal perspective of the human-machine vision gap.
2918, The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes
David Recasens Lafuente; Martin R. Oswald; Marc Pollefeys; Javier Civera;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Deformable odometry and SLAM pipelines, which tackle the most challenging scenario of exploratory trajectories, suffer from a lack of robustness and proper quantitative evaluation methodologies. To tackle this issue with a common benchmark, we introduce the Drunkard's Dataset, a challenging collection of synthetic data targeting visual navigation and reconstruction in deformable environments.
2919, MLFMF: Data Sets for Machine Learning for Mathematical Formalization
Andrej Bauer; Matej Petković; Ljupco Todorovski;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce \emph{MLFMF}, a collection of data sets for benchmarking recommendation systems used to support formalization of mathematics with proof assistants.
2920, LithoBench: Benchmarking AI Computational Lithography for Semiconductor Manufacturing
Su Zheng; Haoyu Yang; Binwu Zhu; Bei Yu; Martin Wong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To boost the development of AI-driven computational lithography, we present the LithoBench dataset, a collection of circuit layout tiles for deep-learning-based lithography simulation and mask optimization.
2921, EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
Karttikeya Mangalam; Raiymbek Akshulakov; Jitendra Malik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems.
2922, NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation
Wei Zheng; Cheng Peng; Zeyuan Hou; Boyu Lyu; Mengfan Wang; Xuelong Mi; Shuoxuan Qiao; Yinan Wan; Guoqiang Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The existing nuclei segmentation benchmarks either worked on 2D only or annotated a small number of 3D cells, perhaps due to the high cost of 3D annotation for large-scale data. To fulfill the critical need, we constructed NIS3D, a 3D, high cell density, large-volume, and completely annotated Nuclei Image Segmentation benchmark, assisted by our newly designed semi-automatic annotation software. NIS3D provides more than 22,000 cells across multiple most-used species in this area.
2923, Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Viorica Patraucean; Lucas Smaira; Ankush Gupta; Adria Recasens; Larisa Markeeva; Dylan Banarse; Skanda Koppula; joseph heyward; Mateusz Malinowski; Yi Yang; Carl Doersch; Tatiana Matejovicova; Yury Sulsky; Antoine Miech; Alexandre Fréchette; Hanna Klimczak; Raphael Koster; Junlin Zhang; Stephanie Winkler; Yusuf Aytar; Simon Osindero; Dima Damen; Andrew Zisserman; Joao Carreira;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, BEiT-3, or GPT-4).
2924, Lo-Hi: Practical ML Drug Discovery Benchmark
Simon Steshin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: For the Hi task, we designed a novel molecular splitting algorithm that solves the Balanced Vertex Minimum $k$-Cut problem.
2925, GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image
Mingjian Zhu; Hanting Chen; Qiangyu YAN; Xudong Huang; Guanyu Lin; Wei Li; Zhijun Tu; Hailin Hu; Jie Hu; Yunhe Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce the GenImage dataset, which has the following advantages: 1) Plenty of Images, including over one million pairs of AI-generated fake images and collected real images.
2926, An NLP Benchmark Dataset for Assessing Corporate Climate Policy Engagement
Gaku Morio; Christopher D Manning;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a dataset to estimate corporate climate policy engagement from various PDF-formatted documents.
2927, MiliPoint: A Point Cloud Dataset for MmWave Radar
Han Cui; Shu Zhong; Jiacheng Wu; Zichao Shen; Naim Dahnoun; Yiren Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, as a Radio Frequency based technology, mmWave radars rely on capturing reflected signals from objects, making them more prone to noise compared to cameras. This raises an intriguing question for the deep learning community: Can we develop more effective point set-based deep learning methods for such attractive sensors?
2928, OV-PARTS: Towards Open-Vocabulary Part Segmentation
Meng Wei; Xiaoyu Yue; Wenwei Zhang; Shu Kong; Xihui Liu; Jiangmiao Pang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Furthermore, the large-scale vision and language models, which play a key role in the open vocabulary setting, struggle to recognize parts as effectively as objects. To comprehensively investigate and tackle these challenges, we propose an Open-Vocabulary Part Segmentation (OV-PARTS) benchmark.
2929, Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning
Joseph Suarez; David Bloomin; Kyoung Choe; Hao Xiang Li; Ryan Sullivan; Nishaanth Kanna; Daniel Scott; Rose Shuman; Herbie Bradley; Louis Castricato; Phillip Isola; Chenghui Yu; Yuhao Jiang; Qimai Li; Jiaxin Chen; Xiaolong Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Neural MMO 2.0 is a massively multi-agent and multi-task environment for reinforcement learning research.
2930, HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding
Hao Zheng; Regina Lee; Yuqian Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To enable technological breakthrough, we present HA-ViD – the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations.
2931, CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care
Tong Xiang; Liangzhi Li; Wangyue Li; Mingbai Bai; Lu Wei; Bowen Wang; Noa Garcia;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we present a benchmark, CARE-MI, for evaluating LLM misinformation in: 1) a sensitive topic, specifically the maternity and infant care domain; and 2) a language other than English, namely Chinese.
2932, D4: Improving LLM Pretraining Via Document De-Duplication and Diversification
Kushal Tirumala; Daniel Simig; Armen Aghajanyan; Ari Morcos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we show that careful data selection (on top of de-duplicated data) via pre-trained model embeddings can speed up training (20% efficiency gains) and improves average downstream accuracy on 16 NLP tasks (up to 2%) at the 6.7B model scale.
2933, What A MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation
Benedikt Blumenstiel; Johannes Jakubik; Hilde Kuehne; Michael Vössing;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we build a benchmark for Multi-domain Evaluation of Zero-Shot Semantic Segmentation (MESS), which allows a holistic analysis of performance across a wide range of domain-specific datasets such as medicine, engineering, earth monitoring, biology, and agriculture.
2934, Low-shot Object Learning with Mutual Exclusivity Bias
Anh Thai; Ahmad Humayun; Stefan Stojanov; Zixuan Huang; Bikram Boote; James Rehg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in infants during word learning.
2935, Digital Typhoon: Long-term Satellite Image Dataset for The Spatio-Temporal Modeling of Tropical Cyclones
Asanobu Kitamoto; Jared Hwang; Bastien Vuillod; Lucas Gautier;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents the official release of the Digital Typhoon dataset, the longest typhoon satellite image dataset for 40+ years aimed at benchmarking machine learning models for long-term spatio-temporal data.
2936, Generating QM1B with PySCF$_{\text{IPU}}$
Alexander Mathiasen; Hatem Helal; Kerstin Klaser; Paul Balanca; Josef Dean; Carlo Luschi; Dominique Beaini; Andrew Fitzgibbon; Dominic Masters;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take a first step towards utilising hardware accelerators by introducing the data generator PySCF$_{\text{IPU}}$ using Intelligence Processing Units (IPUs).
2937, EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis
Dragos Georgian Corlatescu; Alexandru Dinu; Mihaela Petruta Gaman; Paul Sumedrea;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose to address the deficiencies in the space of similarity research on binary files, starting from EMBER — one of the largest malware classification datasets.
2938, Understanding Social Reasoning in Language Models with Language Models
Kanishk Gandhi; Jan-Philipp Franken; Tobias Gerstenberg; Noah Goodman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This is primarily due to two distinct challenges: (1) the presence of inconsistent results from previous evaluations, and (2) concerns surrounding the validity of existing evaluation methodologies. To address these challenges, we present a novel framework for procedurally generating evaluations with LLMs by populating causal templates.
2939, LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite
Artur Toshev; Gianluca Galletti; Fabian Fritz; Stefan Adami; Nikolaus Adams;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present LagrangeBench, the first benchmarking suite for Lagrangian particle problems, focusing on temporal coarse-graining.
2940, Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark
Lukasz Augustyniak; Szymon Woźniak; Marcin Gruza; Piotr Gramacki; Krzysztof Rajda; Mikołaj Morzy; Tomasz Kajdanowicz;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work presents the most extensive open massively multilingual corpus of datasets for training sentiment models.
2941, A Comprehensive Benchmark for Neural Human Body Rendering
Kenkun Liu; Derong Jin; Ailing Zeng; Xiaoguang Han; Lei Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we design and execute thorough studies into unified evaluation settings and metrics to establish a fair and reasonable benchmark for human NeRF models.
2942, Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context
Julian Tanke; Oh-Hun Kwon; Felix B Mueller; Andreas Doering; Jürgen Gall;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These complex relations between scene geometry and persons ariseconstantly in our daily lives, and models that wish to accurately forecasthuman behavior will have to take them into consideration. To facilitate research in this direction, we propose Humans in Kitchens, alarge-scale multi-person human motion dataset with annotated 3D human poses, scene geometry and activities per person and frame.
2943, Into The LAION’s Den: Investigating Hate in Multimodal Datasets
Abeba Birhane; vinay prabhu; Vishnu Boddeti; Sanghyun Han; Sasha Alexandra Luccioni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate the effect of scaling datasets on hateful content through a comparative audit of two datasets: LAION-400M and LAION-2B.
2944, GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection
Namyong Park; Ryan Rossi; Xing Wang; Antoine Simoulin; Nesreen K. Ahmed; Christos Faloutsos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the recent attempt to tackle this important problem, there has been no comprehensive benchmark environment to evaluate the performance of GL model selection methods. To bridge this gap, we present GLEMOS in this work, a comprehensive benchmark for instantaneous GL model selection that makes the following contributions. (i) GLEMOS provides extensive benchmark data for fundamental GL tasks, i.e., link prediction and node classification, including the performances of 360 models on 460 graphs on these tasks.
2945, The Waymo Open Sim Agents Challenge
Nico Montali; John Lambert; Paul Mougin; Alex Kuefler; Nicholas Rhinehart; Michelle Li; Cole Gulino; Tristan Emrich; Zoey Yang; Shimon Whiteson; Brandyn White; Dragomir Anguelov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce the Waymo Open Sim Agents Challenge (WOSAC).
2946, Knowledge-based in Silico Models and Dataset for The Regulatory Evaluation of Mammography AI for A Range of Breast Characteristics, Lesion Conspicuities and Doses
Elena Sizikova; Niloufar Saharkhiz; Diksha Sharma; Miguel Lago; Berkman Sahiner; Jana Delfino; Aldo Badano;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an evaluation approach for testing medical imaging AI models that relies on in silico imaging pipelines in which stochastic digital models of human anatomy (in object space) with and without pathology are imaged using a digital replica imaging acquisition system to generate realistic synthetic image datasets.
2947, Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models
Shuo Chen; Jindong Gu; Zhen Han; Yunpu Ma; Philip Torr; Volker Tresp;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we assess the robustness of 11 widely-used adaptation methods across 4 vision-language datasets under multimodal corruptions.
2948, ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
Xiaoxuan Ma; Stephan Kaufhold; Jiajun Su; Wentao Zhu; Jack Terwilliger; Andres Meza; Yixin Zhu; Federico Rossano; Yizhou Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the lack of non-human primate behavior datasets limits the study of primate social dynamics and interactions, hindering research on our closest living relatives. To tackle these limitations, we offer ChimpACT, a comprehensive dataset for deciphering the longitudinal behavior and social relations of chimpanzees within a social group.
2949, Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework
Weiduo Liao; Ying Wei; Mingchen Jiang; Qingfu Zhang; Hisao Ishibuchi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current state-of-the-art benchmarks seldom evaluate the compositional generalization capability exactly, which leaves an unexplored but interesting question to answer. We propose two vision benchmarks, named Compositional GQA (CGQA) and Compositional OBJects365 (COBJ), and a new evaluation framework, named Compositional Few-Shot Testing (CFST), to evaluate this capability comprehensively on three aspects systematicity, productivity, and substitutivity.
2950, MARBLE: Music Audio Representation Benchmark for Universal Evaluation
Ruibin Yuan; Yinghao Ma; Yizhi Li; Ge Zhang; Xingran Chen; Hanzhi Yin; zhuo le; Yiqi Liu; Jiawen Huang; Zeyue Tian; Binyue Deng; Ningzhi Wang; Chenghua Lin; Emmanouil Benetos; Anton Ragni; Norbert Gyenge; Roger Dannenberg; wenhu chen; Gus Xia; Wei Xue; Si Liu; Shi Wang; Ruibo Liu; Yike Guo; Jie Fu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark. To address this issue, we in troduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE.
2951, ProteinShake: Building Datasets and Benchmarks for Deep Learning on Protein Structures
Tim Kucera; Carlos Oliver; Dexiong Chen; Karsten Borgwardt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present ProteinShake, a Python software package that simplifies dataset creation and model evaluation for deep learning on protein structures.
2952, Diverse Community Data for Benchmarking Data Privacy Algorithms
Aniruddha Sen; Christine Task; Dhruv Kapur; Gary Howarth; Karan Bhagat;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper summarizes four CRC contributions: theoretical work on the relationship between diverse populations and challenges for equitable deidentification; public benchmark data focused on diverse populations and challenging features; a comprehensive open source suite of evaluation metrology for deidentified datasets; and an archive of more than 450 deidentified data samples from a broad range of techniques.
2953, Breaking The Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy
Richeng Jin; Zhonggen Su; caijun zhong; Zhaoyang Zhang; Tony Quek; Huaiyu Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP).
2954, Structured State Space Models for In-Context Reinforcement Learning
Chris Lu; Yannick Schroecker; Albert Gu; Emilio Parisotto; Jakob Foerster; Satinder Singh; Feryal Behbahani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a modification to a variant of S4 that enables us to initialise and reset the hidden state in parallel, allowing us to tackle reinforcement learning tasks.
2955, Adaptive Selective Sampling for Online Prediction with Experts
Rui Castro; Fredrik Hellström; Tim van Erven;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider online prediction of a binary sequence with expert advice. For this setting, we devise label-efficient forecasting algorithms, which use a selective sampling scheme that enables collecting much fewer labels than standard procedures.
2956, MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
Tianyu Liu; Yuge Wang; Rex Ying; Hongyu Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Discovering genes with similar functions across diverse biomedical contexts poses a significant challenge in gene representation learning due to data heterogeneity. In this study, we resolve this problem by introducing a novel model called Multimodal Similarity Learning Graph Neural Network, which combines Multimodal Machine Learning and Deep Graph Neural Networks to learn gene representations from single-cell sequencing and spatial transcriptomic data.
2957, Reference-Based POMDPs
Edward Kim; Yohan Karunanayake; Hanna Kurniawati;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose the modified problem of a Reference-based POMDP wherein an agent tries to solve a POMDP while also trying to respect a given reference policy.
2958, Binary Classification with Confidence Difference
Wei Wang; Lei Feng; Yuchen Jiang; Gang Niu; Min-Ling Zhang; Masashi Sugiyama;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead of pointwise confidence, we are given only unlabeled data pairs equipped with confidence difference specifying the difference in the probabilities of being positive. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound achieves the optimal convergence rate.
2959, High Precision Causal Model Evaluation with Non-Randomized Trials
Chao Ma; Cheng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, non-randomized experiments based on inverse probability weighting (IPW) offer a more realistic approach but may suffer from high estimation variance. To tackle this challenge and enhance causal model evaluation in real-world non-randomized settings, we introduce a novel low-variance estimator for causal error, dubbed as the pairs estimator.
2960, Generalization in The Face of Adaptivity: A Bayesian Perspective
Moshe Shenfeld; Katrina Ligett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we prove that straightforward noise-addition algorithms already provide variance-dependent guarantees that also extend to unbounded queries.
2961, Object-centric Learning with Cyclic Walks Between Parts and Whole
Ziyu Wang; Mike Zheng Shou; Mengmi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from CNN or transformers and object entities.
2962, FIRAL: An Active Learning Algorithm for Multinomial Logistic Regression
Youguang Chen; George Biros;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on our theoretical analysis, we propose a novel active learning algorithm that employs regret minimization to minimize the FIR.
2963, On The Variance, Admissibility, and Stability of Empirical Risk Minimization
Gil Kur; Eli Putterman; Alexander Rakhlin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The key message of this paper is that, under mild assumptions, the suboptimality of ERM must be due to large bias rather than variance.
2964, Learning to Receive Help: Intervention-Aware Concept Embedding Models
Mateo Espinosa Zarlenga; Katie Collins; Krishnamurthy Dvijotham; Adrian Weller; Zohreh Shams; Mateja Jamnik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We argue that this is rooted in a CBM's lack of train-time incentives for the model to be appropriately receptive to concept interventions. To address this, we propose Intervention-aware Concept Embedding models (IntCEMs), a novel CBM-based architecture and training paradigm that improves a model's receptiveness to test-time interventions.
2965, Block-Coordinate Methods and Restarting for Solving Extensive-Form Games
Darshan Chakrabarti; Jelena Diakonikolas; Christian Kroer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present the first cyclic coordinate-descent-like method for the polytope of sequence-form strategies, which form the strategy spaces for the players in an extensive-form game (EFG).
2966, Lightweight Vision Transformer with Bidirectional Interaction
Qihang Fan; Huaibo Huang; Xiaoqiang Zhou; Ran He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, the bidirectional interaction between these two contexts has not been well explored and exploited, which is important in the human visual system. This paper proposes a **F**ully **A**daptive **S**elf-**A**ttention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways.
2967, Unsupervised Protein-Ligand Binding Energy Prediction Via Neural Euler's Rotation Equation
Wengong Jin; Siranush Sarkizova; Xun Chen; Nir HaCohen; Caroline Uhler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore unsupervised approaches and reformulate binding energy prediction as a generative modeling task.
2968, Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism
Xiaohan Zhao; Hualin Zhang; Zhouyuan Huo; Bin Gu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose forward gradient descent (FGD) as a potential solution to overcome the memory capacity limitation in on-device learning.
2969, A Unified Framework for U-Net Design and Analysis
Christopher Williams; Fabian Falck; George Deligiannidis; Chris C Holmes; Arnaud Doucet; Saifuddin Syed;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we provide a framework for designing and analysing general U-Net architectures.
2970, The Pick-to-Learn Algorithm: Empowering Compression for Tight Generalization Bounds and Improved Post-training Performance
Dario Paccagnan; Marco Campi; Simone Garatti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we build upon a recent breakthrough in compression theory to develop a new framework yielding tight generalization bounds of wide practical applicability.
2971, Projection Regret: Reducing Background Bias for Novelty Detection Via Diffusion Models
Sungik Choi; Hankook Lee; Honglak Lee; Moontae Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on our observation that diffusion models can *project* any sample to an in-distribution sample with similar background information, we propose *Projection Regret (PR)*, an efficient novelty detection method that mitigates the bias of non-semantic information.
2972, DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models
Tao Yang; Yuwang Wang; Yan Lu; Nanning Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a new task, disentanglement of (DPMs): given a pre-trained DPM, without any annotations of the factors, the task is to automatically discover the inherent factors behind the observations and disentangle the gradient fields of DPM into sub-gradient fields, each conditioned on the representation of each discovered factor.
2973, Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping
Jia-Qi Yang; De-Chuan Zhan; Le Gan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To validate the aforementioned analysis, we propose a method that involves jointly learning a semantic aware grouping function based on deep model features and logits to partition the data space into subsets.
2974, Learning Interpretable Low-dimensional Representation Via Physical Symmetry
Xuanjie Liu; Daniel Chin; Yichen Huang; Gus Xia;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this study, we take inspiration from modern physics and use *physical symmetry* as a self-consistency constraint for the latent space.
2975, SoTTA: Robust Test-Time Adaptation on Noisy Data Streams
Taesik Gong; Yewon Kim; Taeckyung Lee; Sorn Chottananurak; Sung-Ju Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This leads to a new threat to existing TTA algorithms; we found that prior TTA algorithms suffer from those non-interest test samples as they blindly adapt to incoming samples. To address this problem, we present Screening-out Test-Time Adaptation (SoTTA), a novel TTA algorithm that is robust to non-interest samples.
2976, Rethinking Rendering in Generalizable Neural Surface Reconstruction: A Learning-based Solution
Yixun Liang; Hao He; Yingcong Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present Reconstruction TRansformer (ReTR), a novel framework that leverages the transformer architecture to redesign the rendering process, enabling complex photon-particle interaction modeling.
2977, Birth of A Transformer: A Memory Viewpoint
Alberto Bietti; Vivien Cabannes; Diane Bouchacourt; Herve Jegou; Leon Bottou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By a careful empirical analysis of the training process on a simplified two-layer transformer, we illustrate the fast learning of global bigrams and the slower development of an induction head mechanism for the in-context bigrams.
2978, Learning Via Wasserstein-Based High Probability Generalization Bounds
Paul Viallard; Maxime Haddouche; Umut Simsekli; Benjamin Guedj;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Even though these bounds alleviated the aforementioned issues to a certain extent, they either hold in expectation, are for bounded losses, or are nontrivial to minimize in an SRM framework. In this work, we contribute to this line of research and prove novel Wasserstein distance-based PAC-Bayesian generalisation bounds for both batch learning with independent and identically distributed (i.i.d.) data, and online learning with potentially non-i.i.d. data.
2979, DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization
Hua Wang; Sheng Gao; Huanyu Zhang; Weijie Su; Milan Shen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In our paper, we introduce DP-HyPO, a pioneering framework for adaptive private hyperparameter optimization, aiming to bridge the gap between private and non-private hyperparameter optimization.
2980, Diffusion Dropout with Adaptive Prior for Speech Enhancement
Wenxin Tai; Yue Lei; Fan Zhou; Goce Trajcevski; Ting Zhong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, incorporating condition information into DDPMs for SE remains a challenge. We propose a model-agnostic method called DOSE that employs two efficient condition-augmentation techniques to address this challenge, based on two key insights: (1) We force the model to prioritize the condition factor when generating samples by training it with dropout operation; (2) We incorporate the condition information into the sampling process by providing an informative adaptive prior.
2981, ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
Ren Li; Benoit Guillard; Pascal Fua;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a parametric garment representation model that does this.
2982, Learning Functional Transduction
Mathieu Chalvidal; Thomas Serre; Rufin VanRullen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a hybrid approach and show that transductive regression principles can be meta-learned through gradient descent to form efficient in-context neural approximators by leveraging the theory of vector-valued Reproducing Kernel Ba- nach Spaces (RKBS).
2983, Going Beyond Persistent Homology Using Persistent Homology
Johanna Immonen; Amauri Souza; Vikas Garg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Augmenting these graph models with topological features via persistent homology (PH) has gained prominence, but identifying the class of attributed graphs that PH can recognize remains open. We introduce a novel concept of color-separating sets to provide a complete resolution to this important problem.
2984, Efficient Learning of Temporal Regularities with Event Embeddings
Chi Gao; Zidong Zhou; Luping Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For complete evaluations of models' TR learning capabilities, we formally define complementary problems of TR detection and TR query, formulate their evaluation metrics, and evaluate NE on classic ICEWS14, ICEWS18, and GDELT datasets.
2985, Beyond Normal: On The Evaluation of Mutual Information Estimators
Paweł Czyż; Frederic Grabowski; Julia Vogt; Niko Beerenwinkel; Alexander Marx;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we show how to construct a diverse family of distributions with known ground-truth mutual information and propose a language-independent benchmarking platform for mutual information estimators.
2986, Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions
Duligur Ibeling; Thomas Icard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The aim of this paper is to make clear and precise the relationship between the Rubin causal model (RCM) and structural causal model (SCM) frameworks for causal inference.
2987, Computing A Human-like Reaction Time Metric from Stable Recurrent Vision Models
Lore Goetschalckx; Lakshmi Narasimhan Govindarajan; Alekh Karkada Ashok; Thomas Serre;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we introduce a novel metric leveraging insights from subjective logic theory summarizing evidence accumulation in recurrent vision models.
2988, Hierarchical VAEs Provide A Normative Account of Motion Processing in The Primate Brain
Hadi Vafaii; Jacob Yates; Daniel Butts;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel synthetic data framework, Retinal Optic Flow Learning (ROFL), that enables control over motion statistics and their causes.
2989, Unexpected Improvements to Expected Improvement for Bayesian Optimization
Sebastian Ament; Samuel Daulton; David Eriksson; Maximilian Balandat; Eytan Bakshy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new family of acquisition functions, LogEI, whose members either have identical or approximately equal optima as their canonical counterparts, but are substantially easier to optimize numerically.
2990, Boosting with Tempered Exponential Measures
Richard Nock; Ehsan Amid; Manfred Warmuth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that $t$-AdaBoost retains AdaBoost's celebrated exponential convergence rate when $t\in [0,1)$ while allowing a slight improvement of the rate's hidden constant compared to $t=1$.
2991, Topological Obstructions and How to Avoid Them
Babak Esmaeili; Robin Walters; Heiko Zimmermann; Jan-Willem van de Meent;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we theoretically and empirically characterize obstructions to training encoders with geometric latent spaces.
2992, Energy Discrepancies: A Score-Independent Loss for Energy-Based Models
Tobias Schröder; Zijing Ou; Jen Lim; Yingzhen Li; Sebastian Vollmer; Andrew Duncan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a novel loss function called Energy Discrepancy (ED) which does not rely on the computation of scores or expensive Markov chain Monte Carlo.
2993, Uncertainty-Aware Instance Reweighting for Off-Policy Learning
Xiaoying Zhang; Junpu Chen; Hongning Wang; Hong Xie; Yang Liu; John C.S. Lui; Hang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The contribution of this work is to explicitly model the uncertainty in the estimated logging policy, and propose an Uncertainty-aware Inverse Propensity Score estimator (UIPS) for improved off-policy learning, with a theoretical convergence guarantee.
2994, Alternating Updates for Efficient Transformers
Cenk Baykal; Dylan Cutler; Nishanth Dikkala; Nikhil Ghosh; Rina Panigrahy; Xin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Alternating Updates (AltUp), a simple-to-implement method to increase a model's capacity without the computational burden.
2995, Adjustable Robust Reinforcement Learning for Online 3D Bin Packing
Yuxin Pan; Yize Chen; Fangzhen Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To realize this lower bound, we adopt an iterative procedure that searches for the associated mixture dynamics and improves the corresponding policy. We integrate this procedure into two popular robust adversarial algorithms to develop the exact and approximate AR2L algorithms.
2996, EXPLORING THE OPTIMAL CHOICE FOR GENERATIVE PROCESSES IN DIFFUSION MODELS: ORDINARY VS STOCHASTIC DIFFERENTIAL EQUATIONS
Yu Cao; Jingrun Chen; Yixin Luo; Xiang ZHOU;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we examine the problem mathematically by examining two limiting scenarios: the ODE case and the large diffusion case.
