Paper Digest: ICLR 2026 Papers & Highlights
Browse all 5,300+ ICLR 2026 papers, each with a one-sentence highlight. Search them, generate a literature review, and compare papers side by side.
The International Conference on Learning Representations (ICLR) is one of the top machine learning conferences in the world. In 2026, it is to be held in Brazil. To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers and generated one highlight sentence (typically the main topic) for each paper, so readers can quickly get the main idea of each paper. Beyond this list, every paper is positioned in our knowledge graph: users can find related papers, patents, grants and experts for any paper, and research or review a topic using all papers in the proceedings.
Note: ICLR-2026 accepts more than 5,300 papers, this page only includes 500 of them selected by our daily paper digest algorithm. To search for papers presented at ICLR-2026 on a specific topic, please make use of the search by venue (ICLR-2026) service. To summarize the latest research published at ICLR-2026 on a specific topic, you can utilize the review by venue (ICLR-2026) service. If you are interested in browsing papers by author, we have a comprehensive list of ~ 22,000 authors (ICLR-2026). Additionally, you may want to explore our “Best Paper” Digest (ICLR), which lists the most influential ICLR papers since 2018.
Since 2018, Paper Digest has built a foundation of data spanning decades of conferences, journals, and research topics. The platform features a daily digest service that sifts through tens of thousands of new papers, clinical trials, news articles, and community posts, filtering the noise to highlight what matters most to specific interests. Beyond daily updates, dozens of built-in research tools streamline the academic workflow, supporting efficient reading and writing, comprehensive literature reviews, and automated research report generation.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: ICLR 2026 Papers & Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | SAM 3: Segment Anything with Concepts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., “yellow school bus”), image exemplars, or a combination of both. |
Nicolas Carion; Laura Gustafson; Yuan-Ting Hu; Shoubhik Debnath; Ronghang Hu; Didac Suris Coll-Vinent; Chaitanya Ryali; Kalyan Vasudev Alwala; Haitham Khedr; Andrew Huang; Jie Lei; Tengyu Ma; Baishan Guo; Arpit Kalla; Markus Marks; Joseph Greer; Meng Wang; Peize Sun; Roman Rädle; Triantafyllos Afouras; Effrosyni Mavroudi; Katherine Xu; Tsung-Han Wu; Yu Zhou; Liliane Momeni; RISHI HAZRA; Shuangrui Ding; Sagar Vaze; Francois Porcher; Feng Li; Siyuan Li; Aishwarya Kamath; Ho Kei Cheng; Piotr Dollar; Nikhila Ravi; Kate Saenko; Pengchuan Zhang; Christoph Feichtenhofer; |
| 2 | Depth Anything 3: Recovering The Visual Space from Any Views Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. |
Haotong Lin; Sili Chen; Jun Hao Liew; Donny Y. Chen; Zhenyu Li; Yang Zhao; Sida Peng; Hengkai Guo; Xiaowei Zhou; Guang Shi; Jiashi Feng; Bingyi Kang; |
| 3 | Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Cosmos Policy, a simple approach for adapting a large pretrained video model (Cosmos-Predict2) into an effective robot policy through a single stage of post-training on the robot demonstration data collected on the target platform, with no architectural modifications. |
Moo Jin Kim; Yihuai Gao; Tsung-Yi Lin; Yen-Chen Lin; Yunhao Ge; Grace Lam; Percy Liang; Shuran Song; Ming-Yu Liu; Chelsea Finn; Jinwei Gu; |
| 4 | Rubrics As Rewards: Reinforcement Learning Beyond Verifiable Domains Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce $\textbf{Rubrics as Rewards (\textit{RaR})}$, an on-policy reinforcement learning method that extends RLVR beyond verifiable domains by using rubric-based feedback. |
Anisha Gunjal; Anthony Wang; Elaine Lau; Vaskar Nath; Yunzhong He; Bing Liu; Sean M. Hendryx; |
| 5 | Lyra: Generative 3D Scene Reconstruction Via Video Diffusion Model Self-Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a self-distillation framework that aims to distill the implicit 3D knowledge in the video diffusion models into an explicit 3D Gaussian Splatting (3DGS) representation, eliminating the need for multi-view training data. |
Sherwin Bahmani; Tianchang Shen; Jiawei Ren; Jiahui Huang; Yifeng Jiang; Haithem Turki; Andrea Tagliasacchi; David B. Lindell; Zan Gojcic; Sanja Fidler; Huan Ling; Jun Gao; Xuanchi Ren; |