2997, Exponentially Convergent Algorithm for Supervised Dictionary Learning and Application in Identification of Oncogene Clusters
Joowon Lee; Hanbaek Lyu; Weixin Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide a novel framework that 'lifts' SDL as a low-rank matrix estimation problem in a combined factor space and propose an efficient algorithm that provably converges exponentially fast to a global minimizer of the objective with arbitrary initialization.
2998, Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics
Mathias Schreiner; Ole Winther; Simon Olsson;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we present Implict Transfer Operator (ITO) Learning, a theoretical framework to learn surrogates of the simulation process with multiple time-resolutions.
2999, Neural Sculpting: Uncovering Hierarchically Modular Task Structure Through Pruning and Network Analysis
Shreyas Malakarjun Patil; Loizos Michael; Constantine Dovrolis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The high-level question in this work is: if we learn a task using a sufficiently deep neural network, how can we uncover the underlying hierarchy of sub-functions in that task?
3000, Towards Efficient Image Compression Without Autoregressive Models
Muhammad Salman Ali; Yeongwoong Kim; Sung-Ho Bae; Hui Yong Kim; Sung-Chang Lim; Donghyun Kim; Chaoning Zhang; Maryam Qamar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel alternative to the AR-based approach that can provide a significantly better trade-off between performance and complexity.
3001, Momentum Provably Improves Error Feedback!
Ilyas Fatkhullin; Alexander Tyurin; Peter Richtarik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In particular, in the canonical nonconvex setting, all known variants of EF rely on very large batch sizes to converge, which can be prohibitive in practice. We propose a surprisingly simple fix which removes this issue both theoretically, and in practice: the application of Polyak's momentum to the latest incarnation of EF due to Richt�rik et al. [2021] known as EF21.
3002, Reliable Learning in Challenging Environments
Maria-Florina Balcan; Steve Hanneke; Rattana Pukdee; Dravyansh Sharma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we consider the design and analysis of reliable learners in challenging test-time environments as encountered in modern machine learning problems: namely adversarial test-time attacks (in several variations) and natural distribution shifts.
3003, Unified Lower Bounds for Interactive High-dimensional Estimation Under Information Constraints
Jayadev Acharya; Clément L Canonne; Ziteng Sun; Himanshu Tyagi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide a unified framework enabling us to derive a variety of (tight) minimax lower bounds for different parametric families of distributions, both continuous and discrete, under any $\ell_p$ loss.
3004, Langevin Quasi-Monte Carlo
Sifan Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we show that the estimation error of LMC can also be reduced by using quasi-random samples.
3005, Robust Knowledge Transfer in Tiered Reinforcement Learning
Jiawei Huang; Niao He;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we study the Tiered Reinforcement Learning setting, a parallel transfer learning framework, where the goal is to transfer knowledge from the low-tier (source) task to the high-tier (target) task to reduce the exploration risk of the latter while solving the two tasks in parallel.
3006, Adaptive Topological Feature Via Persistent Homology: Filtration Learning for Point Clouds
Naoki Nishikawa; Yuichi Ike; Kenji Yamanishi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a framework that learns a filtration adaptively with the use of neural networks.
3007, Single-Stage Visual Query Localization in Egocentric Videos
Hanwen Jiang; Santhosh Kumar Ramakrishnan; Kristen Grauman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose VQLoC, a novel single-stage VQL framework that is end-to-end trainable.
3008, Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
Tingting Dan; Jiaqi Ding; Ziquan Wei; Shahar Kovalsky; Minjeong Kim; Won Hwa Kim; Guorong Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the classic Brachistochrone problem, we seek how to devise a new inductive bias for cutting-edge graph application and present a general framework through the lens of variational analysis.
3009, How A Student Becomes A Teacher: Learning and Forgetting Through Spectral Methods
Lorenzo Giambagli; Lorenzo Buffoni; Lorenzo Chicchi; Duccio Fanelli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we take a decisive leap forward by proposing a radically different optimization scheme which builds on a spectral representation of the linear transfer of information between layers.
3010, Large Language Models Transition from Integrating Across Position-yoked, Exponential Windows to Structure-yoked, Power-law Windows
David Skrill; Samuel Norman-Haignere;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although many studies have investigated attentional weights in large language models (LLMs), little is known about whether LLMs exhibit a meaningful integration window, and if so, whether these windows follow a particular functional form or vary with structural boundaries in language. To answer these questions, we developed a simple word-swap procedure for estimating integration windows from neural language models that does not depend upon access to gradients or knowledge of the model architecture (e.g., attention weights).
3011, Cascading Contextual Assortment Bandits
Hyun-jun Choi; Rajan Udwani; Min-hwan Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel combinatorial bandit model, termed as the \textit{cascading contextual assortment bandit}, which generalizes the existing cascading and assortment bandits.
3012, PoET: A Generative Model of Protein Families As Sequences-of-sequences
Timothy Truong Jr; Tristan Bepler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current models are either difficult to direct to produce a protein from a specific family of interest, or must be trained on a large multiple sequence alignment (MSA) from the specific family of interest, making them unable to benefit from transfer learning across families. To address this, we propose **P**r**o**tein **E**volutionary **T**ransformer (PoET), an autoregressive generative model of whole protein families that learns to generate sets of related proteins as sequences-of-sequences across tens of millions of natural protein sequence clusters.
3013, Task-aware Distributed Source Coding Under Dynamic Bandwidth
Po-han Li; Sravan Kumar Ankireddy; Ruihan Zhao; Hossein Nourkhiz Mahjoub; Ehsan Moradi Pari; Ufuk Topcu; Sandeep Chinchali; Hyeji Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We design a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA).
3014, Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives
Wenjie Qiu; Wensen Mao; He Zhu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these approaches do not guarantee generalization to out-of-distribution LTL objectives, which may have increased complexity. In this paper, we propose a novel approach to address this challenge.
3015, Towards Understanding The Dynamics of Gaussian-Stein Variational Gradient Descent
Tianle Liu; Promit Ghosal; Krishnakumar Balasubramanian; Natesh Pillai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a complete picture by considering both the mean-field PDE and discrete particle systems.
3016, Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization
Jun Chen; Hong Chen; Bin Gu; Hao Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper aims to establish systematic theoretical assessments of FedZO by developing the analysis technique of on-average model stability.
3017, Two-Stage Predict+Optimize for MILPs with Unknown Parameters in Constraints
Xinyi Hu; Jasper Lee; Jimmy Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we give a new simpler and more powerful framework called Two-Stage Predict+Optimize, which we believe should be the canonical framework for the Predict+Optimize setting.
3018, Convex-Concave Zero-Sum Stochastic Stackelberg Games
Denizalp Goktas; Arjun Prakash; Sadie Zhao; Amy Greenwald;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Zero-sum stochastic Stackelberg games can be used to model a large class of problems, ranging from economics to human robot interaction. In this paper, we develop policy gradient methods to solve these games from noisy gradient estimates computed from observed trajectories of play.
3019, Exposing The Troublemakers in Described Object Detection
Chi Xie; Zhao Zhang; Yixuan Wu; Feng Zhu; Rui Zhao; Shuang Liang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Detecting objects based on language descriptions is a popular task that includes Open-Vocabulary object Detection (OVD) and Referring Expression Comprehension (REC). In this paper, we advance them to a more practical setting called Described Object Detection (DOD) by expanding category names to flexible language expressions for OVD and overcoming the limitation of REC to only grounding the pre-existing object.
3020, Modeling Dynamics Over Meshes with Gauge Equivariant Message Passing
Jung Yeon Park; Lawson Wong; Robin Walters;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new gauge-equivariant architecture that implements nonlinear message passing on meshes.
3021, SAMoSSA: Multivariate Singular Spectrum Analysis with Stochastic Autoregressive Noise
Abdullah Alomar; Munther Dahleh; Sean Mann; Devavrat Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To establish theoretical guarantees, we overcome three hurdles: (i) we characterize the spectra of Page matrices of stable AR processes, thus extending the analysis of mSSA; (ii) we extend the analysis of AR process identification in the presence of arbitrary bounded perturbations; (iii) we characterize the out-of-sample or forecasting error, as opposed to solely considering model identification.
3022, A Fast and Accurate Estimator for Large Scale Linear Model Via Data Averaging
Rui Wang; Yanyan Ouyang; Yu Panpan; Wangli Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To achieve a better statistical performance, we propose a new sketching method based on data averaging.
3023, Improved Communication Efficiency in Federated Natural Policy Gradient Via ADMM-based Gradient Updates
Guangchen Lan; Han Wang; James Anderson; Christopher Brinton; Vaneet Aggarwal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, high communication overhead remains a critical bottleneck, particularly for natural policy gradient (NPG) methods, which are second-order. To address this issue, we propose the FedNPG-ADMM framework, which leverages the alternating direction method of multipliers (ADMM) to approximate global NPG directions efficiently.
3024, Gaussian Mixture Solvers for Diffusion Models
Hanzhong Guo; Cheng Lu; Fan Bao; Tianyu Pang; Shuicheng Yan; Chao Du; Chongxuan LI;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our investigation suggests that this is because the Gaussian assumption in the reverse transition kernel is frequently violated (even in the case of simple mixture data) given a limited number of discretization steps. To overcome this limitation, we introduce a novel class of SDE-based solvers called Gaussian Mixture Solvers (GMS) for diffusion models.
3025, Universal Prompt Tuning for Graph Neural Networks
Taoran Fang; Yunchao Zhang; YANG YANG; Chunping Wang; Lei Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy.
3026, Dynamic Non-monotone Submodular Maximization
Kiarash Banihashem; Leyla Biabani; Samira Goudarzi; MohammadTaghi Hajiaghayi; Peyman Jabbarzade; Morteza Monemizadeh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We answer this question **affirmatively** by showing a reduction from maximizing non-monotone submodular functions under the cardinality constraint $k$ to maximizing monotone submodular functions under the same constraint. Through this reduction, we obtain a dynamic algorithm that maintains a $(8+\varepsilon)$-approximate solution for this problem using amortized expected $O(\varepsilon^{-3}k^3\log^3(n)\log(k))$ oracle queries.
3027, Efficient Potential-based Exploration in Reinforcement Learning Using Inverse Dynamic Bisimulation Metric
Yiming Wang; Ming Yang; Renzhi Dong; Binbin Sun; Leong Hou U; Furui Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Nevertheless, these methods heavily rely on the count-based episodic term in their exploration bonus which falls short in scalability. To address these limitations, we propose a general end-to-end potential-based exploration bonus for deep RL via potentials of state discrepancy, which motivates the agent to discover novel states and provides them with denser rewards without manual intervention.
3028, Adaptive Uncertainty Estimation Via High-Dimensional Testing on Latent Representations
Tsai Hor Chan; Kin Wai Lau; Jiajun Shen; Guosheng Yin; Lequan Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Also, most of them rely on seen out-of-distribution (OOD) data in training for better estimation of uncertainty, which limits their uncertainty estimation performance in practice when the OOD data are generally unseen. To overcome the above limitations, we propose a new framework for uncertainty estimation, which leverages the statistical properties of the feature representations and estimates uncertainties using data-adaptive high-dimensional hypothesis testing.
3029, Partial Label Learning with Dissimilarity Propagation Guided Candidate Label Shrinkage
Yuheng Jia; Fuchao Yang; Yongqiang Dong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we first construct a constrained regression model to capture the confidence of the candidate labels, and multiply the label confidence matrix by its transpose to build a second-order similarity matrix, whose elements indicate the pairwise similarity relationships of samples globally. Then we develop a semantic dissimilarity matrix by considering the complement of the intersection of the candidate label set, and further propagate the initial dissimilarity relationships to the whole data set by leveraging the local geometric structure of samples.
3030, Stochastic Multi-armed Bandits: Optimal Trade-off Among Optimality, Consistency, and Tail Risk
Feng Zhu; Zeyu Zheng; David Simchi-Levi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the stochastic multi-armed bandit problem and fully characterize the interplays among three desired properties for policy design: worst-case optimality, instance-dependent consistency, and light-tailed risk.
3031, Task Arithmetic in The Tangent Space: Improved Editing of Pre-Trained Models
Guillermo Ortiz-Jimenez; Alessandro Favero; Pascal Frossard;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a comprehensive study of task arithmetic in vision-language models and show that weight disentanglement is the crucial factor that makes it effective.
3032, On The Powerfulness of Textual Outliers for Visual OoD Detection
Sangha Park; Jisoo Mok; Dahuin Jung; Saehyung Lee; Sungroh Yoon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Drawing inspiration from the recent advancements in vision-language pre-training, this paper venture out to the uncharted territory of textual outlier exposure.
3033, Knowledge Diffusion for Distillation
Tao Huang; Yuan Zhang; Mingkai Zheng; Shan You; Fei Wang; Chen Qian; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models.
3034, Exploiting Hidden Structures in Non-convex Games for Convergence to Nash Equilibrium
Iosif Sakos; Emmanouil-Vasileios Vlatakis-Gkaragkounis; Panayotis Mertikopoulos; Georgios Piliouras;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Driven by this observation, several recent threads in the literature have focused on the study of games with such a hidden structure, that is, when players control a layer of nonlinear functions whose output subsequently serves as input for a convex, monotone game. In this general setting, our paper proposes a flexible first-order method that successfully exploits this hidden structure and converges to a Nash equilibrium under minimal assumptions for the transformation connecting the players' control layer to the game's hidden, convex-structured layer.
3035, Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT
Zhen Zhang; Bingqiao Luo; Shengliang Lu; Bingsheng He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce the concept of *Live Graph Lab* for temporal graphs, which enables open, dynamic and real transaction graphs from blockchains.
3036, ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition
Aashaka Desai; Lauren Berger; Fyodor Minakov; Nessa Milano; Chinmay Singh; Kriston Pumphrey; Richard Ladner; Hal Daumé III; Alex X Lu; Naomi Caselli; Danielle Bragg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To help tackle this problem, we release ASL Citizen, the first crowdsourced Isolated Sign Language Recognition (ISLR) dataset, collected with consent and containing 83,399 videos for 2,731 distinct signs filmed by 52 signers in a variety of environments. We propose that this dataset be used for sign language dictionary retrieval for American Sign Language (ASL), where a user demonstrates a sign to their webcam to retrieve matching signs from a dictionary.
3037, Real3D-AD: A Dataset of Point Cloud Anomaly Detection
Jiaqi Liu; Guoyang Xie; Ruitao Chen; Xinpeng Li; Jinbao Wang; Yong Liu; Chengjie Wang; Feng Zheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Additionally, we present a comprehensive benchmark for Real3D-AD, revealing the absence of baseline methods for high-precision point cloud anomaly detection. To address this, we propose Reg3D-AD, a registration-based 3D anomaly detection method incorporating a novel feature memory bank that preserves local and global representations.
3038, A High-Resolution Dataset for Instance Detection with Multi-View Object Capture
QIANQIAN SHEN; Yunhan Zhao; Nahyun Kwon; Jeeeun Kim; Yanan Li; Shu Kong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite its practical significance, its advancement is overshadowed by Object Detection, which aims to detect objects belonging to some predefined classes. One major reason is that current InsDet datasets are too small in scale by today's standards. For example, the popular InsDet dataset GMU (published in 2016) has only 23 instances, far less than COCO (80 classes), a well-known object detection dataset published in 2014. We are motivated to introduce a new InsDet dataset and protocol.
3039, PopSign ASL V1.0: An Isolated American Sign Language Dataset Collected Via Smartphones
Thad Starner; Sean Forbes; Matthew So; David Martin; Rohit Sridhar; Gururaj Deshpande; Sam Sepah; Sahir Shahryar; Khushi Bhardwaj; Tyler Kwok; Daksh Sehgal; Saad Hassan; Bill Neubauer; Sofia Vempala; Alec Tan; Jocelyn Heath; Unnathi Kumar; Priyanka Mosur; Tavenner Hall; Rajandeep Singh; Christopher Cui; Glenn Cameron; Sohier Dane; Garrett Tanzer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Fortraining the recognizer, we introduce the PopSign ASL v1.0 dataset that collectsexamples of 250 isolated American Sign Language (ASL) signs using Pixel 4Asmartphone selfie cameras in a variety of environments.
3040, A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Casual Relationship
Shiyu Hu; Dailing Zhang; wu meiqi; Xiaokun Feng; Xuchen Li; Xin Zhao; Kaiqi Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, these selected videos are still short sequences with uncomplicated spatio-temporal and casual relationships, and the provided semantic descriptions are too simple to characterize video content. To address these issues, we (1) first propose a new multi-modal global instance tracking benchmark named MGIT.
3041, WordScape: A Pipeline to Extract Multilingual, Visually Rich Documents with Layout Annotations from Web Crawl Data
Maurice Weber; Carlo Siebenschuh; Rory Butler; Anton Alexandrov; Valdemar Thanner; Georgios Tsolakis; Haris Jabbar; Ian Foster; Bo Li; Rick Stevens; Ce Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora comprising millions of pages with annotations for document layout detection.
3042, OFCOURSE: A Multi-Agent Reinforcement Learning Environment for Order Fulfillment
Yiheng Zhu; Yang Zhan; Xuankun Huang; Yuwei Chen; yujie Chen; Jiangwen Wei; Wei Feng; Yinzhi Zhou; Haoyuan Hu; Jieping Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, managing efficient order fulfillment is challenging due to a series of interdependent online sequential decision-making problems. To clear this hurdle, rather than solving the problems separately as some recent researchers attempted, this paper proposes a method based on multi-agent reinforcement learning to integratively solve the series of problems, including order handling, packing and pickup, storage, order consolidation, and last-mile delivery.
3043, RoboHive: A Unified Framework for Robot Learning
Vikash Kumar; Rutav Shah; Gaoyue Zhou; Vincent Moens; Vittorio Caggiano; Abhishek Gupta; Aravind Rajeswaran;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present RoboHive, a comprehensive software platform and ecosystem for research in the field of Robot Learning and Embodied AI.
3044, Persuading Farsighted Receivers in MDPs: The Power of Honesty
Martino Bernasconi; Matteo Castiglioni; Alberto Marchesi; Mirco Mutti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we show that Markovian signaling schemes do *not* constitute the right class of policies.
3045, Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics
mu niu; Zhenwen Dai; Pokman Cheung; Yizhu Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This article presents a novel approach to construct Intrinsic Gaussian Processes for regression on unknown manifolds with probabilistic metrics (GPUM) in point clouds.
3046, Small Transformers Compute Universal Metric Embeddings
Anastasis Kratsios; Valentin Debarnot; Ivan Dokmanić;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We study representations of data from an arbitrary metric space $\mathcal{X}$ in the space of univariate Gaussian mixtures equipped with a transport metric (Delon and Desolneux 2020).
3047, Euler-Lagrange Analysis of Generative Adversarial Networks
Siddarth Asokan; Chandra Seelamantula;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Considering Wasserstein GANs (WGANs) with a gradient-norm penalty, we show that the optimal discriminator is the solution to a Poisson differential equation.
3048, Large Sample Spectral Analysis of Graph-based Multi-manifold Clustering
Nicolas Garcia Trillos; Pengfei He; Chenghui Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we study statistical properties of graph-based algorithms for multi-manifold clustering (MMC).
3049, The Separation Capacity of Random Neural Networks
Sjoerd Dirksen; Martin Genzel; Laurent Jacques; Alexander Stollenwerk;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the present article, we enhance the theoretical understanding of random neural networks by addressing the following data separation problem: under what conditions can a random neural network make two classes $\mathcal{X}^-, \mathcal{X}^+ \subset \mathbb{R}^d$ (with positive distance) linearly separable?
3050, Bilevel Optimization with A Lower-level Contraction: Optimal Sample Complexity Without Warm-Start
Riccardo Grazzi; Massimiliano Pontil; Saverio Salzo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we show that without warm-start, it is still possible to achieve order-wise (near) optimal sample complexity.
3051, Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data
Bingqing Hu; Bin Nan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this article, we consider estimating the conditional distribution function using neural networks for both censored and uncensored data.
3052, [Re] Pure Noise to The Rescue of Insufficient Data
Seungjae Lee; Seungmin Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We examine the main claims of the original paper [1], whichstates that in an image classification task with imbalanced training data, (i) using purenoise to augment minority-class images encourages generalization by improving minority-class accuracy. This method is paired with (ii) a new batch normalization layer thatnormalizes noise images using affine parameters learned from natural images, whichimproves the model�s performance. Moreover, (iii) this improvement is robust to vary-ing levels of data augmentation. Finally, the authors propose that (iv) adding pure noiseimages can improve classification even on balanced training data.
3053, [Re] CrossWalk: Fairness-enhanced Node Representation Learning
Luca Pantea; Andrei-Eusebiu Blahovici;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work aims to reproduce the findings of the paper �CrossWalk: Fairness-enhanced Node Representation Learning� by investigating the two main claims made by the authors about CrossWalk, which suggest that (i) CrossWalk enhances fairness in three graph algorithms, while only suffering from small decreases in performance, and that (ii) CrossWalk preserves the necessary structural properties of the graph while reducing disparity.
3054, Reproducibility Study of The Fairness-enhanced Node Representation Learning
Gijs Moens; Job De Witte; Tobias Gobel; Meggie Van den Oever;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The limited size of the data sets in combination with the efficient algorithms enables the experiments to be conducted without significant difficulties and is computable on standard CPUs without the need for additional resources. In this reproducibility report, the outcomes of the experiments are in agreement with the results presented in the original paper.
3055, [Re] Variational Neural Cellular Automata
Albert Aillet; Simon Sondén;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The paper presents two variants of this VNCA decoder: the doubling VNCA variant that is claimed to have a simple latent space, and the non-doubling VNCA variant that is claimed to be optimized for damage recovery and stability over many steps.
3056, Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”
Aditya Patra; Sina Taslimi; Luke Chin A Foeng; Pratik Kayal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this reproducibility study, we verify the claims and contributions in Cartoon Explanations of Image Classifiers by Kolek et al..
3057, [Re] Fairness Guarantees Under Demographic Shift
Valentin Buchner; Philip Schutte; Yassin Ben Allal; Hamed Ahadi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our results approached the results reported in the original paper. They supported the claim that \textit{Shifty} reliably guarantees fairness under demographic shift, but could not verify that Shifty performs at no loss of accuracy.
3058, [Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
Kyosuke Morita;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This study aims to reproduce the results of the paper 'FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles' by Lucic et al.
3059, Reproducibility Study of Label-Free Explainability for Unsupervised Models
Valentinos Pariza; Avik Pal; Madhura Pawar; Quim Serra Faber;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our goal is to reproduce the paper's four main claims in a label-free setting:(1) feature importance scores determine salient features of a model's input, (2) example importance scores determine salient training examples to explain a test example, (3) interpretability of saliency maps is hard for disentangled VAEs, (4) distinct pretext tasks don’t have interchangeable representations.
3060, Easy Bayesian Transfer Learning with Informative Priors
Martin Špendl; Klementina Pirc;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The paper proposes a three-step pipeline for replacing standard transfer learning with a pre-trained prior.
3061, [Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking
Sean Mcleish; Long Tran-Thanh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this report, we aim to validate the claims of Bansal et al. These are that the recurrent architecture presented, with skip connections and a progressive loss function, prevent the original problem being forgotten or corrupted during processing allowing for the recurrent module to be applied indefinitely and that this architecture avoids the overthinking trap.
3062, [Re] On Explainability of Graph Neural Networks Via Subgraph Explorations
Yannik Mahlau; Lukas Berg; Leonie Kayser;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We were able to reproduce the main claims on the MUTAG dataset, where SubgraphX has a better performance than GNNExplainer. Furthermore, SubgraphX has a reasonable runtime of about seven times longer than GNNExplainer.
3063, Towards Last-Layer Retraining for Group Robustness with Fewer Annotations
Tyler LaBonte; Vidya Muthukumar; Abhishek Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The recent deep feature reweighting (DFR) technique achieves state-of-the-art group robustness via simple last-layer retraining, but it requires held-out group and class annotations to construct a group-balanced reweighting dataset. In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations.
3064, Active Observing in Continuous-time Control
Samuel Holt; Alihan Hüyük; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we are the first to formalize the continuous-time control problem with costly observations.
3065, Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?
Danika Gao; Kaizhe Hu; Guowei Xu; Huazhe Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we propose Learning from the Void (LfVoid), a method that leverages the power of pre-trained text-to-image models and advanced image editing techniques to guide robot learning.
3066, Flat Seeking Bayesian Neural Networks
Van-Anh Nguyen; Tung-Long Vuong; Hoang Phan; Thanh-Toan Do; Dinh Phung; Trung Le;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop theories, the Bayesian setting, and the variational inference approach for the sharpness-aware posterior.
3067, Uncovering Motifs of Concurrent Signaling Across Multiple Neuronal Populations
Evren Gokcen; Anna Jasper; Alison Xu; Adam Kohn; Christian Machens; Byron M Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we develop a dimensionality reduction framework that determines (1) the subset of populations described by each latent dimension, (2) the direction of signal flow among those populations, and (3) how those signals evolve over time within and across experimental trials.
3068, Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases
Mazda Moayeri; Wenxiao Wang; Sahil Singla; Soheil Feizi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues.
3069, Advancing Bayesian Optimization Via Learning Smooth Latent Spaces
Seunghun Lee; Jaewon Chu; Sihyeon Kim; Juyeon Ko; Hyunwoo Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To alleviate the discrepancy, we propose Correlated latent space Bayesian Optimization (CoBO), which focuses on learning correlated latent spaces characterized by a strong correlation between the distances of the latent space and the distances of the objective function.
3070, Policy Optimization for Continuous Reinforcement Learning
HANYANG ZHAO; Wenpin Tang; David Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Built upon recent advances in the continuous approach to RL, we develop a notion of occupation time (specifically for a discounted objective), and show how it can be effectively used to derive performance difference and local approximation formulas.
3071, Analysis of Variance of Multiple Causal Networks
Zhongli Jiang; Dabao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose to unify multiple DCGs with a single structural model and develop a limited-information-based method to simultaneously construct multiple networks and infer their disparities, which can be visualized by appropriate correspondence analysis.
3072, Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
Ziniu Li; Tian Xu; Zeyu Qin; Yang Yu; Zhi-Quan Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the supplementary data may contain out-of-expert-distribution samples, making it tricky to utilize the supplementary data to improve performance. In this paper, we focus on a classic offline IL algorithm called behavioral cloning (BC) and its variants, studying the imitation gap bounds in the context of IL with supplementary data.
3073, Accessing Higher Dimensions for Unsupervised Word Translation
Sida Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose coocmap, a method that can use either high-dimensional co-occurrence counts or their lower-dimensional approximations.
3074, Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks
Minki Kang; Seanie Lee; Jinheon Baek; Kenji Kawaguchi; Sung Ju Hwang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by our theoretical analysis on memorization, we propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales with augmented knowledge retrieved from an external knowledge base.