| 6 | Revisiting Multimodal Positional Encoding in Vision–Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through extensive experiments, we identify three key guidelines: positional coherence, full frequency utilization, and preservation of textual priors—ensuring unambiguous layout, rich representation, and faithful transfer from the pre-trained LLM. Based on these insights, we propose Multi-Head RoPE (MHRoPE) and MRoPE-Interleave (MRoPE-I), two simple and plug-and-play variants that require no architectural changes. |
Jie Huang; Xuejing Liu; Sibo Song; RuiBing Hou; Hong Chang; Junyang Lin; Shuai Bai; |
| 7 | Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces the \textbf{Language Confusion Gate} (LCG), a lightweight, plug-in solution that filters tokens during decoding without altering the base LLM. |
Collin Zhang; Fei Huang; Chenhan Yuan; Junyang Lin; |
| 8 | GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce GDPval, a benchmark evaluating AI model capabilities on real-world economically valuable knowledge-work tasks. |
Tejal Patwardhan; Rachel Dias; Elizabeth Proehl; Grace Kim; Michele Wang; Olivia Watkins; Simon Posada Fishman; Marwan Aljubeh; Phoebe Thacker; Laurance Fauconnet; Natalie S. Kim; Samuel Miserendino; Gildas Chabot; David Li; Patrick Chao; Michael Sharman; Alexandra Barr; Amelia Glaese; Jerry Tworek; |
| 9 | A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present A$^2$Search, an annotation-free, end-to-end training framework to recognize and handle ambiguity. |
Fengji Zhang; Xinyao Niu; Chengyang Ying; Guancheng Lin; Zhongkai Hao; Zhou Fan; Chengen Huang; Jacky Keung; Bei Chen; Junyang Lin; |
| 10 | LLMs Get Lost In Multi-Turn Conversation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this work, we perform large-scale simulation experiments to compare LLM performance in single- and multi-turn settings. |
Philippe Laban; Hiroaki Hayashi; Yingbo Zhou; Jennifer Neville; |
| 11 | Early Signs of Steganographic Capabilities in Frontier LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, LLMs could evade monitoring through steganography: Encoding hidden information within seemingly benign generations. In this paper, we evaluate the steganography capabilities in frontier LLMs to better understand the risk they pose. |
Artur Zolkowski; Kei Nishimura-Gasparian; Robert McCarthy; Roland S. Zimmermann; David Lindner; |
| 12 | EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we use Apple Vision Pro to collect EgoDex: the largest and most diverse dataset of dexterous human manipulation to date. |
Ryan Hoque; Peide Huang; David J. Yoon; Mouli sivapurapu; Jian Zhang; |
| 13 | FASA: FREQUENCY-AWARE SPARSE ATTENTION Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose FASA, a novel framework that achieves query-aware token eviction by dynamically predicting token importance. |
Yifei Wang; Yueqi Wang; Zhenrui Yue; Huimin Zeng; Yong Wang; Ismini Lourentzou; Zhengzhong Tu; Xiangxiang Chu; Julian McAuley; |
| 14 | Evaluating Memory in LLM Agents Via Incremental Multi-Turn Interactions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, based on classic theories from memory science and cognitive science, we identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and selective forgetting. |
Yuanzhe Hu; Yu Wang; Julian McAuley; |
| 15 | RewardBench 2: Advancing Reward Model Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we describe our benchmark construction process and report how existing models perform on it, while quantifying and providing new insights on how performance on the benchmark correlates with downstream use of the models in both inference-time scaling algorithms, like best-of-N sampling, and RLHF training algorithms like proximal policy optimization. |
Saumya Malik; Valentina Pyatkin; Sander Land; Jacob Morrison; Noah A. Smith; Hannaneh Hajishirzi; Nathan Lambert; |
| 16 | X-VLA: Soft-Prompted Transformer As Scalable Cross-Embodiment Vision-Language-Action Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt approach with minimally added parameters, by infusing prompt learning concepts into cross-embodiment robot learning and introducing separate sets of learnable embeddings for each distinct data source. |
Jinliang Zheng; Jianxiong Li; Zhihao Wang; Dongxiu Liu; Xirui Kang; Yuchun Feng; Yinan Zheng; Jiayin Zou; Yilun Chen; Jia Zeng; Tai Wang; Ya-Qin Zhang; Jingjing Liu; Xianyuan Zhan; |