3075, Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition
Yuhang Zhang; Yaqi Li; lixiong Qin; Xuannan Liu; Weihong Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, our aim is to address the imbalanced FER problem.
3076, On Skip Connections and Normalisation Layers in Deep Optimisation
Lachlan MacDonald; Jack Valmadre; Hemanth Saratchandran; Simon Lucey;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a general theoretical framework, designed for the study of gradient optimisation of deep neural networks, that encompasses ubiquitous architecture choices including batch normalisation, weight normalisation and skip connections.
3077, Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training
Jian Meng; Li Yang; Kyungmin Lee; Jinwoo Shin; Deliang Fan; Jae-sun Seo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite the success of the labelless training, current contrastive learning algorithms *failed* to achieve good performance with lightweight (compact) models, e.g., MobileNet, while the requirements of the heavy encoders impede the energy-efficient computation, especially for resource-constrained AI applications. Motivated by this, we propose a new self-supervised CL scheme, named SACL-XD, consisting of two technical components, **S**limmed **A**symmetrical **C**ontrastive **L**earning (SACL) and **Cross**-**D**istillation~(XD), which collectively enable efficient CL with compact models.
3078, MIMEx: Intrinsic Rewards from Masked Input Modeling
Toru Lin; Allan Jabri;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We show how this perspective naturally leads to a unified view on existing intrinsic reward approaches: they are special cases of conditional prediction, where the estimation of novelty can be seen as pseudo-likelihood estimation with different mask distributions. From this view, we propose a general framework for deriving intrinsic rewards -- Masked Input Modeling for Exploration (MIMEx) -- where the mask distribution can be flexibly tuned to control the difficulty of the underlying conditional prediction task.
3079, A Unified Fast Gradient Clipping Framework for DP-SGD
Weiwei Kong; Andres Munoz Medina;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: When the loss function in DP-SGD is consists of an intermediate linear operation, existing methods in the literature have proposed decompositions of gradients that are amenable to fast norm computations. In this paper, we present a framework that generalizes the above approach to arbitrary (possibly nonlinear) intermediate operations.
3080, GloptiNets: Scalable Non-Convex Optimization with Certificates
Gaspard Beugnot; Julien Mairal; Alessandro Rudi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a novel approach to non-convex optimization with certificates, which handles smooth functions on the hypercube or on the torus.
3081, FlowPG: Action-constrained Policy Gradient with Normalizing Flows
Janaka Brahmanage; Jiajing LING; Akshat Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While adding a projection layer on top of the original policy network is a commonly used approach, it involves solving a mathematical program, either during training or in action execution, or both, which can result in longer training times and slower convergence. To address this issue, first, we leverage Hamiltonian Monte Carlo simulation to generate uniformly distributed valid actions that satisfy the constraints. Second, we approximate the distribution of these valid actions using a normalizing flow model, which can transform a simple distribution, such as a Gaussian or uniform distribution, into a complex one.
3082, Encoding Time-Series Explanations Through Self-Supervised Model Behavior Consistency
Owen Queen; Thomas Hartvigsen; Teddy Koker; Huan He; Theodoros Tsiligkaridis; Marinka Zitnik;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present TimeX, a time series consistency model for training explainers.
3083, Self-supervised Video Pretraining Yields Human-aligned Visual Representations
Nikhil Parthasarathy; S. M. Ali Eslami; Joao Carreira; Olivier Henaff;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Yet, outside of specific tasks that require explicit temporal understanding, static image pretraining remains the dominant paradigm for learning foundational models of natural scenes. In this work we question this dichotomy, and ask whether video pretraining can yield visual representations that bear the hallmarks of human perception: generalisation across tasks, robustness to perturbations, and alignment to human judgements.
3084, Understanding Deep Gradient Leakage Via Inversion Influence Functions
Haobo Zhang; Junyuan Hong; Yuyang Deng; Mehrdad Mahdavi; Jiayu Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel Inversion Influence Function (I$^2$F) that establishes a closed-form connection between the recovered images and the private gradients by implicitly solving the DGL problem.
3085, The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning
Artyom Gadetsky; Maria Brbic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present HUME, a simple model-agnostic framework for inferring human labeling of a given dataset without any external supervision.
3086, GLIME: General, Stable and Local LIME Explanation
Zeren Tan; Yang Tian; Jian Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Additionally, LIME's sampling approach is non-local and biased towards the reference, leading to diminished local fidelity and instability to references. To address these challenges, we propose \textsc{Glime}, an enhanced framework that extends LIME and unifies several previous methods.
3087, Posthoc Privacy Guarantees for Collaborative Inference with Modified Propose-Test-Release
Abhishek Singh; Praneeth Vepakomma; Vivek Sharma; Ramesh Raskar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing works so far evaluate the privacy of these encodings through empirical reconstruction attacks. In this work, we develop a new framework that provides formal privacy guarantees for an arbitrarily trained neural network by linking its local Lipschitz constant with its local sensitivity.
3088, Time-uniform Confidence Bands for The CDF Under Nonstationarity
Paul Mineiro; Steven Howard;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consistent with known impossibility results, we present computationally felicitous time-uniform and value-uniform bounds on the CDF of the running averaged conditional distribution of a real-valued random variable which are always valid and sometimes trivial, along with an instance-dependent convergence guarantee.
3089, Fairness Aware Counterfactuals for Subgroups
Loukas Kavouras; Konstantinos Tsopelas; Giorgos Giannopoulos; Dimitris Sacharidis; Eleni Psaroudaki; Nikolaos Theologitis; Dimitrios Rontogiannis; Dimitris Fotakis; Ioannis Emiris;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present Fairness Aware Counterfactuals for Subgroups (FACTS), a framework for auditing subgroup fairness through counterfactual explanations.
3090, Explore to Generalize in Zero-Shot RL
Ev Zisselman; Itai Lavie; Daniel Soudry; Aviv Tamar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, on problems such as the ProcGen Maze, an adequate solution that is invariant to the task visualization does not exist, and therefore invariance-based approaches fail. Our insight is that learning a policy that explores the domain effectively is harder to memorize than a policy that maximizes reward for a specific task, and therefore we expect such learned behavior to generalize well; we indeed demonstrate this empirically on several domains that are difficult for invariance-based approaches.
3091, Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
Liming Wu; Zhichao Hou; Jirui Yuan; Yu Rong; Wenbing Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we reformulate dynamics simulation as a spatio-temporal prediction task, by employing the trajectory in the past period to recover the Non-Markovian interactions.
3092, Evolving Connectivity for Recurrent Spiking Neural Networks
Guan Wang; Yuhao Sun; Sijie Cheng; Sen Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the widely-used surrogate gradient-based training methods for RSNNs are inherently inaccurate and unfriendly to neuromorphic hardware. To address these limitations, we propose the evolving connectivity (EC) framework, an inference-only method for training RSNNs.
3093, A Diffusion-Model of Joint Interactive Navigation
Matthew Niedoba; Jonathan Lavington; Yunpeng Liu; Vasileios Lioutas; Justice Sefas; Xiaoxuan Liang; Dylan Green; Setareh Dabiri; Berend Zwartsenberg; Adam Scibior; Frank Wood;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present DJINN -- a diffusion based method of generating traffic scenarios.
3094, Training on Foveated Images Improves Robustness to Adversarial Attacks
Muhammad Shah; Bhiksha Raj;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In the context of vision, we hypothesize that an important contributor to the robustness of human visual perception is constant exposure to low-fidelity visual stimuli in our peripheral vision. To investigate this hypothesis, we develop RBlur, an image transform that simulates the loss in fidelity of peripheral vision by blurring the image and reducing its color saturation based on the distance from a given fixation point.
3095, What Do Deep Saliency Models Learn About Visual Attention?
Shi Chen; Ming Jiang; Qi Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a novel analytic framework that sheds light on the implicit features learned by saliency models and provides principled interpretation and quantification of their contributions to saliency prediction.
3096, Memory-Efficient Fine-Tuning of Compressed Large Language Models Via Sub-4-bit Integer Quantization
Jeonghoon Kim; Jung Hyun Lee; Sungdong Kim; Joonsuk Park; Kang Min Yoo; Se Jung Kwon; Dongsoo Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the issue, we present Parameter-Efficient and Quantization-aware Adaptation (PEQA), a novel quantization-aware PEFT technique that facilitates model compression and accelerates inference.
3097, A Combinatorial Algorithm for Approximating The Optimal Transport in The Parallel and MPC Settings
Nathaniel Lahn; Sharath Raghvendra; Kaiyi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the first parallel combinatorial algorithm to find an additive $\varepsilon$-approximation of the OT distance.
3098, TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models
Pum Jun Kim; Yoojin Jang; Jisu Kim; Jaejun Yoo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a robust and reliable evaluation metric for generative models called Topological Precision and Recall (TopP&R, pronounced “topper”), which systematically estimates supports by retaining only topologically and statistically significant features with a certain level of confidence.
3099, Effective Targeted Attacks for Adversarial Self-Supervised Learning
Minseon Kim; Hyeonjeong Ha; Sooel Son; Sung Ju Hwang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we introduce an algorithm that selects the most confusing yet similar target example for a given instance based on entropy and similarity, and subsequently perturbs the given instance towards the selected target.
3100, Learning Invariant Representations with A Nonparametric Nadaraya-Watson Head
Alan Wang; Minh Nguyen; Mert Sabuncu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present a nonparametric strategy for learning invariant representations based on the recently-proposed Nadaraya-Watson (NW) head.
3101, Probabilistic Exponential Integrators
Nathanael Bosch; Philipp Hennig; Filip Tronarp;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, like standard solvers, they suffer performance penalties for certain stiff systems, where small steps are required not for reasons of numerical accuracy but for the sake of stability. This issue is greatly alleviated in semi-linear problems by the probabilistic exponential integrators developed in this paper.
3102, Implicit Convolutional Kernels for Steerable CNNs
Maksim Zhdanov; Nico Hoffmann; Gabriele Cesa;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose using implicit neural representation via multi-layer perceptrons (MLPs) to parameterize $G$-steerable kernels.
3103, Structured Federated Learning Through Clustered Additive Modeling
Jie Ma; Tianyi Zhou; Guodong Long; Jing Jiang; Chengqi Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, the static clustering assumption on data may not hold for dynamically changing models, which are sensitive to cluster imbalance/initialization or outliers. To address these challenges, we propose ''Clustered Additive Modeling (CAM)'', which applies a globally shared model $\Theta_g$ on top of the cluster-wise models $\Theta_{1:K}$, i.e., $y=h(x;\Theta_g)+f(x;\Theta_k)$ for clients of cluster-$k$.
3104, Revisiting Implicit Differentiation for Learning Problems in Optimal Control
Ming Xu; Timothy L. Molloy; Stephen Gould;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper revisits using the implicit function theorem (IFT) to differentiate through constrained discrete-time optimal control problems.
3105, Group Robust Classification Without Any Group Information
Christos Tsirigotis; Joao Monteiro; Pau Rodriguez; David Vazquez; Aaron Courville;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This study contends that current bias-unsupervised approaches to group robustness continue to rely on group information to achieve optimal performance.
3106, CoLLAT: On Adding Fine-grained Audio Understanding to Language Models Using Token-Level Locked-Language Tuning
Dadallage A R Silva; Spencer Whitehead; Christopher Lengerich; Hugh Leather;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: They also perform poorly when comprehending audio clips with multiple audio concepts. To bridge these gaps, we propose $CoLLAT$: $Co$ntrastive $L$ocked $L$anguage and $A$udio $T$uning.
3107, Gaussian Membership Inference Privacy
Tobias Leemann; Martin Pawelczyk; Gjergji Kasneci;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a new privacy notion called $f$-membership inference privacy ($f$-MIP) which addresses the significant utility loss of machine learning models trained under differential privacy (DP) constraints.
3108, Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model
Luning Sun; Xu Han; Han Gao; Jian-Xun Wang; Liping Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, there are challenges in predicting the solution in the original high-dimensional space. To bridge these gaps, we propose a framework with the regeneration learning paradigm for accurately predicting/generating fluid dynamics.
3109, Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model
Xi Yu; Xiang Gu; Haozhi Liu; Jian Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a Non-isotropic Gaussian Diffusion Model (NGDM) for image-to-image translation and image editing, which require translating or editing the source image while preserving the image regions irrelevant to the translation/editing task.
3110, A General Theory of Correct, Incorrect, and Extrinsic Equivariance
Dian Wang; Xupeng Zhu; Jung Yeon Park; Mingxi Jia; Guanang Su; Robert Platt; Robin Walters;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A missing piece in the equivariant learning literature is the analysis of equivariant networks when symmetry exists only partially in the domain. In this work, we present a general theory for such a situation.
3111, ViSt3D: Video Stylization with 3D CNN
Ayush Pande; Gaurav Sharma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To the best of our knowledge, we present the first approach to video stylization using 3D CNN directly, building upon insights from 2D image stylization.
3112, Discriminative Calibration
Yuling Yao; Justin Domke;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose to replace the marginal rank test with a flexible classification approach that learns test statistics from data.
3113, Mesogeos: A Multi-purpose Dataset for Data-driven Wildfire Modeling in The Mediterranean
Spyros Kondylatos; Ioannis Prapas; Gustau Camps-Valls; Ioannis Papoutsis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce Mesogeos, a large-scale multi-purpose dataset for wildfire modeling in the Mediterranean.
3114, Pgx: Hardware-accelerated Parallel Game Simulators for Reinforcement Learning
Sotetsu Koyamada; Shinri Okano; Soichiro Nishimori; Yu Murata; Keigo Habara; Haruka Kita; Shin Ishii;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators.
3115, ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design
Pascal Notin; Aaron Kollasch; Daniel Ritter; Lood van Niekerk; Nathan Rollins; Steffanie Paul; Ada Shaw; Ruben Weitzman; Jonathan Frazer; Mafalda Dias; Dinko Franceschi; Rose Orenbuch; Han Spinner; Yarin Gal; Debora Marks;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We devise a robust evaluation framework that combines metrics for both fitness prediction and design, factors in known limitations of the underlying experimental methods, and covers both zero-shot and supervised settings.
3116, Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
Abhinav Nippani; Dongyue Li; Haotian Ju; Haris Koutsopoulos; Hongyang Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume.
3117, Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations
Jungtaek Kim; Mingxuan Li; Oliver Hinder; Paul Leu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose benchmarks and systems for assessing the optical properties of photonic structures and their parametric designs.
3118, Abide By The Law and Follow The Flow: Conservation Laws for Gradient Flows
Sibylle Marcotte; Remi Gribonval; Gabriel Peyré;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: The purpose of this article is threefold. First, we rigorously expose the definition and basic properties of ``conservation laws'', which are maximal sets of independent quantities conserved during gradient flows of a given model (e.g. of a ReLU network with a given architecture) with any training data and any loss. Then we explain how to find the exact number of these quantities by performing finite-dimensional algebraic manipulations on the Lie algebra generated by the Jacobian of the model. Finally, we provide algorithms (implemented in SageMath) to: a) compute a family of polynomial laws; b) compute the number of (not necessarily polynomial) conservation laws.
3119, GPEX, A Framework For Interpreting Artificial Neural Networks
Amir Hossein Hosseini Akbarnejad; Gilbert Bigras; Nilanjan Ray;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we derive an evidence lower-bound that encourages the GP's posterior to match the ANN's output without any requirement on the ANN.
3120, Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning
Yu Wang; Zhun Zhong; Pengchong Qiao; Xuxin Cheng; Xiawu Zheng; Chang Liu; Nicu Sebe; Rongrong Ji; Jie Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take the initiative to explore and propose a uniformed framework, called Taxonomic context pIrors Discovering and Aligning ( TIDA ), which exploits the relationship of samples under various granularity.
3121, Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
Jinxin Liu; Hongyin Zhang; Zifeng Zhuang; Yachen Kang; Donglin Wang; Bin Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we decouple the iterative bi-level offline RL from the offline training phase, forming a non-iterative bi-level paradigm and avoiding the iterative error propagation over two levels.
3122, Template-free Articulated Neural Point Clouds for Reposable View Synthesis
Lukas Uzolas; Elmar Eisemann; Petr Kellnhofer;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present a novel method utilizing a point-based representation and Linear Blend Skinning (LBS) to jointly learn a Dynamic NeRF and an associated skeletal model from even sparse multi-view video.
3123, Mitigating Source Bias for Fairer Weak Supervision
Changho Shin; Sonia Cromp; Dyah Adila; Frederic Sala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Surprisingly, given everyday use and the potential for increased bias, weak supervision has not been studied from the point of view of fairness. We begin such a study, starting with the observation that even when a fair model can be built from a dataset with access to ground-truth labels, the corresponding dataset labeled via weak supervision can be arbitrarily unfair.
3124, GRD: A Generative Approach for Interpretable Reward Redistribution in Reinforcement Learning
Yudi Zhang; Yali Du; Biwei Huang; Ziyan Wang; Jun Wang; Meng Fang; Mykola Pechenizkiy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contribution of state and action from a causal perspective, resulting in an interpretable return decomposition.
3125, The CLIP Model Is Secretly An Image-to-Prompt Converter
Yuxuan Ding; Lingqiao Liu; Chunna Tian; Haoxuan Ding;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing methods have attempted to address this limitation by employing expensive training procedures involving millions of training samples for image-to-image generation. In contrast, this paper demonstrates that the CLIP model, as utilized in Stable Diffusion, inherently possesses the ability to instantaneously convert images into text prompts.
3126, Training Transitive and Commutative Multimodal Transformers with LoReTTa
Manuel Tran; Amal Lahiani; Yashin Dicente Cid; Fabian Theis; Tingying Peng; Eldad Klaiman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This makes it difficult to integrate and combine all modalities into a large pre-trained neural network. We introduce LoReTTa ($\textbf{L}$inking m$\textbf{O}$dalities with a t$\textbf{R}$ansitive and commutativ$\textbf{E}$ pre-$\textbf{T}$raining s$\textbf{T}$r$\textbf{A}$tegy) to address this understudied problem.
3127, A Unified Framework for Information-theoretic Generalization Bounds
Yifeng Chu; Maxim Raginsky;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a general methodology for deriving information-theoretic generalization bounds for learning algorithms.
3128, Neural Fields with Hard Constraints of Arbitrary Differential Order
Fangcheng Zhong; Kyle Fogarty; Param Hanji; Tianhao Wu; Alejandro Sztrajman; Andrew Spielberg; Andrea Tagliasacchi; Petra Bosilj; Cengiz Oztireli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the rich literature on meshless interpolation and its extension to spectral collocation methods in scientific computing,we develop a series of approaches for enforcing hard constraints on neural fields.
3129, ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation
Zhuo Chen; Laker Newhouse; Eddie Chen; Di Luo; Marin Soljacic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While representing quantum states with tensor networks and neural networks are the two state-of-the-art methods for approximate simulations, each has its own limitations in terms of expressivity and inductive bias. To address these challenges, we develop a novel architecture, Autoregressive Neural TensorNet (ANTN), which bridges tensor networks and autoregressive neural networks.
3130, ASPEN: Breaking Operator Barriers for Efficient Parallelization of Deep Neural Networks
Jongseok Park; Kyungmin Bin; Gibum Park; Sangtae Ha; Kyunghan Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we present ASPEN, a novel parallel computation solution for DNNs to break the synchronization barriers of operators and expose parallel computation opportunities across operators.
3131, Language Semantic Graph Guided Data-Efficient Learning
Wenxuan Ma; Shuang Li; lincan Cai; Jingxuan Kang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel perspective on data efficiency that involves exploiting the semantic information contained in the labels of the available data.
3132, A Computation and Communication Efficient Method for Distributed Nonconvex Problems in The Partial Participation Setting
Alexander Tyurin; Peter Richtarik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a new method that includes three key components of distributed optimization and federated learning: variance reduction of stochastic gradients, partial participation, and compressed communication.
3133, Safety Verification of Decision-Tree Policies in Continuous Time
Christian Schilling; Anna Lukina; Emir Demirović; Kim Larsen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents the first algorithm to directly verify decision-tree controlled system in continuous time.
3134, HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
Eric Nguyen; Michael Poli; Marjan Faizi; Armin Thomas; Michael Wornow; Callum Birch-Sykes; Stefano Massaroli; Aman Patel; Clayton Rabideau; Yoshua Bengio; Stefano Ermon; Christopher Ré; Stephen Baccus;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Leveraging Hyena’s new long-range capabilities, we present HyenaDNA, a genomic foundation model pretrained on the human reference genome with context lengths of up to 450,000 tokens at the single nucleotide-level – an up to 220x increase over previous dense attention-based models.
3135, On The Robustness of Mechanism Design Under Total Variation Distance
Anuran Makur; Marios Mertzanidis; Alexandros Psomas; Athina Terzoglou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of designing mechanisms when agents' valuation functions are drawn from unknown and correlated prior distributions.
3136, ESSEN: Improving Evolution State Estimation for Temporal Networks Using Von Neumann Entropy
Qiyao Huang; Yingyue Zhang; Zhihong Zhang; Edwin Hancock;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the existing methods often struggle to account for the time-varying nature of these network structures, hindering their performance when applied to networks with complex evolving states. To mitigate this problem, we propose a novel framework called ESSEN, an Evolution StateS awarE Network, to measure temporal network evolution using von Neumann entropy and thermodynamic temperature difference.
3137, Context-Aware PoseFormer: Single Image Beats Hundreds for 3D Human Pose Estimation
Qitao Zhao; Ce Zheng; Mengyuan Liu; Chen Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the \emph{readily available} intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors -- no finetuning on the 3D task is even needed.
3138, Causal De Finetti: On The Identification of Invariant Causal Structure in Exchangeable Data
Siyuan Guo; Viktor Toth; Bernhard Schölkopf; Ferenc Huszar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we observe that exchangeable data contains richer conditional independence structure than $i.i.d.\$ data, and show how the richer structure can be leveraged for causal discovery.
3139, P-Flow: A Fast and Data-Efficient Zero-Shot TTS Through Speech Prompting
Sungwon Kim; Kevin Shih; rohan badlani; Joao Felipe Santos; Evelina Bakhturina; Mikyas Desta; Rafael Valle; Sungroh Yoon; Bryan Catanzaro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our work proposes P-Flow, a fast and data-efficient zero-shot TTS model that uses speech prompts for speaker adaptation.
3140, SmoothHess: ReLU Network Feature Interactions Via Stein's Lemma
Max Torop; Aria Masoomi; Davin Hill; Kivanc Kose; Stratis Ioannidis; Jennifer Dy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose SmoothHess, a method of estimating second-order interactions through Stein's Lemma.
3141, Bayesian Nonparametric (non-)renewal Processes for Analyzing Neural Spike Train Variability
David Liu; Mate Lengyel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, currently, they only allow the instantaneous mean, but not the instantaneous variability, of responses to depend on covariates. To resolve this limitation, we propose a scalable Bayesian approach generalizing modulated renewal processes using sparse variational Gaussian processes.
3142, Personalized Dictionary Learning for Heterogeneous Datasets
Geyu Liang; Naichen Shi; Raed AL Kontar; Salar Fattahi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Challenges for PerDL not only are inherited from classical dictionary learning(DL), but also arise due to the unknown nature of the shared and unique features. In this paper, we rigorously formulate this problem and provide conditions under which the global and local dictionaries can be provably disentangled.
3143, Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation
Tingliang Feng; Hao Shi; Xueyang Liu; Wei Feng; Liang Wan; Yanlin Zhou; Di Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features.
3144, Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data
Vaidotas Simkus; Benjamin Rhodes; Michael Gutmann;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, in contrast to standard latent-variable models, parameter estimation with incomplete data often requires estimating exponentially-many conditional distributions of the missing variables, hence making standard VI methods intractable. We address this gap by introducing variational Gibbs inference (VGI), a new general-purpose method to estimate the parameters of statistical models from incomplete data.
3145, Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
Kamélia Daudel; Joe Benton; Yuyang Shi; Arnaud Doucet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we formalize and study the VR-IWAE bound, a generalization of the importance weighted auto-encoder (IWAE) bound.
3146, Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds
Didong Li; Wenpin Tang; Sudipto Banerjee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We focus on asymptotic behaviour for Gaussian processes constructed over compact Riemannian manifolds.
3147, Concentration Analysis of Multivariate Elliptic Diffusions
Lukas Trottner; Cathrine Aeckerle-Willems; Claudia Strauch;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We prove concentration inequalities and associated PAC bounds for both continuous- and discrete-time additive functionals for possibly unbounded functions of multivariate, nonreversible diffusion processes.
3148, Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic Under State Distribution Mismatch
Shangtong Zhang; Remi Tachet des Combes; Romain Laroche;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we establish the global optimality and convergence rate of an off-policy actor critic algorithm in the tabular setting without using density ratio to correct the discrepancy between the state distribution of the behavior policy and that of the target policy.
3149, MMD Aggregated Two-Sample Test
Antonin Schrab; Ilmun Kim; Mélisande Albert; Béatrice Laurent; Benjamin Guedj; Arthur Gretton;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose two novel nonparametric two-sample kernel tests based on the Maximum Mean Discrepancy (MMD).
3150, Graph Clustering with Graph Neural Networks
Anton Tsitsulin; John Palowitch; Bryan Perozzi; Emmanuel Müller;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate further by carefully designing a set of experiments to study different signal-to-noise scenarios both in graph structure and attribute data. To address these methods' poor performance in clustering, we introduce Deep Modularity Networks (DMoN), an unsupervised pooling method inspired by the modularity measure of clustering quality, and show how it tackles recovery of the challenging clustering structure of real-world graphs.
3151, SODA: Robust Training of Test-Time Data Adaptors
Zige Wang; Yonggang Zhang; Zhen Fang; Long Lan; Wenjing Yang; Bo Han;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We find that the issue directly stems from the unreliable estimation of the gradients used to optimize the data adaptor, which is inherently due to the unreliable nature of the pseudo-labels assigned to the test data. Based on this observation, we propose pseudo-label-robust data adaptation (SODA) to improve the performance of data adaptation.
3152, A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning
Nika Haghtalab; Michael Jordan; Eric Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide a unifying framework for the design and analysis of multi-calibrated predictors.
3153, Graph-Structured Gaussian Processes for Transferable Graph Learning
Jun Wu; Lisa Ainsworth; Andrew Leakey; Haixun Wang; Jingrui He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The major challenge of transferable graph learning is the distribution shift between source and target graphs induced by individual node attributes and complex graph structures. To solve this problem, in this paper, we propose a generic graph-structured Gaussian process framework (GraphGP) for adaptively transferring knowledge across graphs with either homophily or heterophily assumptions.
3154, Transformer As A Hippocampal Memory Consolidation Model Based on NMDAR-inspired Nonlinearity
Dong Kyum Kim; Jea Kwon; Meeyoung Cha; C. Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We find that NMDAR-like nonlinearity is essential for shifting short-term working memory into long-term reference memory in transformers, thus enhancing a process that resembles memory consolidation in the mammalian brain.
3155, Survival Instinct in Offline Reinforcement Learning
Anqi Li; Dipendra Misra; Andrey Kolobov; Ching-An Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel observation about the behavior of offline reinforcement learning (RL) algorithms: on many benchmark datasets, offline RL can produce well-performing and safe policies even when trained with wrong reward labels, such as those that are zero everywhere or are negatives of the true rewards.
3156, Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost
Yu-Jie Zhang; Masashi Sugiyama;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we provide an algorithm that enjoys joint statistical and computational efficiency for the logistic bandit problem.
3157, What Truly Matters in Trajectory Prediction for Autonomous Driving?
Haoran Wu; Tran Phong; Cunjun Yu; Panpan Cai; Sifa Zheng; David Hsu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, focusing solely on accuracy fails to address the demand for computational efficiency, which is critical for the real-time response required by the autonomous driving system. Therefore, in this paper, we demonstrate that an interactive, task-driven evaluation approach for trajectory prediction is crucial to reflect its efficacy for autonomous driving.
3158, Gradient Flossing: Improving Gradient Descent Through Dynamic Control of Jacobians
Rainer Engelken;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we propose gradient flossing, a novel approach to tackling gradient instability by pushing Lyapunov exponents of the forward dynamics towards zero during learning.
3159, Differentiable Sorting for Censored Time-to-event Data
Andre Vauvelle; Benjamin Wild; Roland Eils; Spiros Denaxas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite their potential, current differentiable sorting methods cannot account for censoring, a crucial aspect of many real-world datasets. We propose a novel method, Diffsurv, to overcome this limitation by extending differentiable sorting methods to handle censored tasks.
3160, BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery
Yashas Annadani; Nick Pawlowski; Joel Jennings; Stefan Bauer; Cheng Zhang; Wenbo Gong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite recent progress towards efficient posterior inference over DAGs, existing methods are either limited to variational inference on node permutation matrices for linear causal models, leading to compromised inference accuracy, or continuous relaxation of adjacency matrices constrained by a DAG regularizer, which cannot ensure resulting graphs are DAGs. In this work, we introduce a scalable Bayesian causal discovery framework based on stochastic gradient Markov Chain Monte Carlo (SG-MCMC) that overcomes these limitations.
3161, Simultaneous Embedding of Multiple Attractor Manifolds in A Recurrent Neural Network Using Constrained Gradient Optimization
Haggai Agmon; Yoram Burak;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consequently, population activity patterns exhibit systematic drifts towards one of these discrete minima, thereby degrading the stored memory over time. Here we show that it is possible to dramatically attenuate these detrimental interference effects by adjusting the synaptic weights.
3162, Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
Xiang Ji; Gen Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting.
3163, Partial Matrix Completion
Elad Hazan; Adam Tauman Kalai; Varun Kanade; Clara Mohri; Y. Jennifer Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel formulation of the problem as Partial Matrix Completion, where the objective is to complete a substantial subset of the entries with high confidence.
3164, LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction
Di Liu; Anastasis Stathopoulos; Qilong Zhangli; Yunhe Gao; Dimitris Metaxas;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose LEPARD, a framework that discovers semantically meaningful 3D parts and reconstructs 3D shapes in a part-based manner.
3165, Adaptive Recurrent Vision Performs Zero-shot Computation Scaling to Unseen Difficulty Levels
Vijay Veerabadran; Srinivas Ravishankar; Yuan Tang; Ritik Raina; Virginia de Sa;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, little work has been performed to assess whether such adaptive computation can also enable vision models to extrapolate solutions beyond their training distribution's difficulty level, with prior work focusing on very simple tasks. In this study, we investigate a critical functional role of such adaptive processing using recurrent neural networks: to dynamically scale computational resources conditional on input requirements that allow for zero-shot generalization to novel difficulty levels not seen during training using two challenging visual reasoning tasks: PathFinder and Mazes.
3166, Towards A Unified Analysis of Kernel-based Methods Under Covariate Shift
Xingdong Feng; Xin HE; Caixing Wang; Chao Wang; Jingnan Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite its practical importance in various learning problems, most of the existing methods only focus on some specific learning tasks and are not well validated theoretically and numerically. To tackle this problem, we propose a unified analysis of the general nonparametric methods in a reproducing kernel Hilbert space (RKHS) under covariate shift.
3167, Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on A Synthetic Task
Maya Okawa; Ekdeep S Lubana; Robert Dick; Hidenori Tanaka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: What are the reasons underlying this behavior? Which concepts does the model generally find difficult to compose to form novel data? To address these questions, we perform a controlled study of compositional generalization in conditional diffusion models in a synthetic setting, varying different attributes of the training data and measuring the model's ability to generate samples out-of-distribution.
3168, Suggesting Variable Order for Cylindrical Algebraic Decomposition Via Reinforcement Learning
Fuqi Jia; Yuhang Dong; Minghao Liu; Pei Huang; Feifei Ma; Jian Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes two Reinforcement Learning (RL) approaches combined with Graph Neural Networks (GNN) for Suggesting Variable Order (SVO).
3169, Model Spider: Learning to Rank Pre-Trained Models Efficiently
Yi-Kai Zhang; Ting-Ji Huang; Yao-Xiang Ding; De-Chuan Zhan; Han-Jia Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose Model Spider, which tokenizes both PTMs and tasks by summarizing their characteristics into vectors to enable efficient PTM selection.
3170, On The Power of SVD in Clustering Problems
Xinyu Mao; Jiapeng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It is an interesting question to understand the behavior of spectral steps in clustering problems. As an initial step (but not the final step) in this direction, this paper studies the power of vanilla-SVD algorithm in the stochastic block model (SBM).
3171, CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders
Anthony Fuller; Koreen Millard; James Green;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present CROMA: a framework that combines contrastive and reconstruction self-supervised objectives to learn rich unimodal and multimodal representations.
3172, FedGame: A Game-Theoretic Defense Against Backdoor Attacks in Federated Learning
Jinyuan Jia; Zhuowen Yuan; Dinuka Sahabandu; Luyao Niu; Arezoo Rajabi; Bhaskar Ramasubramanian; Bo Li; Radha Poovendran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on the analysis of our model, we design an interactive defense mechanism FedGame.
3173, E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning
Xiuhong Lin; Changjie Qiu; zhipeng cai; Siqi Shen; Yu Zang; Weiquan Liu; Xuesheng Bian; Matthias Müller; Cheng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose E2PNet, the first learning-based method for event-to-point cloud registration.
3174, End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
Alexandre Maraval; Matthieu Zimmer; Antoine Grosnit; Haitham Bou Ammar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures.
3175, Transformers Over Directed Acyclic Graphs
Yuankai Luo; Veronika Thost; Lei Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we study transformers over directed acyclic graphs (DAGs) and propose architecture adaptations tailored to DAGs: (1) An attention mechanism that is considerably more efficient than the regular quadratic complexity of transformers and at the same time faithfully captures the DAG structure, and (2) a positional encoding of the DAG's partial order, complementing the former.
3176, Efficient Robust Bayesian Optimization for Arbitrary Uncertain Inputs
Lin Yang; Junlong Lyu; Wenlong Lyu; Zhitang Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel robust Bayesian Optimization algorithm, AIRBO, which can effectively identify a robust optimum that performs consistently well under arbitrary input uncertainty.
3177, Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models
Yichao Cao; Qingfei Tang; Xiu Su; Song Chen; Shan You; Chang Xu; Xiaobo Lu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We conduct a deep analysis of the three hierarchical features inherent in visual HOI detectors and propose a method for high-level relation extraction aimed at VL foundation models, which we call HO prompt-based learning.
3178, Characterizing Scaling and Transfer Learning of Neural Networks for Scientific Machine Learning
Shashank Subramanian; Peter Harrington; Kurt Keutzer; Wahid Bhimji; Dmitriy Morozov; Michael Mahoney; Amir Gholami;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we study how pre-training could be used for scientific machine learning applications described by PDEs, and specifically in the context of transfer learning.
3179, Cross-links Matter for Link Prediction: Rethinking The Debiased GNN from A Data Perspective
Zihan Luo; Jianxun Lian; Hong Huang; Xiran Song; Xing Xie; Hai Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recently, the bias-related issues in GNN-based link prediction have raised widely spread concerns. In this paper, we emphasize the bias on links across different node clusters, which we call cross-links, after considering its significance in both easing information cocoons and preserving graph connectivity.
3180, Resilient Multiple Choice Learning: A Learned Scoring Scheme with Application to Audio Scene Analysis
Victor Letzelter; Mathieu Fontaine; Patrick Pérez; Gaël Richard; Slim Essid; Mickael Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Resilient Multiple Choice Learning (rMCL), an extension of the MCL approach for conditional distribution estimation in regression settings where multiple targets may be sampled for each training input.
3181, D-CIPHER: Discovery of Closed-form Partial Differential Equations
Krzysztof Kacprzyk; Zhaozhi Qian; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose D-CIPHER, which is robust to measurement artifacts and can uncover a new and very general class of differential equations.
3182, Rewiring Neurons in Non-Stationary Environments
Zhicheng Sun; Yadong Mu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In distinction to existing rewiring approaches that rely on pruning or dynamic routing, which may limit network capacity and plasticity, this work presents a novel rewiring scheme by permuting hidden neurons.
3183, Maximum State Entropy Exploration Using Predecessor and Successor Representations
Arnav Kumar Jain; Lucas Lehnert; Irina Rish; Glen Berseth;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose $\eta\psi$-Learning, a method to learn efficient exploratory policies by conditioning on past episodic experience to make the next exploratory move.
3184, CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels
Wanxing Chang; Ye Shi; Jingya Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel optimal transport (OT) formulation, called Curriculum and Structure-aware Optimal Transport (CSOT).
3185, Towards Efficient Pre-Trained Language Model Via Feature Correlation Distillation
Kun Huang; Xin Guo; Meng Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, our analysis indicates that the different relations within self-attention, as adopted in other works, involves more computation complexities and can easily be constrained by the number of heads, potentially leading to suboptimal solutions. To address these issues, we propose a novel approach that builds relationships directly from output features.
3186, Covariance-adaptive Best Arm Identification
El Mehdi Saad; Gilles Blanchard; Nicolas Verzelen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce new algorithms that adapt to the unknown covariance of the arms and demonstrate through theoretical guarantees that substantial improvement can be achieved over the standard setting.
3187, Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design
Matthew T Jackson; Minqi Jiang; Jack Parker-Holder; Risto Vuorio; Chris Lu; Greg Farquhar; Shimon Whiteson; Jakob Foerster;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite impressive initial results from algorithms such as Learned Policy Gradient (LPG), there remains a generalization gap when these algorithms are applied to unseen environments. In this work, we examine how characteristics of the meta-training distribution impact the generalization performance of these algorithms.
3188, Continual Learning for Instruction Following from Realtime Feedback
Alane Suhr; Yoav Artzi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose and deploy an approach to continually train an instruction-following agent from feedback provided by users during collaborative interactions.
3189, On The Identifiability and Interpretability of Gaussian Process Models
Jiawen Chen; Wancen Mu; Yun Li; Didong Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we critically examine the prevalent practice of using additive mixtures of Mat\'ern kernels in single-output Gaussian process (GP) models and explore the properties of multiplicative mixtures of Mat\'ern kernels for multi-output GP models.
3190, Revisit Weakly-Supervised Audio-Visual Video Parsing from The Language Perspective
Yingying Fan; Yu Wu; Yutian Lin; Bo Du;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We focus on the weakly-supervised audio-visual video parsing task (AVVP), which aims to identify and locate all the events in audio/visual modalities.
3191, Sequential Memory with Temporal Predictive Coding
Mufeng Tang; Helen Barron; Rafal Bogacz;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Inspired by neuroscience theories and recent successes in applying predictive coding (PC) to \emph{static} memory tasks, in this work we propose a novel PC-based model for \emph{sequential} memory, called \emph{temporal predictive coding} (tPC).
3192, Data Market Design Through Deep Learning
Sai Srivatsa Ravindranath; Yanchen Jiang; David Parkes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce the use of deep learning for the automated design of data markets to expand the frontiers of what can be achieved.
3193, PRODIGY: Enabling In-context Learning Over Graphs
Qian Huang; Hongyu Ren; Peng Chen; Gregor Kržmanc; Daniel Zeng; Percy Liang; Jure Leskovec;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we develop \textbf{Pr}etraining \textbf{O}ver \textbf{D}iverse \textbf{I}n-Context \textbf{G}raph S\textbf{y}stems (PRODIGY), the first pretraining framework that enables in-context learning over graphs.
3194, Optimizing Over Trained GNNs Via Symmetry Breaking
Shiqiang Zhang; Juan Campos; Christian Feldmann; David Walz; Frederik Sandfort; Miriam Mathea; Calvin Tsay; Ruth Misener;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper formulates and solves optimization problems constrained by trained graph neural networks (GNNs).
3195, Online PCA in Converging Self-consistent Field Equations
Xihan Li; Xiang Chen; Rasul Tutunov; Haitham Bou Ammar; Jun Wang; Lei Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Traditional fixed-point iteration methods for solving such equations suffer from non-convergence issues. In this work, we present a novel perspective on such SCF equations as a principal component analysis (PCA) for non-stationary time series, in which a distribution and its own top principal components are mutually updated over time, and the equilibrium state of the model corresponds to the solution of the SCF equations.
3196, Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Daogao Liu; Arun Ganesh; Sewoong Oh; Abhradeep Guha Thakurta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building upon the previous variance-reduced algorithm SpiderBoost, we propose a novel framework that employs two types of gradient oracles: one that estimates the gradient at a single point and a more cost-effective option that calculates the gradient difference between two points.
3197, Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery
Sarah Rastegar; Hazel Doughty; Cees Snoek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we conceptualize a \textit{category} through the lens of optimization, viewing it as an optimal solution to a well-defined problem.
3198, Focus Your Attention When Few-Shot Classification
Haoqing Wang; Shibo Jie; Zhihong Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Since many pre-trained vision transformers emerge and provide strong representation for various downstream tasks, we aim to adapt them to few-shot image classification tasks in this work.
3199, False Discovery Proportion Control for Aggregated Knockoffs
Alexandre Blain; Bertrand Thirion; Olivier Grisel; Pierre Neuvial;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a new method, KOPI, that controls the proportion of false discoveries for Knockoff-based inference.
3200, Matrix Compression Via Randomized Low Rank and Low Precision Factorization
Rajarshi Saha; Varun Srivastava; Mert Pilanci;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although prohibitively large, such matrices are often approximately low rank. We propose an algorithm that exploits this structure to obtain a low rank decomposition of any matrix $\mathbf{A}$ as $\mathbf{A} = \mathbf{L}\mathbf{R}$, where $\mathbf{L}$ and $\mathbf{R}$ are the low rank factors.
3201, Resilient Constrained Learning
Ignacio Hounie; Alejandro Ribeiro; Luiz F. O. Chamon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a constrained learning approach that adapts the requirements while simultaneously solving the learning task.
3202, Macro Placement By Wire-Mask-Guided Black-Box Optimization
Yunqi Shi; Ke Xue; Song Lei; Chao Qian;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a new black-box optimization (BBO) framework (called WireMask-BBO) for macro placement, by using a wire-mask-guided greedy procedure for objective evaluation.
3203, Reliable Off-Policy Learning for Dosage Combinations
Jonas Schweisthal; Dennis Frauen; Valentyn Melnychuk; Stefan Feuerriegel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel method for reliable off-policy learning for dosage combinations.
3204, Kernelized Cumulants: Beyond Kernel Mean Embeddings
Patric Bonnier; Harald Oberhauser; Zoltan Szabo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In $\mathbb{R}^d$, it is well-known that cumulants provide an alternative to moments that can achieve the same goals with numerous benefits such as lower variance estimators. In this paper we extend cumulants to reproducing kernel Hilbert spaces (RKHS) using tools from tensor algebras and show that they are computationally tractable by a kernel trick.
3205, Reduced Policy Optimization for Continuous Control with Hard Constraints
Shutong Ding; Jingya Wang; Yali Du; Ye Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by the generalized reduced gradient (GRG) algorithm, a classical constrained optimization technique, we propose a reduced policy optimization (RPO) algorithm that combines RL with GRG to address general hard constraints.
3206, Learning Pareto-Optimal Policies for Multi-Objective Joint Distribution
Xin-Qiang Cai; Pushi Zhang; Li Zhao; Jiang Bian; Masashi Sugiyama; Ashley Llorens;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, current MORL algorithms fail to account for distributional preferences over the multi-variate returns, which are particularly important in real-world scenarios such as autonomous driving. To address this issue, we extend the concept of Pareto-optimality in MORL into distributional Pareto-optimality, which captures the optimality of return distributions, rather than the expectations.
3207, Learning Cuts Via Enumeration Oracles
Daniel Thuerck; Boro Sofranac; Marc E Pfetsch; Sebastian Pokutta;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel generic approach for learning the facets of the underlying polyhedron by accessing it implicitly via an enumeration oracle in a reduced dimension.
3208, Multimodal Deep Learning Model Unveils Behavioral Dynamics of V1 Activity in Freely Moving Mice
Aiwen Xu; Yuchen Hou; Cristopher Niell; Michael Beyeler;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Consequently, it is still unknown how natural visual input and different behavioral variables may integrate over time to generate responses in primary visual cortex (V1). To address this, we introduce a multimodal recurrent neural network that integrates gaze-contingent visual input with behavioral and temporal dynamics to explain V1 activity in freely moving mice.
3209, Accountable Batched Control with Decision Corpus
Hao Sun; Alihan Hüyük; Daniel Jarrett; Mihaela van der Schaar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces the Accountable Batched Controller (ABC) that employs the batched dataset as the Decision Corpus and performs accountable control based on a tailored selection of examples, referred to as the Corpus Subset.
3210, A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks
Vignesh Kothapalli; Tom Tirer; Joan Bruna;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we focus on node-wise classification, illustrated with community detection on stochastic block model graphs, and explore the feature evolution through the lens of the Neural Collapse (NC) phenomenon.
3211, Learning From Biased Soft Labels
Hua Yuan; Yu Shi; Ning Xu; Xu Yang; Xin Geng; Yong Rui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present two indicators to measure the effectiveness of the soft labels.
3212, On Certified Generalization in Structured Prediction
Bastian Boll; Christoph Schnörr;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel PAC-Bayesian risk bound for structured prediction wherein the rate of generalization scales not only with the number of structured examples but also with their size.
3213, Team-PSRO for Learning Approximate TMECor in Large Team Games Via Cooperative Reinforcement Learning
Stephen McAleer; Gabriele Farina; Gaoyue Zhou; Mingzhi Wang; Yaodong Yang; Tuomas Sandholm;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we introduce two algorithms: Team-PSRO, an extension of PSRO from two-player games to team games, and Team-PSRO Mix-and-Match which improves upon Team PSRO by better using population policies.
3214, Deep Neural Collapse Is Provably Optimal for The Deep Unconstrained Features Model
Peter Súkeník; Marco Mondelli; Christoph Lampert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our key technical contribution is to show that, in a deep unconstrained features model, the unique global optimum for binary classification exhibits all the properties typical of DNC.
3215, Latent Density Models for Uncertainty Categorization
Hao Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a framework for categorizing uncertain examples flagged by UQ methods.
3216, Slot-guided Volumetric Object Radiance Fields
DI QI; Tong Yang; Xiangyu Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel framework for 3D object-centric representation learning.
3217, Improving Self-supervised Molecular Representation Learning Using Persistent Homology
Yuankai Luo; Lei Shi; Veronika Thost;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we study SSL based on persistent homology (PH), a mathematical tool for modeling topological features of data that persist across multiple scales.
3218, Egocentric Planning for Scalable Embodied Task Achievement
Xiatoian Liu; Hector Palacios; Christian Muise;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present Egocentric Planning, an innovative approach that combines symbolic planning and Object-oriented POMDP to solve tasks in complex environments, harnessing existing models for visual perception and natural language processing.
3219, ConRad: Image Constrained Radiance Fields for 3D Generation from A Single Image
Senthil Purushwalkam; Nikhil Naik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel method for reconstructing 3D objects from a single RGB image.
3220, Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression
Youngsoo Baek; Samuel Berchuck; Sayan Mukherjee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we compare and contrast the behavior of the posterior predictive distribution to the risk of the the maximum a posteriori estimator for the random features regression model in the overparameterized regime.
3221, RegBN: Batch Normalization of Multimodal Data with Regularization
Morteza Ghahremani Boozandani; Christian Wachinger;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces a novel approach for the normalization of multimodal data, called RegBN, that incorporates regularization.
3222, Transformers Learn Through Gradual Rank Increase
Emmanuel Abbe; Samy Bengio; Enric Boix-Adsera; Etai Littwin; Joshua Susskind;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We identify incremental learning dynamics in transformers, where the difference between trained and initial weights progressively increases in rank.
3223, Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks
Mingze Wang; Chao Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we conduct a complete theoretical characterization of the training process of a two-layer ReLU network trained by Gradient Flow on a linearly separable data.
3224, Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds
Jihun Yun; Eunho Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce Riemannian SAM by generalizing conventional Euclidean SAM to Riemannian manifolds.
3225, CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes
Xiaohan Wang; Yuehu Liu; Xinhang Song; Beibei Wang; Shuqiang Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a causal diagram of InterNav clarifying the confounding bias caused by obstacles.
3226, Contrastive Training of Complex-Valued Autoencoders for Object Discovery
Aleksandar Stanić; Anand Gopalakrishnan; Kazuki Irie; Jürgen Schmidhuber;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we introduce architectural modifications and a novel contrastive learning method that greatly improve the state-of-the-art synchrony-based model.
3227, The Noise Level in Linear Regression with Dependent Data
Ingvar Ziemann; Stephen Tu; George J. Pappas; Nikolai Matni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Up to constant factors, our analysis correctly recovers the variance term predicted by the Central Limit Theorem---the noise level of the problem---and thus exhibits graceful degradation as we introduce misspecification.
3228, K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing
Shuai Li; Yingjie Zhang; Hongtu Zhu; Christina Wang; Hai Shu; Ziqi Chen; Zhuoran Sun; Yanfeng Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Conditional independence (CI) testing is a fundamental task in statistics and machine learning, but its effectiveness is hindered by the challenges posed by high-dimensional conditioning variables and limited data samples. This article introduces a novel testing approach to address these challenges and enhance control of the type I error while achieving high power under alternative hypotheses.
3229, Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning
Yang Yang; Yuxuan Zhang; XIN SONG; Yi Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, concentrating solely on selecting pseudo-ID instances may cause the training imbalance of the ID classifier and OOD detector. To address this issue, we propose a simple yet effective sampling scheme, dubbed Progressive Active Learning (PAL).
3230, Causal Discovery from Subsampled Time Series with Proxy Variables
Mingzhou Liu; Xinwei Sun; Lingjing Hu; Yizhou Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a constraint-based algorithm that can identify the entire causal structure from subsampled time series, without any parametric constraint.
3231, Robust Data Pruning Under Label Noise Via Maximizing Re-labeling Accuracy
Dongmin Park; Seola Choi; Doyoung Kim; Hwanjun Song; Jae-Gil Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we formalize the problem of data pruning with Re-labeling.
3232, Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
Abhin Shah; Karthikeyan Shanmugam; Murat Kocaoglu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we provide testable conditional independence statements to compute the causal effect using front-door-like adjustment without knowing the graph under limited structural side information.
3233, Efficient Bayesian Learning Curve Extrapolation Using Prior-Data Fitted Networks
Steven Adriaensen; Herilalaina Rakotoarison; Samuel Müller; Frank Hutter;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we argue that, while the inherent uncertainty in the extrapolation of learning curves warrants a Bayesian approach, existing methods are (i) overly restrictive, and/or (ii) computationally expensive.
3234, Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers
Zixuan Jiang; Jiaqi Gu; Hanqing Zhu; David Pan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: By removing the inherent redundant mean information in the main branch of Pre-LN Transformers, we can reduce LayerNorm to RMSNorm, achieving higher efficiency.
3235, Aligning Gradient and Hessian for Neural Signed Distance Function
Ruian Wang; Zixiong Wang; Shiqing Xin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose to learn the SDF directly from point clouds without normals motivated by the key observation that the alignment between the gradient and the Hessian of the SDF allows for more effective control over the direction of the gradients, making up for the weakness of only regularizing the gradient norm.
3236, Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
Zhanpeng Zhou; Yongyi Yang; Xiaojiang Yang; Junchi Yan; Wei Hu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a stronger notion of linear connectivity, Layerwise Linear Feature Connectivity (LLFC), which says that the feature maps of every layer in different trained networks are also linearly connected.
3237, Adversarial Training from Mean Field Perspective
Soichiro Kumano; Hiroshi Kera; Toshihiko Yamasaki;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we present the first theoretical analysis of adversarial training in random deep neural networks without any assumptions on data distributions.
3238, When Can Linear Learners Be Robust to Indiscriminate Poisoning Attacks?
Fnu Suya; Xiao Zhang; Yuan Tian; David Evans;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error.
3239, Distribution-Free Model-Agnostic Regression Calibration Via Nonparametric Methods
Shang Liu; Zhongze Cai; Xiaocheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we consider the uncertainty quantification problem for regression models.
3240, Sample-efficient Multi-objective Molecular Optimization with GFlowNets
Yiheng Zhu; Jialu Wu; Chaowen Hu; Jiahuan Yan; kim hsieh; Tingjun Hou; Jian Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Computational methods have achieved initial success but still struggle with considering diversity in both objective and search space. To fill this gap, we propose a multi-objective Bayesian optimization (MOBO) algorithm leveraging the hypernetwork-based GFlowNets (HN-GFN) as an acquisition function optimizer, with the purpose of sampling a diverse batch of candidate molecular graphs from an approximate Pareto front.
3241, Language-driven Scene Synthesis Using Multi-conditional Diffusion Model
An Dinh Vuong; Minh Nhat VU; Toan Nguyen; Baoru Huang; Dzung Nguyen; Thieu Vo; Anh Nguyen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a language-driven scene synthesis task, which is a new task that integrates text prompts, human motion, and existing objects for scene synthesis.
3242, Learning Curves for Deep Structured Gaussian Feature Models
Jacob Zavatone-Veth; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we derive learning curves for models with many layers of structured Gaussian features.