| 17 | DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: For RL training, to reduce the variance of token log-likelihood estimates and maintain training efficiency, we propose coupled-GRPO, a novel sampling scheme that constructs complementary mask noise for completions used in training. |
Shansan Gong; Ruixiang ZHANG; Huangjie Zheng; Jiatao Gu; Navdeep Jaitly; Lingpeng Kong; Yizhe Zhang; |
| 18 | Pre-training Under Infinite Compute Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We first show that existing data-constrained approaches of increasing epoch count and parameter count overfit, and we improve upon such recipes by tuning regularization, finding that the optimal weight decay is $30\times$ larger than standard practice. Since our regularized recipe monotonically decreases loss following a power law in parameter count, we estimate its best possible performance via the \textbf{asymptote} of its scaling law rather than the performance at a fixed compute budget. We then identify that ensembling independently trained models achieves a significantly lower loss asymptote than the regularized recipe. |
Konwoo Kim; Suhas Kotha; Percy Liang; Tatsunori Hashimoto; |
| 19 | RL’s Razor: Why Online Reinforcement Learning Forgets Less Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis reveals that on-policy RL is implicitly biased towards KL-minimal solutions among the many that solve the new task, whereas SFT can converge to distributions arbitrarily far from the base model. |
Idan Shenfeld; Jyothish Pari; Pulkit Agrawal; |
| 20 | Scaling Agents Via Continual Pre-training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on this approach, we develop a deep research agent model named AgentFounder. |
Liangcai Su; Zhen Zhang; Guangyu Li; Zhuo Chen; Chenxi Wang; Maojia Song; Xinyu Wang; Kuan Li; Jialong Wu; Xuanzhong Chen; Zile Qiao; Zhongwang Zhang; Huifeng Yin; Shihao Cai; Runnan Fang; Zhengwei Tao; Wenbiao Yin; Rui Ye; Yong Jiang; Ningyu Zhang; Pengjun Xie; Fei Huang; Kai Ye; Kewei Tu; Chenxiong Qian; Jingren Zhou; |
| 21 | Epistemic Uncertainty Quantification To Improve Decisions From Black-Box Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Distinguishing epistemic uncertainty (model ignorance) from aleatoric uncertainty (task randomness) is critical for reliable AI systems, yet standard confidence evaluation metrics … |
Sébastien Melo; Gaël Varoquaux; Marine Le Morvan; |
| 22 | Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper systematically investigates the impact of RLVR on LLM reasoning. |
Xumeng Wen; Zihan Liu; Shun Zheng; Shengyu Ye; Zhirong Wu; Yang Wang; Zhijian Xu; Xiao Liang; Junjie Li; Ziming Miao; Jiang Bian; Mao Yang; |
| 23 | Spatial Mental Modeling from Limited Views Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Adding reinforcement learning pushed performance even further to 70.7% (+32.9%). Our key insight is that such scaffolding of spatial mental models, actively constructing and utilizing internal structured spatial representations with flexible reasoning processes, significantly improves understanding of unobservable space. |
Qineng Wang; Baiqiao Yin; Pingyue Zhang; Jianshu Zhang; Kangrui Wang; Zihan Wang; Jieyu Zhang; Keshigeyan Chandrasegaran; Han Liu; Ranjay Krishna; Saining Xie; Jiajun Wu; Li Fei-Fei; Manling Li; |
| 24 | ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit signs of embodied cognition? To investigate this, we introduce **ENACT**, a benchmark that probes this question through world modeling from egocentric interaction. |
Qineng Wang; Wenlong Huang; Yu Zhou; Hang Yin; Tianwei Bao; Jianwen Lyu; Weiyu Liu; Ruohan Zhang; Jiajun Wu; Li Fei-Fei; Manling Li; |
| 25 | Principled RL for Diffusion LLMs Emerges from A Sequence-Level Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The core difficulty lies in likelihood approximation: while autoregressive models naturally provide token-level conditional probabilities essential for token-level RL objectives (e.g., GRPO), dLLMs generate sequences through iterative non-autoregressive denoising steps that lack this factorization. To address this fundamental mismatch, we propose ELBO-based Sequence-level Policy Optimization (ESPO), a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy. |
Jingyang Ou; Jiaqi Han; Minkai Xu; Shaoxuan Xu; Jianwen Xie; Stefano Ermon; Yi Wu; Chongxuan Li; |