3243, Theoretically Modeling Client Data Divergence for Federated Natural Language Backdoor Defense
Zhiyuan Zhang; Deli Chen; Hao Zhou; Fandong Meng; Jie Zhou; Xu Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The main reason is that, although text backdoor patterns are obvious at the underlying dataset level, they are usually hidden at the parameter level, since injecting backdoors into texts with discrete feature space has less impact on the statistics of the model parameters. To settle this issue, we propose to identify backdoor clients by explicitly modeling the data divergence among clients in federated NLP systems.
3244, Parallel Submodular Function Minimization
Deeparnab Chakrabarty; Andrei Graur; Haotian Jiang; Aaron Sidford;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Interestingly, to obtain our second result we give the first highly-parallel algorithm for minimizing $\ell_\infty$-Lipschitz functions over the hypercube, which achieves near-optimal parallel complexity for constant accuracy.
3245, Why Models Take Shortcuts When Roads Are Perfect: Understanding and Mitigating Shortcut Learning in Tasks with Perfect Stable Features
Aahlad Manas Puli; Lily Zhang; Yoav Wald; Rajesh Ranganath;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, models trained in the typical way by minimizing log-loss using gradient descent, which we call default-ERM, should utilize the shortcut.
3246, Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser
Yung-Hsuan Lai; Yen-Chun Chen; Frank Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Such weak video-level labels only tell what events happen without knowing the modality they are perceived (audio, visual, or both). To enhance learning in this challenging setting, we incorporate large-scale contrastively pre-trained models as the modality teachers.
3247, Inferring Hybrid Neural Fluid Fields from Videos
Hong-Xing Yu; Yang Zheng; Yuan Gao; Yitong Deng; Bo Zhu; Jiajun Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The challenge is further pronounced by the turbulent nature of fluid flows, which calls for properly designed fluid velocity representations. To address these challenges, we propose \modelfull (\model), a neural approach to jointly infer fluid density and velocity fields.
3248, UE4-NeRF:Neural Radiant Field for Real-Time Rendering of Large-Scale Scene
Jiaming Gu; Minchao Jiang; Hongsheng Li; Xiaoyuan Lu; Guangming Zhu; Syed Afaq Ali Shah; Liang Zhang; Mohammed Bennamoun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, its real-time rendering capability, especially for interactive real-time rendering of large-scale scenes, still has significant limitations. To address these challenges, in this paper, we propose a novel neural rendering system called UE4-NeRF, specifically designed for real-time rendering of large-scale scenes.
3249, Sample Complexity of Forecast Aggregation
Yiling Chen; Tao Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a Bayesian forecast aggregation model where $n$ experts, after observing private signals about an unknown binary event, report their posterior beliefs about the event to a principal, who then aggregates the reports into a single prediction for the event.
3250, Strategic Stability Under Regularized Learning in Games
Victor Boone; Panayotis Mertikopoulos;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we examine the long-run behavior of regularized, no-regret learning in finite N-player games.
3251, Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
Eshaan Nichani; Alex Damian; Jason Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we show that three-layer neural networks have provably richer feature learning capabilities than two-layer networks.
3252, Fair Allocation of Combinatorial Tasks: Beyond Additive Costs
Bo Li; Fangxiao Wang; Yu Zhou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the maximin share (MMS) fair allocation of $m$ indivisible tasks to $n$ agents who have costs for completing the assigned tasks.
3253, SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities
Hugues Van Assel; Titouan Vayer; Rémi Flamary; Nicolas Courty;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we uncover a novel characterization of EA as an optimal transport problem, allowing a natural symmetrization that can be computed efficiently using dual ascent.
3254, Learning Domain-Aware Detection Head with Prompt Tuning
Haochen Li; Rui Zhang; Hantao Yao; Xinkai Song; Yifan Hao; Yongwei Zhao; Ling Li; Yunji Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Inspired by the high generalization of vision-language models (VLMs), applying a VLM as the robust detection backbone following a domain-aware detection head is a reasonable way to learn the discriminative detector for each domain, rather than reducing the domain bias in traditional methods. To achieve the above issue, we thus propose a novel DAOD framework named Domain-Aware detection head with Prompt tuning (DA-Pro), which applies the learnable domain-adaptive prompt to generate the dynamic detection head for each domain.
3255, Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models
wenqiang wang; Chongyang Du; Tao Wang; Kaihao Zhang; Wenhan Luo; Lin Ma; Wei Liu; Xiaochun Cao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we for the first time in the community propose a novel mode of textual attack, punctuation-level attack.
3256, Towards Personalized Federated Learning Via Heterogeneous Model Reassembly
Jiaqi Wang; Xingyi Yang; Suhan Cui; Liwei Che; Lingjuan Lyu; Dongkuan (DK) Xu; Fenglong Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneous model reassembly to achieve personalized federated learning.
3257, Learning Adaptive Tensorial Density Fields for Clean Cryo-EM Reconstruction
Yuanhao Wang; Ramzi Idoughi; Wolfgang Heidrich;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a novel learning-based framework for reconstructing 3D structures from tilt-series cryo-Electron Microscopy (cryo-EM) data.
3258, Metropolis Sampling for Constrained Diffusion Models
Nic Fishman; Leo Klarner; Emile Mathieu; Michael Hutchinson; Valentin De Bortoli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce an alternative simple noising scheme based on rejection sampling that affords substantial gains in computational efficiency and empirical performance compared to the earlier samplers.
3259, PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization
Jiancong Xiao; Ruoyu Sun; Zhi-Quan Luo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing attempts heavily rely on additional strong assumptions, leading to loose bounds. In this paper, we address this issue and provide a spectrally-normalized robust generalization bound for DNNs.
3260, Minimum-Risk Recalibration of Classifiers
Zeyu Sun; Dogyoon Song; Alfred Hero;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce the concept of minimum-risk recalibration within the framework of mean-squared-error (MSE) decomposition, offering a principled approach for evaluating and recalibrating probabilistic classifiers.
3261, Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
Liang Zhang; Junchi YANG; Amin Karbasi; Niao He;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Previous work suggests that first-order methods would need to trade-off convergence rate (gradient complexity) for better reproducibility. In this work, we challenge this perception and demonstrate that both optimal reproducibility and near-optimal convergence guarantees can be achieved for smooth convex minimization and smooth convex-concave minimax problems under various error-prone oracle settings.
3262, Structured Voronoi Sampling
Afra Amini; Li Du; Ryan Cotterell;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods.
3263, Compositional Sculpting of Iterative Generative Processes
Timur Garipov; Sebastiaan De Peuter; Ge Yang; Vikas Garg; Samuel Kaski; Tommi Jaakkola;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We address composition of iterative generative processes: GFlowNets and diffusion models.
3264, Direct Training of SNN Using Local Zeroth Order Method
Bhaskar Mukhoty; Velibor Bojkovic; Xiaohan Zhao; William de Vazelhes; Giulia De Masi; Huan Xiong; Bin Gu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To circumvent this problem, the surrogate method employs a differentiable approximation of the Heaviside function in the backward pass, while the forward pass continues to use the Heaviside function as the spiking function. In this paper, we propose the zeroth order technique at the local, neuron level in training SNNs, motivated both by its regularizing and potential energy-efficient effects.
3265, Language Quantized AutoEncoders for Data Efficient Text-Image Alignment
Hao Liu; Wilson Yan; Pieter Abbeel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While prior works have largely connected image to text through pretraining or fine-tuning, learning such alignments are generally costly due to a combination of curating massive datasets and large computational burdens. In order to resolve these limitations, we propose a simple yet effective approach called \textbf{L}anguage-\textbf{Q}uantized \textbf{A}uto\textbf{E}ncoder (LQAE), a modification of VQ-VAE that learns to align text-image data in an \emph{unsupervised} manner by leveraging pretrained language model denoisers (\eg BERT).
3266, Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems
Fiona Lippert; Bart Kranstauber; Emiel van Loon; Patrick Forré;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building on recent methods that combine ideas from deep learning with principled inference in Gaussian Markov random fields (GMRF), we reformulate graph-structured state-space models as Deep GMRFs defined by simple spatial and temporal graph layers.
3267, Probabilistic Inverse Optimal Control for Non-linear Partially Observable Systems Disentangles Perceptual Uncertainty and Behavioral Costs
Dominik Straub; Matthias Schultheis; Heinz Koeppl; Constantin Rothkopf;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we introduce a probabilistic approach to inverse optimal control for partially-observable stochastic non-linear systems with unobserved action signals, which unifies previous approaches to inverse optimal control with maximum causal entropy formulations.
3268, Deep Patch Visual Odometry
Zachary Teed; Lahav Lipson; Jia Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose Deep Patch Visual Odometry (DPVO), a new deep learning system for monocular Visual Odometry (VO).
3269, Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning
Berken Utku Demirel; Christian Holz;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a novel data augmentation method for time-series tasks that aims to connect intra-class samples together, and thereby find order in the latent space.
3270, Online Adaptive Policy Selection in Time-Varying Systems: No-Regret Via Contractive Perturbations
Yiheng Lin; James Preiss; Emile Anand; Yingying Li; Yisong Yue; Adam Wierman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop the Gradient-based Adaptive Policy Selection (GAPS) algorithm together with a general analytical framework for online policy selection via online optimization.
3271, Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms
Kai Han; He Huang; Shuang Cui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose TripleEagle, a novel algorithmic framework for designing BFMs, based on which we present several simple yet effective BFMs that achieve better approximation ratios than the state-of-the-art work.
3272, Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation
Yuxuan Song; Jingjing Gong; Minkai Xu; Ziyao Cao; Yanyan Lan; Stefano Ermon; Hao Zhou; Wei-Ying Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics.
3273, Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies
Hanna Ziesche; Leonel Rozo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We instead propose to leverage the structure of probabilistic policies by casting the policy optimization as an optimal transport problem.
3274, Computing Optimal Equilibria and Mechanisms Via Learning in Zero-Sum Extensive-Form Games
Brian Zhang; Gabriele Farina; Ioannis Anagnostides; Federico Cacciamani; Stephen McAleer; Andreas Haupt; Andrea Celli; Nicola Gatti; Vincent Conitzer; Tuomas Sandholm;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a new approach for computing optimal equilibria via learning in games.
3275, Error Bounds for Score Matching Causal Discovery
Zhenyu Zhu; Francesco Locatello; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper provides statistical sample complexity bounds for score-matching and its applications in causal discovery.
3276, Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
Zunzhi You; Daochang Liu; Bohyung Han; Chang Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The MIM pretrained models, like most deep neural network methods, are still vulnerable to adversarial attacks, limiting their practical application, and this issue has received little research attention. In this paper, we investigate how this powerful self-supervised learning paradigm can provide adversarial robustness to downstream classifiers.
3277, Bayesian Active Causal Discovery with Multi-Fidelity Experiments
Zeyu Zhang; Chaozhuo Li; Xu Chen; Xing Xie;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this problem also brings more challenges because the model has to make trade-offs to select cheaper oracles which are sufficiently informative to reveal the real causal graph. In this paper, we formally define the task of multi-fidelity active causal discovery, and design a probabilistic model for solving this problem.
3278, Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces
Odelia Melamed; Gilad Yehudai; Gal Vardi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we focus on two-layer neural networks trained using data which lie on a low dimensional linear subspace.
3279, Differentiable Clustering with Perturbed Spanning Forests
Lawrence Stewart; Francis Bach; Felipe Llinares-Lopez; Quentin Berthet;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a differentiable clustering method based on minimum-weight spanning forests, a variant of spanning trees with several connected components.
3280, Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalabiliy
Jishnu Ray Chowdhury; Cornelia Caragea;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel framework---Recursion in Recursion (RIR) to strike a balance between the two sides - getting some of the benefits from both worlds.
3281, PFedBreD: Personalized Prior for Reactivating The Overlooked Information in Federated Learning
Mingjia Shi; Yuhao Zhou; Qing Ye; Kai Wang; Huaizheng Zhang; Shudong Huang; Jiancheng Lv;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel scheme to inject personalized prior knowledge into the global model in each client, which attempts to mitigate the introduced incomplete information problem in PFL.
3282, StateMask: Explaining Deep Reinforcement Learning Through State Mask
Zelei Cheng; Xian Wu; Jiahao Yu; Wenbo Guo; Wenhai Sun; Xinyu Xing;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Most existing methods explain why an agent takes individual actions rather than pinpointing the critical steps to its final reward. To fill this gap, we propose StateMask, a novel method to identify the states most critical to the agent's final reward.
3283, Triangulation Residual Loss for Data-efficient 3D Pose Estimation
Jiachen Zhao; Tao Yu; Liang An; Yipeng Huang; Fang Deng; Qionghai Dai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents Triangulation Residual loss (TR loss) for multiview 3D human/animal pose estimation in a data-efficient manner.
3284, Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints
Dohyeong Kim; Kyungjae Lee; Songhwai Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a trust region-based safe RL algorithm for multiple constraints called a safe distributional actor-critic (SDAC).
3285, Sampling Weights of Deep Neural Networks
Erik L Bolager; Iryna Burak; Chinmay Datar; Qing Sun; Felix Dietrich;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We introduce a probability distribution for weights and biases of fully-connected neural networks.
3286, DynPoint: Dynamic Neural Point For View Synthesis
Kaichen Zhou; Andrew Markham; Yiyuan Yang; Kai Lu; Sangyun Shin; Jia-Xing Zhong; Niki Trigoni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, existing algorithms face difficulties when dealing with uncontrolled or lengthy scenarios, and require extensive training time specific to each new scenario. To tackle these limitations, we propose DynPoint, an algorithm designed to facilitate the rapid synthesis of novel views for unconstrained monocular videos.
3287, $p$-value Adjustment for Monotonous, Unbiased, and Fast Clustering Comparison
Kai Klede; Thomas Altstidl; Dario Zanca; Bjoern Eskofier;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce the $p$-value adjusted Rand Index ($\operatorname{PMI}_2$), the first cluster comparison method that is type II unbiased and provably monotonous.
3288, Affinity-Aware Graph Networks
Ameya Velingker; Ali Sinop; Ira Ktena; Petar Veličković; Sreenivas Gollapudi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we explore the use of affinity measures as features in graph neural networks, in particular measures arising from random walks, including effective resistance, hitting and commute times.
3289, Privately Counting Unique Elements
Thomas Steinke; Alexander Knop;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the problem of counting the number of unique elements in a dataset subject to the constraint of differential privacy.
3290, Supply-Side Equilibria in Recommender Systems
Meena Jagadeesan; Nikhil Garg; Jacob Steinhardt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we investigate the resulting supply-side equilibria in personalized content recommender systems.
3291, Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
Hassan Akbari; Dan Kondratyuk; Yin Cui; Rachel Hornung; Huisheng Wang; Hartwig Adam;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Integrated Multimodal Perception (IMP), a simple and scalable multimodal multi-task training and modeling approach.
3292, Curriculum Learning with Infant Egocentric Videos
Saber Sheybani; Himanshu Hansaria; Justin Wood; Linda Smith; Zoran Tiganj;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Is this change in the properties of the visual inputs beneficial or even critical for the proper development of the visual system? To address this question, we used video recordings from infants wearing head-mounted cameras to pre-train state-of-the-art self-supervised video autoencoders.
3293, Learning and Processing The Ordinal Information of Temporal Sequences in Recurrent Neural Circuits
xiaolong zou; Zhikun Chu; Qinghai Guo; Jie Cheng; Bo Ho; Si Wu; Yuanyuan Mi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Using a transfer learning task, we demonstrate that the reuse of a temporal order template facilitates the acquisition of new temporal sequences of the same or similar ordinal structure.
3294, From ViT Features to Training-free Video Object Segmentation Via Streaming-data Mixture Models
Roy Uziel; Or Dinari; Oren Freifeld;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we present a training-free solution, with a low-memory footprint, that yields state-of-the-art results.
3295, Towards Robust and Generalizable Representations of Extracellular Data Using Contrastive Learning
Ankit Vishnubhotla; Charlotte Loh; Akash Srivastava; Liam Paninski; Cole Hurwitz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel contrastive learning framework, CEED (Contrastive Embeddings for Extracellular Data), for high-density extracellular recordings.
3296, Spontaneous Symmetry Breaking in Generative Diffusion Models
Gabriel Raya; Luca Ambrogioni;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Generative diffusion models have recently emerged as a leading approach for generating high-dimensional data. In this paper, we show that the dynamics of these models exhibit a spontaneous symmetry breaking that divides the generative dynamics into two distinct phases: 1) A linear steady-state dynamics around a central fixed-point and 2) an attractor dynamics directed towards the data manifold.
3297, Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
Anastasiia Koloskova; Ryan McKenna; Zachary Charles; John Rush; H. Brendan McMahan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: These methods inject privacy noise through a matrix factorization mechanism, making the noise *linearly correlated* over iterations. We propose a simplified setting that distills key facets of these methods and isolates the impact of linearly correlated noise.
3298, Near Optimal Reconstruction of Spherical Harmonic Expansions
Amir Zandieh; Insu Han; Haim Avron;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose an algorithm for robust recovery of the spherical harmonic expansion of functions defined on the $d$-dimensional unit sphere $\mathbb{S}^{d-1}$ using a near-optimal number of function evaluations.
3299, Adversarial Learning for Feature Shift Detection and Correction
Míriam Barrabés; Daniel Mas Montserrat; Margarita Geleta; Xavier Giró-i-Nieto; Alexander Ioannidis;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Feature shifts can occur in many datasets, including in multi-sensor data, where some sensors are malfunctioning, or in tabular and structured data, including biomedical, financial, and survey data, where faulty standardization and data processing pipelines can lead to erroneous features. In this work, we explore using the principles of adversarial learning, where the information from several discriminators trained to distinguish between two distributions is used to both detect the corrupted features and fix them in order to remove the distribution shift between datasets.
3300, Performance Scaling Via Optimal Transport: Enabling Data Selection from Partially Revealed Sources
Feiyang Kang; Hoang Anh Just; Anit Kumar Sahu; Ruoxi Jia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a framework called *projektor*, which predicts model performance and supports data selection decisions based on partial samples of prospective data sources.
3301, Exploring Geometry of Blind Spots in Vision Models
Sriram Balasubramanian; Gaurang Sriramanan; Vinu Sankar Sadasivan; Soheil Feizi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: On the other hand, prior works have also observed that deep networks can be under-sensitive, wherein large-magnitude perturbations in input space do not induce appreciable changes to network activations. In this work, we study in detail the phenomenon of under-sensitivity in vision models such as CNNs and Transformers, and present techniques to study the geometry and extent of “equi-confidence” level sets of such networks.
3302, GMSF: Global Matching Scene Flow
Yushan Zhang; Johan Edstedt; Bastian Wandt; Per-Erik Forssen; Maria Magnusson; Michael Felsberg;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In contrast, we propose a significantly simpler single-scale one-shot global matching to address the problem.
3303, Object-Centric Learning for Real-World Videos By Predicting Temporal Feature Similarities
Andrii Zadaianchuk; Maximilian Seitzer; Georg Martius;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets. Building on this approach, we propose a novel way to use such pre-trained features in the form of a temporal feature similarity loss.
3304, Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
Longlin Yu; Tianyu Xie; Yu Zhu; Tong Yang; Xiangyu Zhang; Cheng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose hierarchical semi-implicit variational inference, called HSIVI, which generalizes SIVI to allow more expressive multi-layer construction of semi-implicit distributions.
3305, Mastering Atari Games with Generalized Weighted Path Consistency
Dengwei Zhao; Shikui Tu; Lei Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, GW-PCZero is proposed to generalize PCZero to the case where the environment emits non-zero immediate reward.
3306, Blackbox Differential Privacy for Interactive ML
Haim Kaplan; Yishay Mansour; Shay Moran; Kobbi Nissim; Uri Stemmer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work we revisit an interactive variant of joint differential privacy, recently introduced by Naor et al. [2023], and generalize it towards handling online processes in which existing privacy definitions seem too restrictive.
3307, ProtoDiff: Learning to Learn Prototypical Networks By Task-Guided Diffusion
Yingjun Du; Zehao Xiao; Shengcai Liao; Cees Snoek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, estimating a deterministic prototype using a simple average function from a limited number of examples remains a fragile process. To overcome this limitation, we introduce ProtoDiff, a novel framework that leverages a task-guided diffusion model during the meta-training phase to gradually generate prototypes, thereby providing efficient class representations.
3308, Reducing Shape-Radiance Ambiguity in Radiance Field with A Closed-Form Color Estimation Method
Qihang Fang; Yafei Song; Keqiang Li; Liefeng Bo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a more adaptive method to reduce the shape-radiance ambiguity.
3309, Epidemic Learning
Martijn De Vos; Sadegh Farhadkhani; Rachid Guerraoui; Anne-marie Kermarrec; Rafael Pires; Rishi Sharma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present Epidemic Learning (EL), a simple yet powerful decentralized learning (DL) algorithm that leverages changing communication topologies to achieve faster model convergence compared to conventional DL approaches.
3310, Domain Agnostic Fourier Neural Operators
Ning Liu; Siavash Jafarzadeh; Yue Yu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: However, to achieve good accuracy and efficiency, FNOs rely on the Fast Fourier transform (FFT), which is restricted to modeling problems on rectangular domains. To lift such a restriction and permit FFT on irregular geometries as well as topology changes, we introduce domain agnostic Fourier neural operator (DAFNO), a novel neural operator architecture for learning surrogates with irregular geometries and evolving domains.
3311, Unleashing The Full Potential of Product Quantization for Large-Scale Image Retrieval
Yu Liang; Shiliang Zhang; Li Ken Li; Xiaoyu Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To tackle those issues, we propose a novel deep hashing framework based on product quantization (PQ).
3312, CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference
Wenxuan Zeng; Meng Li; Wen-jie Lu; Runsheng Wang; Ru Huang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we present CoPriv, a framework that jointly optimizes the 2PC inference protocol and the DNN architecture.
3313, Causal Discovery in Semi-Stationary Time Series
Shanyun Gao; Raghavendra Addanki; Tong Yu; Ryan Rossi; Murat Kocaoglu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This model holds considerable practical utility because it can represent periodicity, including common occurrences such as seasonality and diurnal variation. We propose a constraint-based, non-parametric algorithm for discovering causal relations in this setting.
3314, Auxiliary Losses for Learning Generalizable Concept-based Model
Ivaxi Sheth; Samira Ebrahimi Kahou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To overcome the performance-explainability trade-off, we propose coop-CBMs.
3315, Causal Effect Identification in Uncertain Causal Networks
Sina Akbari; Fateme Jamshidi; Ehsan Mokhtarian; Matthew Vowels; Jalal Etesami; Negar Kiyavash;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we study the setting where a probabilistic model of the causal structure is available.
3316, Coop: Memory Is Not A Commodity
Jianhao Zhang; Shihan Ma; Peihong Liu; Jinhui Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This leads to severe memory fragmentation and increases the cost of potential rematerializations. To address this issue, we propose to evict tensors within a sliding window to ensure all evictions are contiguous and are immediately used.
3317, What If We Enrich Day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
Oussama Boussif; Ghait Boukachab; Dan Assouline; Stefano Massaroli; Tianle Yuan; Loubna Benabbou; Yoshua Bengio;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we put forth a deep learning architecture designed to harness spatio-temporal context using satellite data, to attain highly accurate day-ahead time-series forecasting for any given station, with a particular emphasis on forecasting Global Horizontal Irradiance (GHI).
3318, Do Not Marginalize Mechanisms, Rather Consolidate!
Moritz Willig; Matej Zečević; Devendra Dhami; Kristian Kersting;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While methods for marginalizing and abstracting SCM already exist today, they may destroy the causality of the marginalized model. To alleviate this, we introduce the concept of consolidating causal mechanisms to transform large-scale SCM while preserving consistent interventional behaviour.
3319, Successor-Predecessor Intrinsic Exploration
Changmin Yu; Neil Burgess; Samuel J Gershman; Maneesh Sahani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Successor-Predecessor Intrinsic Exploration (SPIE), an exploration algorithm based on a novel intrinsic reward combining prospective and retrospective information.
3320, DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries
Joshua Engels; Benjamin Coleman; Vihan Lakshman; Anshumali Shrivastava;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We identify this problem as a core subroutine for semantic search applications and find that existing solutions are unacceptably slow. Towards this end, we present a new approximate search algorithm, DESSERT ($\text{\bf D}$ESSERT $\text{\bf E}$ffeciently $\text{\bf S}$earches $\text{\bf S}$ets of $\text{\bf E}$mbeddings via $\text{\bf R}$etrieval $\text{\bf T}$ables).
3321, The Minimum Conditional Dependence Criterion for Self-explaining Rationalization
Wei Liu; Jun Wang; Haozhao Wang; Ruixuan Li; Zhiying Deng; YuanKai Zhang; Yang Qiu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we employ a simple and practical measure for dependence, specifically the KL-divergence, to validate our proposed MCD criterion.
3322, Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems
Zhendong Chu; Nan Wang; Hongning Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, the design of task-specific rewards is critical to facilitate CRS policy learning, which remains largely under-explored in the literature. In this work, we propose a novel approach to address this challenge by learning intrinsic rewards from interactions with users.
3323, Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization
Quanqi Hu; Dixian Zhu; Tianbao Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Our research expands on this area by examining non-smooth weakly-convex FCCO, where the outer function is weakly convex and non-decreasing, and the inner function is weakly-convex. We analyze a single-loop algorithm and establish its complexity for finding an $\epsilon$-stationary point of the Moreau envelop of the objective function.
3324, Analyzing Vision Transformers for Image Classification in Class Embedding Space
Martina Vilas; Timothy Schaumlöffel; Gemma Roig;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This work introduces a method to reverse-engineer Vision Transformers pre-trained to solve image classification tasks.
3325, Language-based Action Concept Spaces for Video Self-Supervised Learning
Kanchana Ranasinghe; Michael Ryoo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce two train objectives, concept distillation and concept alignment, that retain generality of original representations while enforcing relations between actions and their attributes.
3326, CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
Sihan Xu; Ziqiao Ma; Yidong Huang; Honglak Lee; Joyce Chai;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces CycleNet, a novel but simple method that incorporates cycle consistency into DMs to regularize image manipulation.
3327, Toward Re-Identifying Any Animal
Bingliang Jiao; Lingqiao Liu; Liying Gao; Ruiqi Wu; Guosheng Lin; PENG WANG; Yanning Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In light of the importance of ReID technology for tracking wildlife populations and migration patterns, we propose a new task called ``Re-identify Any Animal in the Wild'' (ReID-AW).
3328, Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
Jaeyeon Kim; Asuman Ozdaglar; Chanwoo Park; Ernest Ryu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present H-duality, which represents a surprising one-to-one correspondence between methods efficiently minimizing function values and methods efficiently minimizing gradient magnitude.
3329, Online Robust Non-stationary Estimation
Abishek Sankararaman; Balakrishnan Narayanaswamy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For estimation tasks that can be cast as minimizing a strongly convex loss function, we prove that an appropriately tuned version of the {\ttfamily clipped Stochastic Gradient Descent} (SGD) is simultaneously {\em(i)} adaptive to drift, {\em (ii)} robust to heavy-tailed inliers and arbitrary corruptions, {\em(iii)} requires no distributional knowledge and {\em (iv)} can be implemented in an online streaming fashion.
3330, Finite-Time Analysis of Single-Timescale Actor-Critic
Xuyang Chen; Lin Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate the more practical online single-timescale actor-critic algorithm on continuous state space, where the critic assumes linear function approximation and updates with a single Markovian sample per actor step.
3331, ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer
Haoran You; Huihong Shi; Yipin Guo; Celine Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we propose to reparameterize the pre-trained ViT with a mixture of multiplication primitives, e.g., bitwise shifts and additions, towards a new type of multiplication-reduced model, dubbed $\textbf{ShiftAddViT}$, which aims for end-to-end inference speedups on GPUs without the need of training from scratch.
3332, NPCL: Neural Processes for Uncertainty-Aware Continual Learning
Saurav Jha; Dong Gong; He Zhao; Lina Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we propose an NP-based CL approach (NPCL) with task-specific modules arranged in a hierarchical latent variable model.
3333, Learning to Group Auxiliary Datasets for Molecule
Tinglin Huang; Ziniu Hu; Rex Ying;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Through an empirical analysis, we observe that combining graph structure similarity and task similarity can serve as a more reliable indicator for identifying high-affinity auxiliary datasets. Motivated by this insight, we propose MolGroup, which separates the dataset affinity into task and structure affinity to predict the potential benefits of each auxiliary molecule dataset.
3334, Canonical Normalizing Flows for Manifold Learning
Kyriakos Flouris; Ender Konukoglu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Alternatively, if a locally orthogonal and/or sparse basis is to be learned, here coined canonical intrinsic basis, it can serve in learning a more compact latent space representation. Towards this end, we propose a canonical manifold learning flow method, where a novel optimization objective enforces the transformation matrix to have few prominent and orthogonal basis functions.
3335, One Fits All: Power General Time Series Analysis By Pretrained LM
Tian Zhou; Peisong Niu; xue wang; Liang Sun; Rong Jin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from billions of tokens, for time series analysis.
3336, Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer
Jianwei Zhang; Suren Jayasuriya; Visar Berisha;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a novel regularizer, the ICC regularizer, as a complementary component for contrastive loss to further regularize deep neural networks to produce embeddings with higher repeatability.
3337, StyleTTS 2: Towards Human-Level Text-to-Speech Through Style Diffusion and Adversarial Training with Large Speech Language Models
Yinghao Aaron Li; Cong Han; Vinay Raghavan; Gavin Mischler; Nima Mesgarani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis.
3338, Post-processing Private Synthetic Data for Improving Utility on Selected Measures
Hao Wang; Shivchander Sudalairaj; John Henning; Kristjan Greenewald; Akash Srivastava;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a post-processing technique that improves the utility of the synthetic data with respect to measures selected by the end user, while preserving strong privacy guarantees and dataset quality.
3339, Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Yongqiang Chen; Wei Huang; Kaiwen Zhou; Yatao Bian; Bo Han; James Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To alleviate the reliance, we propose Feature Augmented Training (FAT), to enforce the model to learn richer features ready for OOD generalization.
3340, Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling
Ke Yi; Yansen Wang; Kan Ren; Dongsheng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In order to break the boundaries between different EEG resources and facilitate cross-dataset EEG pre-training, we propose to map all kinds of channel selections to a unified topology.
3341, Computing Approximate $\ell_p$ Sensitivities
Swati Padmanabhan; David Woodruff; Richard Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we provide the first-of-its-kind algorithms for approximating $\ell_p$ sensitivities and other summary statistics of a given matrix.
3342, Cross-Domain Policy Adaptation Via Value-Guided Data Filtering
Kang Xu; Chenjia Bai; Xiaoteng Ma; Dong Wang; Bin Zhao; Zhen Wang; Xuelong Li; Wei Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing research has attempted to solve the problem from the dynamics discrepancy perspective. In this work, we reveal the limitations of these methods and explore the problem from the value difference perspective via a novel insight on the value consistency across domains.
3343, How to Select Which Active Learning Strategy Is Best Suited for Your Specific Problem and Budget
Guy Hacohen; Daphna Weinshall;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, in practice, knowing in advance which AL strategy is most suited for the problem at hand remains an open problem. To tackle this challenge, we propose a practical derivative-based method that dynamically identifies the best strategy for each budget.
3344, Sharp Calibrated Gaussian Processes
Alexandre Capone; Sandra Hirche; Geoff Pleiss;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: State-of-the-art approaches for designing calibrated models rely on inflating the Gaussian process posterior variance, which yields confidence intervals that are potentially too coarse. To remedy this, we present a calibration approach that generates predictive quantiles using a computation inspired by the vanilla Gaussian process posterior variance, but using a different set of hyperparameters, chosen to satisfy an empirical calibration constraint.
3345, InstanT: Semi-supervised Learning with Instance-dependent Thresholds
Muyang Li; Runze Wu; Haoyu Liu; Jun Yu; Xun Yang; Bo Han; Tongliang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose the study of instance-dependent thresholds, which has the highest degree of freedom compared with existing methods.
3346, Rotating Features for Object Discovery
Sindy Löwe; Phillip Lippe; Francesco Locatello; Max Welling;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations.
3347, CARE: Modeling Interacting Dynamics Under Temporal Distribution Shift
Xiao Luo; Haixin Wang; Zijie Huang; Huiyu Jiang; Abhijeet Gangan; Song Jiang; Yizhou Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we take an attempt to provide a probabilistic view for out-of-distribution dynamics and propose a model Context-attended Graph ODE (CARE) for understanding interacting dynamical systems.
3348, Spatially Resolved Gene Expression Prediction from Histology Images Via Bi-modal Contrastive Learning
Ronald Xie; Kuan Pang; Gary Bader; Bo Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this study, we present BLEEP (Bi-modaL Embedding for Expression Prediction), a bi-modal embedding framework capable of generating spatially resolved gene expression profiles of whole-slide Hematoxylin and eosin (H&E) stained histology images.
3349, Homotopy-based Training of NeuralODEs for Accurate Dynamics Discovery
Joon-Hyuk Ko; Hankyul Koh; Nojun Park; Wonho Jhe;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we develop a new training method for NeuralODEs, based on synchronization and homotopy optimization, that does not require changes to the model architecture.
3350, L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference
Julia Linhart; Alexandre Gramfort; Pedro Rodrigues;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Building upon the well-known classifier two-sample test (C2ST), we introduce $\ell$-C2ST, a new method that allows for a local evaluation of the posterior estimator at any given observation.
3351, Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments
Trung Dang; Jasper Lee; Maoyuan 'Raymond' Song; Paul Valiant;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Motivated by the recent effort in the community to go beyond the worst-case analysis of algorithms, we initiate the fine-grained study of the mean estimation problem. Given a distribution $p$, assuming *only* that it has a finite mean and absent any additional assumptions, we show how to construct a distribution $q_{n,\delta}$ such that $p$ and $q$ are impossible to distinguish with $n$ samples with probability $1-\delta$, yet the means of $p$ and $q$ are well-separated.
3352, Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning Under Distribution Shift
Florian Seligmann; Philipp Becker; Michael Volpp; Gerhard Neumann;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To provide a clear picture of the current state of BDL research, we evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks, with a focus on generalization capability and calibration under distribution shift.
3353, Comparing Apples to Oranges: Learning Similarity Functions for Data Produced By Different Distributions
Leonidas Tsepenekas; Ivan Brugere; Freddy Lecue; Daniele Magazzeni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For instance, it is reasonable to assume that when the elements to be compared are produced by different distributions, or in other words belong to different ``demographic'' groups, knowledge of their true similarity might be very difficult to obtain. In this work, we present an efficient sampling framework that learns these across-groups similarity functions, using only a limited amount of experts' feedback.
3354, Self-Predictive Universal AI
Elliot Catt; Jordi Grau-Moya; Marcus Hutter; Matthew Aitchison; Tim Genewein; Grégoire Delétang; Li Kevin Wenliang; Joel Veness;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: AIXI, the most potent theoretical universal agent, leverages planning through comprehensive search as its primary means to find an optimal policy. Here we define an alternative universal agent, which we call Self-AIXI, that on the contrary to AIXI, maximally exploits learning to obtain good policies.
3355, Offline RL with Discrete Proxy Representations for Generalizability in POMDPs
Pengjie Gu; Xinyu Cai; Dong Xing; Xinrun Wang; Mengchen Zhao; Bo An;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, real-world scenarios usually involve partial observability, which brings crucial challenges of the deployment of offline RL methods: i) the policy trained on data with full observability is not robust against the partial observability during execution, and ii) the modality of the partial observability is usually unknown during training. In order to address these challenges, we present Offline RL with Discrete pRoxy rEpresentations (ORDER), a probabilistic framework which leverages novel state representations to improve the robustness against diverse partial observabilities.
3356, Geometry-Aware Adaptation for Pretrained Models
Nicholas Roberts; Xintong Li; Dyah Adila; Sonia Cromp; Tzu-Heng Huang; Jitian Zhao; Frederic Sala;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Such spaces are commonly equipped with a metric that relates the labels via distances between them. We propose a simple approach to exploit this information to adapt the trained model to reliably predict new classes---or, in the case of zero-shot prediction, to improve its performance---without any additional training.
3357, Hyper-HMM: Aligning Human Brains and Semantic Features in A Common Latent Event Space
Caroline Lee; Jane Han; Ma Feilong; Guo Jiahui; James Haxby; Christopher Baldassano;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we propose a hybrid model, the Hyper-HMM, that simultaneously aligns both temporal and spatial features across brains.
3358, Online Corrupted User Detection and Regret Minimization
Zhiyong Wang; Jize Xie; Tong Yu; Shuai Li; John C.S. Lui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present an important online learning problem named LOCUD to learn and utilize unknown user relations from disrupted behaviors to speed up learning, and identify the corrupted users in an online setting.
3359, Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions
Zhaolu Liu; Robert Peach; Pedro A.M Mediano; Mauricio Barahona;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we introduce a hierarchy of $d$-order ($d \geq 2$) interaction measures, increasingly inclusive of possible factorisations of the joint probability distribution, and define non-parametric, kernel-based tests to establish systematically the statistical significance of $d$-order interactions.
3360, Error Bounds for Learning with Vector-Valued Random Features
Samuel Lanthaler; Nicholas H. Nelsen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The main results established in this paper include strong consistency of vector-valued RF estimators under model misspecification and minimax optimal convergence rates in the well-specified setting.
3361, QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks
Thomas Paniagua; Ryan Grainger; Tianfu Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we move a step forward by proposing a novel and rigorous quadratic programming (QP) method of learning ordered top-$K$ attacks with low cost, dubbed as \textbf{QuadAttac$K$}.
3362, Optimal Regret Is Achievable With Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework
Ziyi Huang; Henry Lam; Amirhossein Meisami; Haofeng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Previous research only indicates a negative theoretical result: Thompson sampling could have a worst-case linear regret $\Omega(T)$ with a constant threshold on the inference error measured by one $\alpha$-divergence. To bridge this gap, we propose an Enhanced Bayesian Upper Confidence Bound (EBUCB) framework that can efficiently accommodate bandit problems in the presence of approximate inference.
3363, CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement
Qihe Huang; Lei Shen; Ruixin Zhang; Shouhong Ding; Binwu Wang; Zhengyang Zhou; Yang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, by conducting a comprehensive analysis of the real-world data, we observe that the temporal fluctuations and heterogeneity between variables, caused by unexpected noise, are not well handled by existing methods. To address the above issues, we propose CrossGNN, a linear complexity GNN model to refine the cross-scale and cross-variable interaction for MTS.
3364, Regression with Cost-based Rejection
Xin Cheng; Yuzhou Cao; Haobo Wang; Hongxin Wei; Bo An; Lei Feng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we investigate a novel regression problem called regression with cost-based rejection, where the model can reject to make predictions on some examples given certain rejection costs.
3365, CEIL: Generalized Contextual Imitation Learning
Jinxin Liu; Li He; Yachen Kang; Zifeng Zhuang; Donglin Wang; Huazhe Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present ContExtual Imitation Learning (CEIL), a general and broadly applicable algorithm for imitation learning (IL).
3366, An Information-theoretic Quantification of The Content of Communication Between Brain Regions
Marco Celotto; Jan Bím; Alejandro Tlaie; Vito De Feo; Stefan Lemke; Daniel Chicharro; Hamed Nili; Malte Bieler; Ileana Hanganu-Opatz; Tobias Donner; Andrea Brovelli; Stefano Panzeri;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we develop a new information theoretic measure termed Feature-specific Information Transfer (FIT), quantifying how much information about a specific feature flows between two regions.
3367, Energy-based Learning Algorithms: A Comparative Study
Benjamin Scellier; Maxence Ernoult; Jack Kendall; Suhas Kumar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we carry out an extensive comparison of seven learning algorithms, namely CL and different variants of EP and CpL depending on the type of perturbation used.
3368, Malicious Attacks Via Selective Forgetting
Chenxu Zhao; Wei Qian; Rex Ying; Mengdi Huai;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Despite its significant success, limited attention has been given to the security vulnerabilities of the unlearning system concerning malicious data update requests. Motivated by this, in this paper, we explore the possibility and feasibility of malicious data update requests during the unlearning process.
3369, Generating and Distilling Discrete Adversarial Examples from Large-Scale Models
Andy Zhou; Jindong Wang; Yu-Xiong Wang; Haohan Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a conceptually simple and lightweight framework for improving the robustness of vision models through knowledge distillation.
3370, Exploiting Correlated Auxiliary Feedback in Parameterized Bandits
Arun Verma; Zhongxiang Dai; YAO SHU; Bryan Kian Hsiang Low;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study a novel variant of the parameterized bandits problem in which the learner can observe auxiliary feedback that is correlated with the observed reward.
3371, On Riemannian Projection-free Online Learning
Zihao Hu; Guanghui Wang; Jacob Abernethy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present methods for obtaining sub-linear regret guarantees in online geodesically convex optimization on curved spaces for two scenarios: when we have access to (a) a separation oracle or (b) a linear optimization oracle.
3372, Uncertainty Estimation for Safety-critical Scene Segmentation Via Fine-grained Reward Maximization
Hongzheng Yang; Cheng Chen; Yueyao CHEN; Scheppach; Hon Chi Yip; DOU QI;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel fine-grained reward maximization (FGRM) framework, to address uncertainty estimation by directly utilizing an uncertainty metric related reward function with a reinforcement learning based model tuning paradigm.
3373, RH-BrainFS: Regional Heterogeneous Multimodal Brain Networks Fusion Strategy
Hongting Ye; Yalu Zheng; Yueying Li; Ke Zhang; Youyong Kong; Yonggui Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, to alleviate the issue of regional heterogeneity of multimodal brain networks, we propose a novel Regional Heterogeneous multimodal Brain networks Fusion Strategy (RH-BrainFS).
3374, On Class Distributions Induced By Nearest Neighbor Graphs for Node Classification of Tabular Data
Federico Errica;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Such artificial structures often reflect the homophily assumption, believed to be a key factor in the performances of deep graph networks. In light of recent results demystifying these beliefs, we introduce a theoretical framework to understand the benefits of Nearest Neighbor (NN) graphs when a graph structure is missing.
3375, Equivariant Single View Pose Prediction Via Induced and Restriction Representations
Owen Howell; David Klee; Ondrej Biza; Linfeng Zhao; Robin Walters;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a new algorithm that is a learnable generalization of previously considered methods.
3376, Taylor TD-learning
Michele Garibbo; Maxime Robeyns; Laurence Aitchison;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Here, we introduce a model-based RL framework, Taylor TD, which reduces this variance in continuous state-action settings.
3377, A Novel Framework for Policy Mirror Descent with General Parametrization and Linear Convergence
Carlo Alfano; Rui Yuan; Patrick Rebeschini;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a novel framework for policy optimization based on mirror descent that naturally accommodates general parametrizations.
3378, Supported Value Regularization for Offline Reinforcement Learning
Yixiu Mao; Hongchang Zhang; Chen Chen; Yi Xu; Xiangyang Ji;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Offline reinforcement learning suffers from the extrapolation error and value overestimation caused by out-of-distribution (OOD) actions. To mitigate this issue, value regularization approaches aim to penalize the learned value functions to assign lower values to OOD actions.
3379, For SALE: State-Action Representation Learning for Deep Reinforcement Learning
Scott Fujimoto; Wei-Di Chang; Edward Smith; Shixiang (Shane) Gu; Doina Precup; David Meger;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states.
3380, Conformal Scorecasting: Anticipatory Uncertainty Quantification for Distribution Shift in Time Series
Anastasios Angelopoulos; Ryan Tibshirani; Emmanuel Candes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The algorithms we present are able to prospectively model and adapt to the presence of systematic errors due to seasonality, trends, and other distribution shifts, while remaining simple and theoretically sound.
3381, Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence
Marie Maros; Gesualdo Scutari;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We explore the matrix sensing problem from near-isotropic linear measurements, distributed across a network of agents modeled as an undirected graph, with no centralized node.
3382, Social Motion Prediction with Cognitive Hierarchies
Wentao Zhu; Jason Qin; Yuke Lou; Hang Ye; Xiaoxuan Ma; Hai Ci; Yizhou Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Humans exhibit a remarkable capacity for anticipating the actions of others and planning their own actions accordingly. In this study, we strive to replicate this ability by addressing the social motion prediction problem.
3383, Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
Yulhwa Kim; Dongwon Jo; Hyesung Jeon; Taesu Kim; Daehyun Ahn; Hyungjun Kim; jae-joon kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel approach to speed up the noise estimation network by leveraging the robustness of early-stage diffusion models.
3384, Directional Diffusion Model for Graph Representation Learning
Run Yang; Yuling Yang; Fan Zhou; Qiang Sun;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the application of diffusion models in graph learning has received relatively little attention. In this paper, we address this gap by investigating the use of diffusion models for unsupervised graph representation learning.
3385, Label Correction of Crowdsourced Noisy Annotations with An Instance-Dependent Noise Transition Model
Hui GUO; Boyu Wang; Grace Yi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Specifically, we approximate the instance-dependent noise transition matrices using a Bayesian network with a hierarchical spike and slab prior.
3386, Private Federated Frequency Estimation: Adapting to The Hardness of The Instance
Jingfeng Wu; Wennan Zhu; Peter Kairouz; Vladimir Braverman;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, we show that both our sketch algorithm and count sketch can achieve better accuracy when the problem instance is simpler. Therefore, we propose a two-phase approach to enable the use of a smaller sketch size for simpler problems.
3387, Hierarchical Multi-Agent Skill Discovery
Mingyu Yang; Yaodong Yang; Zhenbo Lu; Wengang Zhou; Houqiang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: One is how to learn skills not only for the individual agents but also for the entire team, and the other is how to coordinate the skills of different agents to accomplish multi-agent tasks. To address these challenges, we present Hierarchical Multi-Agent Skill Discovery (HMASD), a two-level hierarchical algorithm for discovering both team and individual skills in MARL.
3388, AMDP: An Adaptive Detection Procedure for False Discovery Rate Control in High-Dimensional Mediation Analysis
Jiarong Ding; Xuehu ZHU;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The composite null hypothesis presents a challenge for false discovery rate (FDR) control. To address this issue, we propose a data-driven algorithm based on the symmetric property of the null hypothesis.
3389, SPQR: Controlling Q-ensemble Independence for Reinforcement Learning
Dohyeok Lee; Seungyub Han; Taehyun Cho; Jungwoo Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: By introducing a novel regularization loss for Q-ensemble independence based on random matrix theory, we propose spiked Wishart Q-ensemble independence regularization (SPQR) for reinforcement learning.
3390, Soft-Unification in Deep Probabilistic Logic
Jaron Maene; Luc De Raedt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, these properties are not satisfied by previous systems such as the Neural Theorem Prover. Therefore, we introduce a more principled framework called DeepSoftLog based on probabilistic rather than fuzzy semantics.
3391, SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting
Shane Bergsma; Tim Zeyl; Lei Guo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose SutraNets, a novel method for neural probabilistic forecasting of long-sequence time series.
3392, Learning To Dive In Branch And Bound
Max Paulus; Andreas Krause;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Existing divers rely on generic decision rules that fail to exploit structural commonality between similar problem instances that often arise in practice. Therefore, we propose L2Dive to learn specific diving heuristics with graph neural networks: We train generative models to predict variable assignments and leverage the duality of linear programs to make diving decisions based on the model's predictions.
3393, Generator Identification for Linear SDEs with Additive and Multiplicative Noise
Yuanyuan Wang; Xi Geng; Wei Huang; Biwei Huang; Mingming Gong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present conditions for identifying the generator of a linear stochastic differential equation (SDE) from the law of its solution process with a given fixed initial state.
3394, Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability
Maciej Falkiewicz; Naoya Takeishi; Imahn Shekhzadeh; Antoine Wehenkel; Arnaud Delaunoy; Gilles Louppe; Alexandros Kalousis;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose to include a calibration term directly into the training objective of the neural model in selected SBI techniques.
3395, Strategyproof Voting Under Correlated Beliefs
Daniel Halpern; Rachel Li; Ariel Procaccia;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, it is quite reasonable for a voter to believe that other votes are correlated, either to each other or to their own ranking. We consider such beliefs induced by classic probabilistic models in social choice such as the Mallows, Placket-Luce, and Thurstone-Mosteller models.
3396, Break It Down: Evidence for Structural Compositionality in Neural Networks
Michael Lepori; Thomas Serre; Ellie Pavlick;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Another possibility is that they may simply learn to match new inputs to learned templates, eliding task decomposition entirely. Here, we leverage model pruning techniques to investigate this question in both vision and language across a variety of architectures, tasks, and pretraining regimens.
3397, Activity Grammars for Temporal Action Segmentation
Dayoung Gong; Joonseok Lee; Deunsol Jung; Suha Kwak; Minsu Cho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel grammar induction algorithm, dubbed KARI, that extracts a powerful context-free grammar from action sequence data.
3398, Follow-ups Also Matter: Improving Contextual Bandits Via Post-serving Contexts
Chaoqi Wang; Ziyu Ye; Zhe Feng; Ashwinkumar Badanidiyuru Varadaraja; Haifeng Xu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For example, content recommendation platforms like Youtube, Instagram, Tiktok receive much additional features about a user's reward after the user clicks a content (e.g., how long the user stayed, what is the user's watch speed, etc.). To improve online learning efficiency in these applications, we study a novel contextual bandit problem with post-serving contexts and design a new algorithm, poLinUCB, that achieves tight regret under standard assumptions.
3399, ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
Junguang Jiang; Baixu Chen; Junwei Pan; Ximei Wang; Dapeng Liu; Jie Jiang; Mingsheng Long;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Based on our findings, we introduce ForkMerge, a novel approach that periodically forks the model into multiple branches, automatically searches the varying task weights by minimizing target validation errors, and dynamically merges all branches to filter out detrimental task-parameter updates.
3400, Learning to Select A Subset of Training Examples to Generalize Efficient Model Training
Eeshaan Jain; Tushar Nandy; Gaurav Aggarwal; Ashish Tendulkar; Rishabh Iyer; Abir De;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Therefore, for an unseen architecture, one cannot use the subset chosen for a different model. In this work, we propose $\texttt{SubSelNet}$, a non-adaptive subset selection framework, which tackles these problems.
3401, Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction
Qing Wu; Lixuan Chen; Ce Wang; Hongjiang Wei; S. Kevin Zhou; Jingyi Yu; Yuyao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present a novel Polychromatic neural representation (Polyner) to tackle the challenging problem of CT imaging when metallic implants exist within the human body.
3402, Rewarded Soups: Towards Pareto-optimality By Interpolating Weights Fine-tuned on Diverse Rewards
Alexandre Rame; Guillaume Couairon; Corentin Dancette; Jean-Baptiste Gaya; Mustafa Shukor; Laure Soulier; Matthieu Cord;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes embracing the heterogeneity of diverse rewards by following a multi-policy strategy.
3403, Zero-shot Visual Relation Detection Via Composite Visual Cues from Large Language Models
Lin Li; Jun Xiao; Guikun Chen; Jian Shao; Yueting Zhuang; Long Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel method for zero-shot VRD: RECODE, which solves RElation detection via COmposite DEscription prompts.
3404, Counterfactual Evaluation of Peer-Review Assignment Strategies
Martin Saveski; Steven Jecmen; Nihar Shah; Johan Ugander;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we leverage recently proposed strategies that introduce randomness in peer-review assignment—in order to mitigate fraud—as a valuable opportunity to evaluate counterfactual assignment strategies.
3405, Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
Gon Buzaglo; Niv Haim; Gilad Yehudai; Gal Vardi; Yakir Oz; Yaniv Nikankin; Michal Irani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we extend their findings in several directions, including reconstruction from multiclass and convolutional neural networks.
3406, Stein $\Pi$-Importance Sampling
Congye Wang; Ye Chen; Heishiro Kanagawa; Chris Oates;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper studies Stein importance sampling, in which weights are assigned to the states visited by a $\Pi$-invariant Markov chain to obtain a consistent approximation of $P$, the intended target. Surprisingly, the optimal choice of $\Pi$ is not identical to the target $P$; we therefore propose an explicit construction for $\Pi$ based on a novel variational argument.
3407, An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint
Mengzhao Wang; Lingwei Lv; Xiaoliang Xu; Yuxiang Wang; Qiang Yue; Jiongkang Ni;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper introduces an efficient and robust framework for hybrid query (HQ) processing, which combines approximate nearest neighbor search (ANNS) with attribute constraint.
3408, Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
Hyuna Cho; Minjae Jeong; Sooyeon Jeon; Sungsoo Ahn; Won Hwa Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While recent deep neural networks have demonstrated sampling of realistic graphs together with diffusion models, however, they still suffer from oversmoothing problem which inherits from conventional graph convolution and thus high-frequency characteristics of nodes and edges become intractable. To overcome such issues and generate graphs with high fidelity, this paper introduces a novel approach that captures the dependency between nodes and edges at multiple resolutions in the spectral space.
3409, Creating Multi-Level Skill Hierarchies in Reinforcement Learning
Joshua B. Evans; Özgür Şimşek;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: What is a useful skill hierarchy for an autonomous agent? We propose an answer based on the graphical structure of an agent's interaction with its environment.
3410, One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models
Ba-Hien Tran; Giulio Franzese; Pietro Michiardi; Maurizio Filippone;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, they typically achieve lower sample quality compared to state-of-the-art score-based diffusion models (DMs). This paper provides a significant step in the direction of addressing this limitation.
3411, Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation
David Brandfonbrener; Ofir Nachum; Joan Bruna;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In recent years, domains such as natural language processing and image recognition have popularized the paradigm of using large datasets to pretrain representations that can be effectively transferred to downstream tasks. In this work we evaluate how such a paradigm should be done in imitation learning, where both pretraining and finetuning data are trajectories collected by experts interacting with an unknown environment.
3412, Improving Systematic Generalization Using Iterated Learning and Simplicial Embeddings
Yi Ren; Samuel Lavoie; Michael Galkin; Danica J. Sutherland; Aaron Courville;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A line of research in cognitive science has hypothesized a process, iterated learning, to help explain how human language developed this representation ability; the theory rests on simultaneous pressures towards compressibility and expressivity in transmitting messages. Inspired by this process, we propose using iterated learning with deep network models containing a simplicial embedding to obtain approximately discrete messages.
3413, PPi: Pretraining Brain Signal Model for Patient-independent Seizure Detection
Zhizhang Yuan; Daoze Zhang; YANG YANG; Junru Chen; Yafeng Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, modeling SEEG in clinical scenarios will face challenges like huge domain shift between different patients and dramatic pattern evolution among different brain areas. In this study, we propose a Pretraining-based model for Patient-independent seizure detection (PPi) to address these challenges.
3414, Unbiased Constrained Sampling with Self-Concordant Barrier Hamiltonian Monte Carlo
Maxence Noble; Alain Durmus; Valentin De Bortoli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose Barrier Hamiltonian Monte Carlo (BHMC), a version of the HMC algorithm which aims at sampling from a Gibbs distribution $\pi$ on a manifold $\mathsf{M}$, endowed with a Hessian metric $\mathfrak{g}$ derived from a self-concordant barrier.
3415, A Closer Look at The Robustness of Contrastive Language-Image Pre-Training (CLIP)
Weijie Tu; Weijian Deng; Tom Gedeon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we study $85$ CLIP models and $127$ ImageNet classifiers.
3416, Stochastic Distributed Optimization Under Average Second-order Similarity: Algorithms and Analysis
Dachao Lin; Yuze Han; Haishan Ye; Zhihua Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose two new algorithms: SVRS and AccSVRS motivated by previous works.
3417, RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers Via Randomized Deletion
Zhuoqun Huang; Neil G Marchant; Keane Lucas; Lujo Bauer; Olga Ohrimenko; Benjamin Rubinstein;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we adapt randomized smoothing for discrete sequence classifiers to provide certified robustness against edit distance-bounded adversaries.
3418, Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models
Geon Yeong Park Park; Jeongsol Kim; Beomsu Kim; Sang Wan Lee; Jong Chul Ye;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment. To address this, here we present a novel energy-based model (EBM) framework.
3419, An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions
Michael Scholkemper; Michael T Schaub;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Similar to community detection, partitioning the nodes of a complex network according to their structural roles aims to identify fundamental building blocks of a network, which can be used, e.g., to find simplified descriptions of the network connectivity, to derive reduced order models for dynamical processes unfolding on processes, or as ingredients for various network analysis and graph mining tasks. In this work, we offer a fresh look on the problem of role extraction and its differences to community detection and present a definition of node roles and two associated optimization problems (cost functions) grounded in ideas related to graph-isomorphism tests, the Weisfeiler-Leman algorithm and equitable partitions.
3420, Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition
Vivek Bharadwaj; Osman Asif Malik; Riley Murray; Laura Grigori; Aydin Buluc; James Demmel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We present a data structure to randomly sample rows from the Khatri-Rao product of several matrices according to the exact distribution of its leverage scores.
3421, VaRT: Variational Regression Trees
Sebastian Salazar;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce a novel non-parametric Bayesian model that uses variational inference to approximate a posterior distribution over the space of stochastic decision trees.
3422, MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates
Mohammad Mozaffari; Sikan Li; Zhao Zhang; Maryam Mehri Dehnavi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work proposes a Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 updates, called MKOR, that improves the training time and convergence properties of deep neural networks (DNNs).
3423, CAST: Cross-Attention in Space and Time for Video Action Recognition
Dongho Lee; Jongseo Lee; Jinwoo Choi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input.
3424, Iteratively Learn Diverse Strategies with State Distance Information
Wei Fu; Weihua Du; Jingwei Li; Sunli Chen; Jingzhao Zhang; YI WU;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To accurately capture the behavioral difference, we propose to incorporate the state-space distance information into the diversity measure.
3425, Learning Provably Robust Estimators for Inverse Problems Via Jittering
Anselm Krainovic; Mahdi Soltanolkotabi; Reinhard Heckel;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we investigate whether Jittering, a simple regularization technique that adds isotropic Gaussian noise during training, is effective for obtaining worst-case robust estimators for inverse problems.
3426, On The Choice of Perception Loss Function for Learned Video Compression
Sadaf Salehkalaibar; Buu Phan; Jun Chen; Wei Yu; Ashish Khisti;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study causal, low-latency, sequential video compression when the output is subjected to both a mean squared-error (MSE) distortion loss as well as a perception loss to target realism.
3427, Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost
Sepehr Assadi; Vihan Shah; Chen Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: As our main result, we present two novel algorithms that in only $\text{polylog}{(n)}$ space are able to estimate the optimal correlation clustering cost up to some constant multiplicative factor plus some extra additive error.
3428, PointGPT: Auto-regressively Generative Pre-training from Point Clouds
Guangyan Chen; Meiling Wang; Yi Yang; Kai Yu; Li Yuan; Yufeng Yue;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Inspired by the advancements of the GPT, we present PointGPT, a novel approach that extends the concept of GPT to point clouds, addressing the challenges associated with disorder properties, low information density, and task gaps.
3429, Look Beneath The Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL
Peng Cheng; Xianyuan Zhan; zhihao wu; Wenjia Zhang; Youfang Lin; Shou cheng Song; Han Wang; Li Jiang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we provide a new insight that leveraging the fundamental symmetry of system dynamics can substantially enhance offline RL performance under small datasets.
3430, State-Action Similarity-Based Representations for Off-Policy Evaluation
Brahma Pavse; Josiah Hanna;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Instead, in this paper, we seek to enhance the data-efficiency of FQE by first transforming the fixed dataset using a learned encoder, and then feeding the transformed dataset into FQE.
3431, L2T-DLN: Learning to Teach with Dynamic Loss Network
Zhaoyang Hai; Liyuan Pan; Xiabi Liu; Zhengzheng Liu; Mirna Yunita;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we first formulate the loss adjustment as a temporal task by designing a teacher model with memory units, and, therefore, enables the student learning to be guided by the experience of the teacher model. Then, with a Dynamic Loss Network, we can additionally use the states of the loss to assist the teacher learning in enhancing the interactions between the teacher and the student model.
3432, NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA
Hyeong Kyu Choi; Seunghun Lee; Jaewon Chu; Hyunwoo Kim;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To make matters worse, KG nodes often represent pronoun entities and are sometimes encrypted, being uninformative in selecting between paths. To address these problems, we propose Neural Tree Search (NuTrea), a tree search-based GNN model that incorporates the broader KG context.
3433, On The Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Yufeng Zhang; Jialu Pan; Wanwei Liu; Zhenbang Chen; Xinwang Liu; J Wang; Li Ken Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we theoretically study several properties of KL divergence between multivariate Gaussian distributions.
3434, Dream The Impossible: Outlier Imagination with Diffusion Models
Xuefeng Du; Yiyou Sun; Jerry Zhu; Yixuan Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To tackle the problem, this paper proposes a new framework Dream-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the in-distribution (ID) data and classes.
3435, Siamese Masked Autoencoders
Agrim Gupta; Jiajun Wu; Jia Deng; Fei-Fei Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present Siamese Masked Autoencoders (SiamMAE), a simple extension of Masked Autoencoders (MAE) for learning visual correspondence from videos.
3436, On The Impact of Activation and Normalization in Obtaining Isometric Embeddings at Initialization
Amir Joudaki; Hadi Daneshmand; Francis Bach;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we explore the structure of the penultimate Gram matrix in deep neural networks, which contains the pairwise inner products of outputs corresponding to a batch of inputs.
3437, Limits, Approximation and Size Transferability for GNNs on Sparse Graphs Via Graphops
Thien Le; Stefanie Jegelka;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Can graph neural networks generalize to graphs that are different from the graphs they were trained on, e.g., in size? In this work, we study this question from a theoretical perspective.
3438, SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations
Youngsoo Jang; Geon-Hyeong Kim; Jongmin Lee; Sungryull Sohn; Byoungjip Kim; Honglak Lee; Moontae Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a hyperparameter-free offline safe IL algorithm, SafeDICE, that learns safe policy by leveraging the non-preferred demonstrations in the space of stationary distributions.
3439, Active Reinforcement Learning Under Limited Visual Observability
Jinghuan Shang; Michael Ryoo;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we investigate Active Reinforcement Learning (Active-RL), where an embodied agent simultaneously learns action policy for the task while also controlling its visual observations in partially observable environments.
3440, FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy
Zuhao Yang; Yingfang Yuan; Yang Xu; SHUO ZHAN; Huajun Bai; Kefan Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Inspired by empirical findings from psycholinguistics on the periodicity of entropy in language, we propose FACE, a set of metrics based on Fourier Analysis of the estimated Cross-Entropy of language, for measuring the similarity between model-generated and human-written languages.
3441, Label Poisoning Is All You Need
Rishi Jha; Jonathan Hayase; Sewoong Oh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce FLIP, a trajectory-matching-based algorithm that corrupts only the labels in the training set to create a backdoor.
3442, Labeling Neural Representations with Inverse Recognition
Kirill Bykov; Laura Kopf; Shinichi Nakajima; Marius Kloft; Marina Höhne;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose Inverse Recognition (INVERT), a scalable approach for linking the learned representations to human-interpretable concepts based on the ability to differentiate between concepts.
3443, Operation-Level Early Stopping for Robustifying Differentiable NAS
Shen Jiang; Zipeng Ji; Guanghui Zhu; Yihua Huang; Chunfeng Yuan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: % In this paper, we analyze this issue from a simple and straightforward perspective and propose that the domination of skip connections results from parametric operations overfitting the training data while architecture parameters are trained on the validation data, leading to undesired behaviors. % Based on this observation, we propose the operation-level early stopping (OLES) method to overcome this issue and robustify DARTS without introducing any computation overhead.
3444, Neural Representations for Predictive Processing of Dynamic Visual Signals
Pierre-Étienne Fiquet; Eero Simoncelli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we develop a self-supervised representation-learning framework that can reveal and exploit the regularities of natural videos to compute accurate predictions.
3445, Spectral Evolution and Invariance in Linear-width Neural Networks
Zhichao Wang; Andrew Engel; Anand D Sarwate; Ioana Dumitriu; Tony Chiang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We investigate the spectral properties of linear-width feed-forward neural networks, where the sample size is asymptotically proportional to network width.
3446, History Filtering in Imperfect Information Games: Algorithms and Complexity
Christopher Solinas; Doug Rebstock; Nathan Sturtevant; Michael Buro;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce and analyze the computational aspects and tractability of filtering histories for subgame decomposition.
3447, Classification of Superstatistical Features in High Dimensions
Urte Adomaityte; Gabriele Sicuro; Pierpaolo Vivo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We characterise the learning of a mixture of two clouds of data points with generic centroids via empirical risk minimisation in the high dimensional regime, under the assumptions of generic convex loss and convex regularisation.
3448, Neural Algorithmic Reasoning Without Intermediate Supervision
Gleb Rodionov; Liudmila Prokhorenkova;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we instead focus on learning neural algorithmic reasoning only from the input-output pairs without appealing to the intermediate supervision.
3449, MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition
Nicolas Menet; Michael Hersche; Geethan Karunaratne; Luca Benini; Abu Sebastian; Abbas Rahimi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To reduce the computational burden per input, we propose Multiple-Input-Multiple-Output Neural Networks (MIMONets) capable of handling many inputs at once.
3450, FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
Chanakya Ekbote; Ajinkya Deshpande; Arun Iyer; SUNDARARAJAN SELLAMANICKAM; Ramakrishna Bairi;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents a simple filter-based augmentation method to capture different parts of the eigen-spectrum.
3451, Human-Guided Complexity-Controlled Abstractions
Andi Peng; Mycal Tucker; Eoin Kenny; Noga Zaslavsky; Pulkit Agrawal; Julie A Shah;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g., bird vs. sparrow') and use the appropriate abstraction based on tasks. Inspired by this, we train neural models to generate a spectrum of discrete representations, and control the complexity of the representations (roughly, how many bits are allocated for encoding inputs) by tuning the entropy of the distribution over representations.
3452, A Fast Heuristic to Optimize Time-space Tradeoff for Large Models
Akifumi Imanishi; Zijian Xu; Masayuki Takagi; Sixue Wang; Emilio Castillo;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper proposes a novel algorithm for recomputation that achieves better solutions than Checkmate, with significantly reduced optimization time.
3453, Bicriteria Approximation Algorithms for The Submodular Cover Problem
Wenjing Chen; Victoria Crawford;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider the optimization problem Submodular Cover (SCP), which is to find a minimum cardinality subset of a finite universe $U$ such that the value of a submodular function $f$ is above an input threshold $\tau$.
3454, Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization
Nathan Grinsztajn; Daniel Furelos-Blanco; Shikha Surana; Clément Bonnet; Thomas D Barrett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we argue for the benefits of learning a population of complementary policies, which can be simultaneously rolled out at inference.
3455, The Graphical Matrix Pencil Method: Exchangeable Distributions with Prescribed Subgraph Densities
Lee Gunderson; Gecia Bravo-Hermsdorff; Peter Orbanz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper describes an analytic method for (1) inference in and (2) sampling from distributions on graphs with prescribed subgraph densities.
3456, Asynchronous Proportional Response Dynamics in Markets with Adversarial Scheduling
Yoav Kolumbus; Menahem Levy; Noam Nisan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study Proportional Response Dynamics (PRD) in linear Fisher markets where participants act asynchronously.
3457, Entropy-based Training Methods for Scalable Neural Implicit Samplers
Weijian Luo; Boya Zhang; Zhihua Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Traditional approaches like Markov Chain Monte Carlo (MCMC) guarantee asymptotically unbiased samples from such distributions but suffer from computational inefficiency, particularly when dealing with high-dimensional targets, as they require numerous iterations to generate a batch of samples. In this paper, we propose an efficient and scalable neural implicit sampler that overcomes these limitations.
3458, Multi-task Learning with Summary Statistics
Parker Knight; Rui Duan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, the application of multi-task learning to real-world settings is hindered by data-sharing constraints, especially in healthcare settings. To address this challenge, we propose a flexible multi-task learning framework utilizing summary statistics from various sources.
3459, Fitting Trees to $\ell_1$-hyperbolic Distances
Joon-Hyeok Yim; Anna Gilbert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Furthermore, we can interpret the classical tree fitting result of Gromov as a $p = q = \infty$ result. We present an algorithm \textsc{HCCRootedTreeFit} such that the $\ell_1$ error of the output embedding is analytically bounded in terms of the $\ell_1$-norm of the hyperbolicity vector (i.e., $p = q = 1$) and that this result is tight.
3460, Improving Language Plasticity Via Pretraining with Active Forgetting
Yihong Chen; Mikel Artetxe; Kelly Marchisio; Roberta Raileanu; David Adelani; Pontus Lars Erik Saito Stenetorp; Sebastian Riedel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose to use an \textit{active forgetting} mechanism when pretraining, as a simple way of creating PLMs that can quickly adapt to new languages.
3461, Identifiability Guarantees for Causal Disentanglement from Soft Interventions
Jiaqi Zhang; Kristjan Greenewald; Chandler Squires; Akash Srivastava; Karthikeyan Shanmugam; Caroline Uhler;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we focus on the scenario where unpaired observational and interventional data are available, with each intervention changing the mechanism of a latent variable.
3462, LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas
Kensen Shi; Hanjun Dai; Wen-Ding Li; Kevin Ellis; Charles Sutton;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, a common drawback of those approaches is the inability to handle iterative loops, higher-order functions, or lambda functions, thus limiting prior neural searches from synthesizing longer and more general programs. We address this gap by designing a search algorithm called LambdaBeam that can construct arbitrary lambda functions that compose operations within a given DSL.
3463, Equivariant Adaptation of Large Pre-Trained Models
Arnab Kumar Mondal; Siba Smarak Panigrahi; Oumar Kaba; Sai Rajeswar Mudumba; Siamak Ravanbakhsh;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Using dataset-dependent priors to inform the canonicalization function, we are able to make large pre-trained models equivariant while maintaining their performance.
3464, Maximum Independent Set: Self-training Through Dynamic Programming
Lorenzo Brusca; Lars C.P.M. Quaedvlieg; Stratis Skoulakis; Grigorios Chrysos; Volkan Cevher;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work presents a novel graph neural network (GNN) framework for solving the maximum independent set (MIS) inspired by dynamic programming (DP).
3465, Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do
Sarah Toonsi; Jeff Shamma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce higher-order gradient play dynamics that resemble projected gradient ascent with auxiliary states.
3466, DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis
Youngjoong Kwon; Lingjie Liu; Henry Fuchs; Marc Habermann; Christian Theobalt;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model.
3467, Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
Minsu Kim; Federico Berto; Sungsoo Ahn; Jinkyoo Park;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose a novel solution, bootstrapped training of score-conditioned generator (BootGen) algorithm.
3468, POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
Antonin Vobecky; Oriane Siméoni; David Hurych; Spyridon Gidaris; Andrei Bursuc; Patrick Pérez; Josef Sivic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We describe an approach to predict open-vocabulary 3D semantic voxel occupancy map from input 2D images with the objective of enabling 3D grounding, segmentation and retrieval of free-form language queries.
3469, Parts of Speech–Grounded Subspaces in Vision-Language Models
James Oldfield; Christos Tzelepis; Yannis Panagakis; Mihalis Nicolaou; Ioannis Patras;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose to separate representations of the different visual modalities in CLIP’s joint vision-language space by leveraging the association between parts of speech and specific visual modes of variation (e.g. nouns relate to objects, adjectives describe appearance).
3470, Versatile Energy-Based Probabilistic Models for High Energy Physics
Taoli Cheng; Aaron Courville;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This framework builds on a powerful generative model and describes higher-order inter-particle interactions.
3471, WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting
Yuxin Jia; Youfang Lin; Xinyan Hao; Yan Lin; Shengnan Guo; Huaiyu Wan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To address the challenge of capturing different types of semantic information, we propose a novel Water-wave Information Transmission (WIT) framework.
3472, SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks
Rainer Engelken;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel event-based algorithm called SparseProp for simulating and training sparse SNNs.
3473, Moral Responsibility for AI Systems
Sander Beckers;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a formal definition of both conditions within the framework of causal models.
3474, On Masked Pre-training and The Marginal Likelihood
Pablo Moreno-Muñoz; Pol G. Recasens; Søren Hauberg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper shows that masked pre-training with a suitable cumulative scoring function corresponds to maximizing the model's marginal likelihood, which is de facto the Bayesian model selection measure of generalization.
3475, FAMO: Fast Adaptive Multitask Optimization
Bo Liu; Yihao Feng; Peter Stone; Qiang Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we introduce Fast Adaptive Multitask Optimization FAMO, a dynamic weighting method that decreases task losses in a balanced way using O(1) space and time.
3476, TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion
Preetha Vijayan; Prashant Bhat; Elahe Arani; Bahram Zonooz;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Inspired by how the brain exploits multiple mechanisms concurrently, we propose TriRE, a novel CL paradigm that encompasses retaining the most prominent neurons for each task, revising and solidifying the extracted knowledge of current and past tasks, and actively promoting less active neurons for subsequent tasks through rewinding and relearning.
3477, CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection
Yunyao Mao; Jiajun Deng; Wengang Zhou; Li Li; Yao Fang; Houqiang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce CLIP4HOI, a novel framework for zero-shot HOI detection.
3478, Doubly Robust Augmented Transfer for Meta-Reinforcement Learning
Yuankun Jiang; Nuowen Kan; Chenglin Li; Wenrui Dai; Junni Zou; Hongkai Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a doubly robust augmented transfer (DRaT) approach, aiming at addressing the more general sparse reward meta-RL scenario with both dynamics mismatches and varying reward functions across tasks.
3479, Generating Behaviorally Diverse Policies with Latent Diffusion Models
Shashank Hegde; Sumeet Batra; K.R. Zentner; Gaurav Sukhatme;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose using diffusion models to distill the archive into a single generative model over policy parameters.
3480, Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction
Zechuan Zhang; Li Sun; Zongxin Yang; Ling Chen; Yi Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: Current methods exhibit limitations in performance, largely attributable to their dependence on insufficient 2D image features and inconsistent query methods. Owing to this, we present the Global-correlated 3D-decoupling Transformer for clothed Avatar reconstruction (GTA), a novel transformer-based architecture that reconstructs clothed human avatars from monocular images.
3481, When Are Ensembles Really Effective?
Ryan Theisen; Hyunsuk Kim; Yaoqing Yang; Liam Hodgkinson; Michael Mahoney;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that ensembling improves performance significantly whenever the disagreement rate is large relative to the average error rate; and that, conversely, one classifier is often enough whenever the disagreement rate is low relative to the average error rate. On the way to proving these results, we derive, under a mild condition called competence, improved upper and lower bounds on the average test error rate of the majority vote classifier.
3482, Combinatorial Optimization with Policy Adaptation Using Latent Space Search
Felix Chalumeau; Shikha Surana; Clément Bonnet; Nathan Grinsztajn; Arnu Pretorius; Alexandre Laterre; Thomas D Barrett;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Building on the intuition that performant search at inference time should be anticipated during pre-training, we propose COMPASS, a novel RL approach that parameterizes a distribution of diverse and specialized policies conditioned on a continuous latent space.
3483, Structure of Universal Formulas
Dmitry Yarotsky;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: There exist various examples of such formulas, including some in the form of neural networks. In this paper we analyze the essential structural elements of such highly expressive models.
3484, Efficient Hyper-parameter Optimization with Cubic Regularization
Zhenqian Shen; Hansi Yang; Yong Li; James Kwok; Quanming Yao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we consider a sub-class of hyper-parameter optimization problems, where the hyper-gradients are not available.
3485, A Unified Model and Dimension for Interactive Estimation
Nataly Brukhim; Miro Dudik; Aldo Pacchiano; Robert Schapire;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present a simple, general, and broadly-applicable algorithm, for which we obtain both regret and PAC generalization bounds that are polynomial in the new dimension.
3486, Variational Gaussian Processes with Decoupled Conditionals
Xinran Zhu; Kaiwen Wu; Natalie Maus; Jacob Gardner; David Bindel;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To achieve scalability, inducing point methods typically introduce conditional independencies and then approximations to the training and test conditional distributions. In this paper, we consider an alternative approach to modifying the training and test conditionals, in which we make them more flexible.
3487, Private Everlasting Prediction
Moni Naor; Kobbi Nissim; Uri Stemmer; Chao Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce private everlasting prediction taking into account the privacy of both the training set and the (adaptively chosen) queries made to the predictor.
3488, Creating A Public Repository for Joining Private Data
James Cook; Milind Shyani; Nina Mishra;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper shows how the hospital can generate a private sketch and how the airline can privately join with the hospital's sketch by email address.
3489, Multi Time Scale World Models
Vaisakh Shaj Kumar; SALEH GHOLAM ZADEH; Ozan Demir; Luiz Douat; Gerhard Neumann;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a probabilistic formalism to learn multi-time scale world models which we call the Multi Time Scale State Space (MTS3) model.
3490, Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference
Licong Lin; Mufang Ying; Suvrojit Ghosh; Koulik Khamaru; Cun-Hui Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This issue is highlighted by a recent minimax lower bound, which shows that the error of estimating a single coordinate can be enlarged by a multiple of $\sqrt{d}$ when data are allowed to be arbitrarily adaptive, compared with the case when they are i.i.d. Our work explores this striking difference in estimation performance between utilizing i.i.d. and adaptive data.
3491, Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory
Xin Cheng; Di Luo; Xiuying Chen; Lemao Liu; Dongyan Zhao; Rui Yan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, this method is constrained by the quality of the fixed corpus from which memory is retrieved. In this paper, by exploring the duality of the primal problem: better generation also prompts better memory, we propose a novel framework, Selfmem, which addresses this limitation by iteratively employing a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round.
3492, Distributional Policy Evaluation: A Maximum Entropy Approach to Representation Learning
Riccardo Zamboni; Alberto Maria Metelli; Marcello Restelli;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We employ state-aggregation functions as feature functions and we specialize the D-Max-Ent approach into an algorithm, named *D-Max-Ent Progressive Factorization*, which constructs a progressively finer-grained representation of the state space by balancing the trade-off between preserving information (bias) and reducing the effective number of states, i.e., the complexity of the representation space (variance).
3493, An Adaptive Algorithm for Learning with Unknown Distribution Drift
Alessio Mazzetto; Eli Upfal;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We develop and analyze a general technique for learning with an unknown distribution drift.
3494, Latent Space Translation Via Semantic Alignment
Valentino Maiorca; Luca Moschella; Antonio Norelli; Marco Fumero; Francesco Locatello; Emanuele Rodolà;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Different neural models often exhibit similar latent spaces when exposed to semantically similar data; however, this inherent similarity may not always be immediately apparent. Leveraging this observation, our work shows how representations learned from these neural modules can be translated between different pre-trained networks via simpler transformations than previously thought.
3495, Deep Momentum Multi-Marginal Schrödinger Bridge
Tianrong Chen; Guan-Horng Liu; Molei Tao; Evangelos Theodorou;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this article, we extend SB into phase space and propose $\underline{D}$eep $\underline{M}$omentum Multi-Marginal $\underline{S}$chrödinger $\underline{B}$ridge (DMSB), a novel computational framework that learns the smooth measure-valued spline for stochastic systems that satisfy position marginal constraints across time.
3496, Gacs-Korner Common Information Variational Autoencoder
Michael Kleinman; Alessandro Achille; Stefano Soatto; Jonathan Kao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a notion of common information that allows one to quantify and separate the information that is shared between two random variables from the information that is unique to each.
3497, Optimal Exploration for Model-Based RL in Nonlinear Systems
Andrew Wagenmaker; Guanya Shi; Kevin Jamieson;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: While existing work has shown that it is possible to learn a uniformly good model of the system (Mania et al., 2020), in practice, if we aim to learn a good controller with a low cost on the actual system, certain system parameters may be significantly more critical than others, and we therefore ought to focus our exploration on learning such parameters. In this work, we consider the setting of nonlinear dynamical systems and seek to formally quantify, in such settings, (a) which parameters are most relevant to learning a good controller, and (b) how we can best explore so as to minimize uncertainty in such parameters.
3498, ConSpec: Honing in on Critical Steps for Rapid Learning and Generalization in RL
Chen Sun; Wannan Yang; Thomas Jiralerspong; Dane Malenfant; Benjamin Alsbury-Nealy; Yoshua Bengio; Blake Richards;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here, we present a new RL algorithm that uses offline contrastive learning to hone in on critical steps.
3499, Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation
Weihang Dai; Yao DU; Hanru Bai; Xiaomeng Li; Kwang-Ting Cheng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we extend contrastive regression methods to allow unlabeled data to be used in a semi-supervised setting, thereby reducing the reliance on manual annotations.
3500, AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders
Paribesh Regmi; Rui Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Moreover, existing VAE regularization methods largely overlook the importance of network structures and fail to prevent overfitting in deep VAE models with cascades of hidden layers. To address these issues, we propose a Bayesian inference framework that automatically adapts VAE network structures to data and prevent overfitting as they grow deeper.
3501, Learning A Neuron By A Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs
Dmitry Chistikov; Matthias Englert; Ranko Lazic;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise the rank of network parameters.
3502, SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
Zhiqing Xiao; Haobo Wang; Ying Jin; Lei Feng; Gang Chen; Fei Huang; Junbo Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff.
3503, Secure Out-of-Distribution Task Generalization with Energy-Based Models
Shengzhuang Chen; Long-Kai Huang; Jonathan Richard Schwarz; Yilun Du; Ying Wei;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To this end, we build a single coherent framework that supports both detection and adaptation of OOD tasks, while remaining compatible with off-the-shelf meta-learning backbones.
3504, FedNAR: Federated Optimization with Normalized Annealing Regularization
Junbo Li; Ang Li; Chong Tian; Qirong Ho; Eric Xing; Hongyi Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We provide a comprehensive theoretical analysis of FedNAR's convergence rate and conduct extensive experiments on both vision and language datasets with different backbone federated optimization algorithms.
3505, CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence
Bong Gyun Kang; HyunGi Kim; Dahuin Jung; Sungroh Yoon;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, for the first time, we introduce novel algorithmic reasoning (AR) methodology for continual tasks of abstract concepts: CLeAR.
3506, Graph Denoising Diffusion for Inverse Protein Folding
Kai Yi; Bingxin Zhou; Yiqing Shen; Pietro Lió; Yuguang Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose a novel graph denoising diffusion model for inverse protein folding, where a given protein backbone guides the diffusion process on the corresponding amino acid residue types.
3507, Interpretable Prototype-based Graph Information Bottleneck
Sangwoo Seo; Sungwon Kim; Chanyoung Park;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel framework of explainable GNNs, called interpretable Prototype-based Graph Information Bottleneck (PGIB) that incorporates prototype learning within the information bottleneck framework to provide prototypes with the key subgraph from the input graph that is important for the model prediction.
3508, D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts
Fenggen Yu; Qimin Chen; Maham Tanveer; Ali Mahdavi Amiri; Hao Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present D$^2$CSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) representations of 3D CAD shapes.
3509, Boosting Verification of Deep Reinforcement Learning Via Piece-Wise Linear Decision Neural Networks
Jiaxu Tian; Dapeng Zhi; Si Liu; Peixin Wang; Cheng Chen; Min Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The major obstacle lies in the large overestimation introduced inherently during training and then transforming the inexplicable decision-making models, i.e., deep neural networks (DNNs), into easy-to-verify models. In this paper, we propose an inverse transform-then-train approach, which first encodes a DNN into an equivalent set of efficiently and tightly verifiable linear control policies and then optimizes them via reinforcement learning.
3510, Unsupervised Learning for Solving The Travelling Salesman Problem
Yimeng Min; Yiwei Bai; Carla Gomes;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose UTSP, an unsupervised learning (UL) framework for solving the Travelling Salesman Problem (TSP).
3511, PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks
Ian Char; Jeff Schneider;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We assert the PID controller's success shows that only summing and differencing are needed to accumulate information over time for many control tasks. Following this principle, we propose two architectures for encoding history: one that directly uses PID features and another that extends these core ideas and can be used in arbitrary control tasks.
3512, GD-YOLO: Efficient Object Detector Via Gather-and-Distribute Mechanism
Chengcheng Wang; Wei He; Ying Nie; Jianyuan Guo; Chuanjian Liu; Yunhe Wang; Kai Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, we find previous models still suffer from information fusion problem, although Feature Pyramid Network (FPN) and Path Aggregation Network (PANet) have alleviated this. Therefore, this study provides an advanced Gather-and-Distribute mechanism (GD) mechanism, which is realized with convolution and self-attention operations.
3513, Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations
Huiqiao Fu; Kaiqiang Tang; Yuanyang Lu; Yiming Qi; Guizhou Deng; Hongyong Song; Chunlin Chen;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose a novel semi-supervised imitation learning architecture that learns disentangled behavior representations from imbalanced demonstrations using limited labeled data.
3514, RGMIL: Guide Your Multiple-Instance Learning Model with Regressor
Zhaolong Du; Shasha Mao; Yimeng Zhang; Shuiping Gou; Licheng Jiao; Lin Xiong;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, many MIL models paid attentions on analyzing the relationships between instance representations and aggregate them, but neglecting the critical information from the MIL problem itself, which causes difficultly achieving ideal instance-level performance compared with the supervised model. To address this issue, we propose the \textbf{\textit{Regressor-Guided MIL network} (RGMIL)}, which effectively produces discriminative instance-level representations in a general multi-classification scenario.
3515, DrugCLIP: Contrasive Protein-Molecule Representation Learning for Virtual Screening
Bowen Gao; Bo Qiang; Haichuan Tan; Yinjun Jia; Minsi Ren; Minsi Lu; Jingjing Liu; Wei-Ying Ma; Yanyan Lan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel contrastive learning framework, DrugCLIP, by reformulating virtual screening as a dense retrieval task and employing contrastive learning to align representations of binding protein pockets and molecules from a large quantity of pairwise data without explicit binding-affinity scores.
3516, Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
Qian Yu; Yining Wang; Baihe Huang; Qi Lei; Jason Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider a fundamental setting in which the objective function is quadratic, and provide the first tight characterization of the optimal Hessian-dependent sample complexity.
3517, DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning
Alexander Liu; Heng-Jui Chang; Michael Auli; Wei-Ning Hsu; Jim Glass;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we introduce self-distillation and online clustering for self-supervised speech representation learning (DinoSR) which combines masked language modeling, self-distillation, and online clustering.
3518, Theoretical and Practical Perspectives on What Influence Functions Do
Andrea Schioppa; Katja Filippova; Polina Zablotskaia; Ivan Titov;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We show that while most assumptions can be addressed successfully, the parameter divergence poses a clear limitation on the predictive power of IF: influence fades over training time even with deterministic training.
3519, Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning
Zih-Yun Chiu; Yi-Lin Tuan; William Yang Wang; Michael Yip;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we present Knowledge-Grounded RL (KGRL), an RL framework fusing multiple knowledge policies and aiming for human-like efficiency and flexibility.
3520, Coherent Soft Imitation Learning
Joe Watson; Sandy Huang; Nicolas Heess;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This work derives an imitation method that captures the strengths of both methods.
3521, Why Think Step By Step? Reasoning Emerges from The Locality of Experience
Benjamin Prystawski; Michael Li; Noah Goodman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We investigate why and how chain-of-thought reasoning is useful in language models, testing the hypothesis that reasoning is effective when training data consists of local clusters of variables that influence each other strongly.
3522, Finding Safe Zones of Markov Decision Processes Policies
Lee Cohen; Yishay Mansour; Michal Moshkovitz;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We study the complexity of finding optimal SafeZones, and show that in general, the problem is computationally hard.
3523, Lending Interaction Wings to Recommender Systems with Conversational Agents
Jiarui Jin; Xianyu Chen; Fanghua Ye; Mengyue Yang; Yue Feng; Weinan Zhang; Yong Yu; Jun Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose CORE, a new offline-training and online-checking framework to plug a COnversational agent into REcommender systems.
3524, Optimized Covariance Design for AB Test on Social Network Under Interference
Qianyi Chen; Bo Li; Yong Wang; Lu Deng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we strive to balance the bias and variance in designing randomized network experiments.
3525, Doubly Constrained Fair Clustering
John Dickerson; Seyed Esmaeili; Jamie Morgenstern; Claire Jie Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This leaves the understanding of the relations between different fairness notions as an important open problem in fair clustering. In this paper, we take the first step in this direction.
3526, Block Broyden's Methods for Solving Nonlinear Equations
Chengchang Liu; Cheng Chen; Luo Luo; John C.S. Lui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose block variants of both good and bad Broyden's methods, which enjoy explicit local superlinear convergence rates.
3527, Learning Reliable Interpretations with SATNet
Zhaoyu Li; Jinpei Guo; Yuhe Jiang; Xujie Si;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: The goal of bridging logical reasoning and deep learning is essential for advancing AI systems. In this paper, we introduce a framework that addresses this goal by generating interpretable and verifiable logical rules through differentiable learning, without relying on pre-specified logical structures.
3528, VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
Sheng-Yen Chou; Pin-Yu Chen; Tsung-Yi Ho;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents a unified backdoor attack framework (VillanDiffusion) to expand the current scope of backdoor analysis for DMs.
3529, Continuous-time Analysis of Anchor Acceleration
Jaewook Suh; Jisun Park; Ernest Ryu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we analyze continuous-time models of anchor acceleration.
3530, Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
Marcel Kollovieh; Abdul Fatir Ansari; Michael Bohlke-Schneider; Jasper Zschiegner; Hao Wang; Yuyang (Bernie) Wang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we explore the potential of task-agnostic, unconditional diffusion models for several time series applications.
3531, Principled Weight Initialisation for Input-Convex Neural Networks
Pieter-Jan Hoedt; Günter Klambauer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In a set of experiments, we demonstrate that our principled initialisation effectively accelerates learning in ICNNs and leads to better generalisation.
3532, Relational Curriculum Learning for Graph Neural Network
Zheng Zhang; Junxiang Wang; Liang Zhao;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Unfortunately, existing CL strategies are designed for independent data samples and cannot be trivially generalized to handle data dependencies. To address these issues, we propose a novel CL method to gradually incorporates more edges into training according to their difficulty from easy to hard, where the degree of difficulty is measured by how well the edges are expected given the model training status.
3533, Projection-Free Online Convex Optimization Via Efficient Newton Iterations
Khashayar Gatmiry; Zak Mhammedi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: This paper presents new projection-free algorithms for Online Convex Optimization (OCO) over a convex domain $\mathcal{K} \subset \mathbb{R}^d$.
3534, Fast Partitioned Learned Bloom Filter
Atsuki Sato; Yusuke Matsui;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Thus, we propose two methods that can reduce the construction time while maintaining the memory efficiency of PLBF.
3535, A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions
David Loiseaux; Mathieu Carrière; Andrew Blumberg;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this article, we introduce a new general representation framework that leverages recent results on decompositions of multiparameter persistent homology.
3536, Learning Curves for Heterogeneous Feature-Subsampled Ridge Ensembles
Ben Ruben; Cengiz Pehlevan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work we study an ensemble of linear predictors, where individual predictors are fit using ridge regression on a subset of the available features.
3537, The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification
Linhao Qu; xiaoyuan luo; Kexue Fu; Manning Wang; Zhijian Song;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Drawing inspiration from the recent achievements of vision-language models (V-L models) in downstream few-shot classification tasks, we propose a two-level prompt learning MIL framework tailored for pathology, incorporating language prior knowledge.
3538, Gradient Informed Proximal Policy Optimization
Sanghyun Son; Laura Zheng; Ryan Sullivan; Yi-Ling Qiao; Ming Lin;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm.
3539, Learning Invariant Representations of Graph Neural Networks Via Cluster Generalization
Xiao Wang; Donglin Xia; Nian Liu; Chuan Shi;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we experimentally find that the performance of GNNs drops significantly when the structure shift happens, suggesting that the learned models may be biased towards specific structure patterns.
3540, A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
Matthew Bendel; Rizwan Ahmad; Philip Schniter;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In particular, we propose a regularized conditional Wasserstein GAN that generates dozens of high-quality posterior samples per second.
3541, Pitfall of Optimism: Distributional Reinforcement Learning By Randomizing Risk Criterion
Taehyun Cho; Seungyub Han; Heesoo Lee; Kyungjae Lee; Jungwoo Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a novel distributional reinforcement learning that selects actions by randomizing risk criterion without losing the risk-neutral objective.
3542, Preconditioning Matters: Fast Global Convergence of Non-convex Matrix Factorization Via Scaled Gradient Descent
Xixi Jia; Hailin Wang; Jiangjun Peng; Xiangchu Feng; Deyu Meng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we show that precondition helps in accelerating the convergence and prove that scaled gradient descent (ScaledGD) and the alternating scaled gradient descent (AltScaledGD) converge to $\epsilon$-global minima after $O( {\rm ln} \frac{d}{\delta} + {\rm ln} \frac{d}{\epsilon})$ iterations from general random initialization.
3543, Distributionally Robust Linear Quadratic Control
Bahar Taskesen; Dan Iancu; Çağıl Koçyiğit; Daniel Kuhn;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we consider a generalization of the discrete-time, finite-horizon LQG problem, where the noise distributions are unknown and belong to Wasserstein ambiguity sets centered at nominal (Gaussian) distributions.
3544, Sensitivity in Translation Averaging
Lalit Manam; Venu Madhav Govindu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: While there has been much work on robustness to outliers and studies on the uniqueness of the solution, in this paper, we deal with a distinctly different problem of sensitivity in translation averaging under uncertainty.
3545, Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming
Gregory Dexter; Petros Drineas; David Woodruff; Taisuke Yasuda;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we develop new techniques to extend the applicability of sketching-based approaches to the sparse dictionary learning and the Euclidean $k$-means clustering problems.
3546, Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and A Self-attention Network
Zitang Sun; Yen-Ju Chen; Yung-Hao Yang; Shin'ya Nishida;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Here we propose an image-computable model of human motion perception by bridging the gap between human and CV models.
3547, Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks
Feng Chen; Daniel Kunin; Atsushi Yamamura; Surya Ganguli;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overparameterized networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving generalization.
3548, Boosting Spectral Clustering on Incomplete Data Via Kernel Correction and Affinity Learning
Fangchen Yu; Runze Zhao; Zhan Shi; Yiwen Lu; Jicong Fan; Yicheng Zeng; Jianfeng Mao; Wenye Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, incomplete data can lead to inaccurate affinity measures, resulting in degraded clustering performance. To address these issues, we propose an imputation-free framework with two novel approaches to improve spectral clustering on incomplete data.
3549, Computing Optimal Nash Equilibria in Multiplayer Games
Youzhi Zhang; Bo An; Venkatramanan Subrahmanian;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we focus on computing an NE that optimizes a given objective function.
3550, New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
Cornelius Brand; Robert Ganian; Mathis Rocton;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Indeed, while there has been a number of very recent results that establish ever-tighter lower bounds for the problem under linear and ReLU activation functions, little progress has been made towards the identification of novel polynomial-time tractable network architectures. In this article we obtain novel algorithmic upper bounds for training linear- and ReLU-activated neural networks to optimality which push the boundaries of tractability for these problems beyond the previous state of the art.
3551, On The Role of Noise in The Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences
Alireza Fathollah Pour; Hassan Ashtiani;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider the class of noisy multi-layered sigmoid recurrent neural networks with $w$ (unbounded) weights for classification of sequences of length $T$, where independent noise distributed according to $\mathcal{N}(0,\sigma^2)$ is added to the output of each neuron in the network.
3552, Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks
Matthew Farrugia-Roberts;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we give an algorithmic characterisation of unit redundancies and reducible functional equivalence classes for a single-hidden-layer hyperbolic tangent architecture.
3553, Beyond Average Reward in Markov Decision Processes
Alexandre Marthe; Aurélien Garivier; Claire Vernade;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: What are the functionals of the reward that can be computed and optimized exactly in Markov Decision Processes?In the finite-horizon, undiscounted setting, Dynamic Programming (DP) can only handle these operations efficiently for certain classes of statistics. We summarize the characterization of these classes for policy evaluation, and give a new answer for the planning problem.
3554, Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection
Linyan Huang; Zhiqi Li; Chonghao Sima; Wenhai Wang; Jingdong Wang; Yu Qiao; Hongyang Li;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To this end, we introduce VCD, a framework to improve the camera-only apprentice model, including an apprentice-friendly multi-modal expert and temporal-fusion-friendly distillation supervision.
3555, Granger Components Analysis: Unsupervised Learning of Latent Temporal Dependencies
Jacek Dmochowski;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: A new technique for unsupervised learning of time series data based on the notion of Granger Causality is presented.
3556, Nominality Score Conditioned Time Series Anomaly Detection By Point/Sequential Reconstruction
Chih-Yu (Andrew) Lai; Fan-Keng Sun; Zhengqi Gao; Jeffrey H Lang; Duane Boning;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose a framework for unsupervised time series anomaly detection that utilizes point-based and sequence-based reconstruction models.
3557, Adaptive Linear Estimating Equations
Mufang Ying; Koulik Khamaru; Cun-Hui Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For instance, the ordinary least squares (OLS) estimator in an adaptive linear regression model can exhibit non-normal asymptotic behavior, posing challenges for accurate inference and interpretation. In this paper, we propose a general method for constructing debiased estimator which remedies this issue.
3558, Combating Bilateral Edge Noise for Robust Link Prediction
Zhanke Zhou; Jiangchao Yao; Jiaxu Liu; Xiawei Guo; Quanming Yao; LI He; Liang Wang; Bo Zheng; Bo Han;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated. To close this gap, we first conduct an empirical study to disclose that edge noise naturally perturbs both input topology and target label, yielding severe performance degradation and representation collapse. To address this dilemma, we then propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse.
3559, Multiclass Boosting: Simple and Intuitive Weak Learning Criteria
Nataly Brukhim; Amit Daniely; Yishay Mansour; Shay Moran;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being “slightly better than random guessing”.
3560, Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks
Roey Magen; Ohad Shamir;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We provide several new results on the sample complexity of vector-valued linear predictors (parameterized by a matrix), and more generally neural networks.
3561, UniT: A Unified Look at Certified Robust Training Against Text Adversarial Perturbation
Muchao Ye; Ziyi Yin; Tianrong Zhang; Tianyu Du; Jinghui Chen; Ting Wang; Fenglong Ma;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: To mitigate the aforementioned limitations, we propose a unified framework named UniT that enables us to train flexibly in either fashion by working in the word embedding space.
3562, Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case
Taihei Oki; Shinsaku Sakaue;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we present a framework for using predictions to accelerate *M-convex function minimization*, thus complementing previous research and extending the range of discrete optimization algorithms that can benefit from predictions.
3563, Reining Generalization in Offline Reinforcement Learning Via Representation Distinction
Yi Ma; Hongyao Tang; Dong Li; Zhaopeng Meng;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: It has been observed that a considerable portion of the benefits derived from the conservative terms designed by existing offline RL approaches originates from their impact on the learned representation. This observation prompts us to scrutinize the learning dynamics of offline RL, formalize the process of generalization, and delve into the prevalent overgeneralization issue in offline RL.
3564, UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition
Jiancan Zhou; Xi Jia; qiufu li; Linlin Shen; Jinming Duan;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose the unified threshold integrated sample-to-sample based loss (USS loss), which features an explicit unified threshold for distinguishing positive from negative pairs.
3565, A Causal Framework for Decomposing Spurious Variations
Drago Plecko; Elias Bareinboim;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this manuscript, we develop formal tools for decomposing spurious variations in both Markovian and Semi-Markovian models.
3566, ReDS: Offline RL With Heteroskedastic Datasets Via Support Constraints
Anikait Singh; Aviral Kumar; Quan Vuong; Yevgen Chebotar; Sergey Levine;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: For example, at a red light, nearly all human drivers behave similarly by stopping, but when merging onto a highway, some drivers merge quickly, efficiently, and safely, while many hesitate or merge dangerously. Both theoretically and empirically, we show that typical offline RL methods, which are based on distribution constraints fail to learn from data with such non-uniform variability, due to the requirement to stay close to the behavior policy **to the same extent** across the state space.
3567, TOA: Task-oriented Active VQA
xiaoying xing; Mingfu Liang; Ying Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, they may either drop the essential visual information to answer the question correctly or involve irrelevant objects to the task-of-interest. To address this problem, we propose to let large language models make an initial hypothesis according to their knowledge, then actively collect the visual evidence required to verify the hypothesis.
3568, Adaptive Algorithms for Relaxed Pareto Set Identification
Cyrille KONE; Emilie Kaufmann; Laura Richert;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we revisit the fixed-confidence identification of the Pareto optimal set in a multi-objective multi-armed bandit model.
3569, Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees
Veronica Alvarez; Santiago Mazuelas; Jose A. Lozano;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: This paper presents incremental minimax risk classifiers (IMRCs) that effectively exploit forward and backward learning and account for evolving tasks.
3570, Learning Motion Refinement for Unsupervised Face Animation
Jiale Tao; Shuhang Gu; Wen Li; Lixin Duan;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this work, we design a new unsupervised face animation approach to learn simultaneously the coarse and finer motions.
3571, Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction
Feng Wang; Zilong Chen; Guokang Wang; Yafei Song; Huaping Liu;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: In this paper, we propose the Masked Space-Time Hash encoding (MSTH), a novel method for efficiently reconstructing dynamic 3D scenes from multi-view or monocular videos.
3572, Game Solving with Online Learning
Ti-Rong Wu; Hung Guei; Ting Han Wei; Chung-Chin Shih; Jui-Te Chin; I-Chen Wu;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: AlphaZero-based heuristics can be highly inaccurate when evaluating these out-of-distribution positions, which occur throughout the entire search. To address this issue, this paper investigates applying online learning while searching and proposes two methods to learn tailor-designed heuristics for game solving.
3573, Online Ad Allocation with Predictions
Fabian Spaeh; Alina Ene;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: Worst-case algorithms that achieve the ideal competitive ratio are known for both problems, but might act overly conservative given the predictable and usually tame nature of real-world input. Given this discrepancy, we develop an algorithm for both problems that incorporate machine-learned predictions and can thus improve the performance beyond the worst-case.
3574, Ignorance Is Bliss: Robust Control Via Information Gating
Manan Tomar; Riashat Islam; Matthew Taylor; Sergey Levine; Philip Bachman;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: We propose *information gating* as a way to learn parsimonious representations that identify the minimal information required for a task.
3575, Parsel🐍: Algorithmic Reasoning with Language Models By Composing Decompositions
Eric Zelikman; Qian Huang; Gabriel Poesia; Noah Goodman; Nick Haber;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce Parsel, a framework enabling automatic implementation and validation of complex algorithms with code LLMs.
3576, Kerenlized Reinforcement Learning with Order Optimal Regret Bounds
Sattar Vakili; Julia Olkhovskaya;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We propose $\pi$-KRVI, an optimistic modification of least-squares value iteration, when the action-value function is represented by an RKHS.
3577, Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator
Hanzhuo Huang; Yufan Feng; Cheng Shi; Lan Xu; Jingyi Yu; Sibei Yang;
Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View
Highlight: To generate a semantic-coherent video, exhibiting a rich portrayal of temporal semantics such as the whole process of flower blooming rather than a set of ``moving images'', we propose a novel Free-Bloom pipeline that harnesses large language models (LLMs) as the director to generate a semantic-coherence prompt sequence, while pre-trained latent diffusion models (LDMs) as the animator to generate the high fidelity frames.
3578, Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Hao Qin; Kwang-Sung Jun; Chicheng Zhang;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this work, we propose the Kullback-Leibler Maillard Sampling (KL-MS) algorithm, a natural extension of Maillard sampling for achieving KL-style gap-dependent regret bound.
3579, Faster Margin Maximization Rates for Generic Optimization Methods
Guanghui Wang; Zihao Hu; Vidya Muthukumar; Jacob Abernethy;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, while gradient-descent-based algorithms demonstrate fast implicit bias rates, the implicit bias rates of generic optimization methods have been relatively slow. To address this limitation, in this paper, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms.
3580, Diverse Shape Completion Via Style Modulated Generative Adversarial Networks
Wesley Khademi; Fuxin Li;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose a novel conditional generative adversarial network that can produce many diverse plausible completions of a partially observed point cloud.
3581, Policy Finetuning in Reinforcement Learning Via Design of Experiments Using Offline Data
Ruiqi Zhang; Andrea Zanette;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper we propose an algorithm with provable guarantees that can leverage an offline dataset to design a single non-reactive policy for exploration.
3582, Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks
Changhyeon Lee; Seulki Lee;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: In this paper, we propose to approximate the softmax output, which is the key product of the attention mechanism, to reduce its activation memory usage when training attention-based networks (aka Transformers).
3583, 2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression
Alexander Tyurin; Peter Richtarik;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We consider distributed convex optimization problems in the regime when the communication between the server and the workers is expensive in both uplink and downlink directions.
3584, What Planning Problems Can A Relational Neural Network Solve?
Jiayuan Mao; Tomás Lozano-Pérez; Josh Tenenbaum; Leslie Kaelbling;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: However, under what circumstances such a policy can be learned and how efficient the policy will be are not well understood. In this paper, we present a circuit complexity analysis for relational neural networks (such as graph neural networks and Transformers) representing policies for planning problems, by drawing connections with serialized goal regression search (S-GRS).
3585, Generalized Belief Transport
Junqi Wang; PEI WANG; Patrick Shafto;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We introduce a mathematical framework, Generalized Belief Transport (GBT), that unifies and generalizes prior models, including Bayesian inference, cooperative communication and classification, as parameterizations of three learning constraints within Unbalanced Optimal Transport (UOT).
3586, A Trichotomy for Transductive Online Learning
Steve Hanneke; Shay Moran; Jonathan Shafer;
Related Papers Related Patents Related Grants Related Venues Related Experts View
Highlight: We present new upper and lower bounds on the number of learner mistakes in the 'transductive' online learning setting of Ben-David, Kushilevitz and Mansour (1997).