| 26 | WebWatcher: Breaking New Frontiers of Vision-Language Deep Research Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This makes multimodal deep research highly challenging, as such agents require much stronger perceptual, logical, and knowledge-based reasoning abilities, as well as proficiency in more sophisticated tools. To address this limitation, we introduce WebWatcher, a multimodal agent for deep research with joint reasoning ability across both visual and textual modalities. |
Xinyu Geng; Peng Xia; Zhen Zhang; Xinyu Wang; Qiuchen Wang; Ruixue Ding; Chenxi Wang; Jialong Wu; Kuan Li; Yida Zhao; Huifeng Yin; Yong Jiang; Pengjun Xie; Fei Huang; Huaxiu Yao; Yi R. Fung; Jingren Zhou; |
| 27 | Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This property, referred to as \emph{asymmetric verification}, highlights the strong potential of test-time scaling. In this work, we study both sequential and parallel test-time scaling of deep search agents, motivated by the intuition that verification in this setting is often much easier than generation. |
Weihao Zeng; Keqing He; Chuqiao Kuang; Xiaoguang Li; Junxian He; |
| 28 | WebSailor-V2: Bridging The Chasm to Proprietary Agents Via Synthetic Data and Scalable Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To significantly advance the capabilities of open-source web agents, we present WebSailor-V2, a complete post-training pipeline encompassing data construction, Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL). |
Kuan Li; Zhongwang Zhang; Huifeng Yin; Rui Ye; Yida Zhao; Liwen Zhang; Litu Ou; Ding-Chu Zhang; Xixi Wu; Xinmiao Yu; Jialong Wu; Xinyu Wang; Zile Qiao; Zhen Zhang; Yong Jiang; Pengjun Xie; Fei Huang; Zhi-Qin John Xu; Shuai Wang; Minhao Cheng; Jingren Zhou; |
| 29 | Inpainting-Guided Policy Optimization for Diffusion Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce IGPO (Inpainting Guided Policy Optimization), an RL framework that strategically inserts partial ground-truth reasoning traces during online sampling. |
Siyan Zhao; Mengchen Liu; Jing Huang; Miao Liu; Chenyu Wang; Bo Liu; Yuandong Tian; Guan Pang; Sean Bell; Aditya Grover; Feiyu Chen; |
| 30 | Beyond Magnitude: Leveraging Direction of RLVR Updates for LLM Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we argue that the direction of updates is a more critical lens for understanding RLVR’s effects, which can be captured by the signed, token-level log probability difference $\Delta\log p$ between the base and final RLVR models. |
Kexin Huang; Haoming Meng; Junkang Wu; Jinda Lu; Chiyu Ma; Ziqian Chen; Xue Wang; Bolin Ding; Jiancan Wu; Xiang Wang; Xiangnan He; Guoyin Wang; Jingren Zhou; |
| 31 | Sparse But Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a systematic empirical study of RLVR’s distributional effects across three complementary axes: (1) token-level distributional shifts, (2) functional validation via cross-sampling interventions, and (3) exploratory investigations of advantage signal modulation based on token divergence. |
Haoming Meng; Kexin Huang; Shaohang Wei; Chiyu Ma; Shuo Yang; Xue Wang; Guoyin Wang; Bolin Ding; Jingren Zhou; |
| 32 | WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and monolithic generation paradigms that include redundant, irrelevant evidence, suffering from hallucination issues and low citation accuracy. To address these challenges, we introduce \textbf{WebWeaver}, a novel dual-agent framework that emulates the human research process. |
Zijian Li; Xin Guan; Bo Zhang; Shen Huang; Houquan Zhou; Shaopeng Lai; Ming Yan; Yong Jiang; Pengjun Xie; Fei Huang; Jun Zhang; Jingren Zhou; |
| 33 | ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: A key limitation, however, is their failure to learn from this accumulated experience, forcing them to discard valuable insights and repeat past errors. Unlike prior works that primarily store raw experience or successful routines, we propose ReasoningBank, a novel memory framework that allows an agent to self-curate generalizable reasoning strategies from both its successful and failed experiences for future leverage. |
Siru Ouyang; Jun Yan; I-Hung Hsu; Yanfei Chen; Ke Jiang; Zifeng Wang; Rujun Han; Long Le; Samira Daruki; Xiangru Tang; Vishy Tirumalashetty; George Lee; Mahsan Rofouei; Hangfei Lin; Jiawei Han; Chen-Yu Lee; Tomas Pfister; |
| 34 | Kevin: Multi-Turn RL for Generating CUDA Kernels Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present Kevin the Kernel Writer, the first model trained with multi-turn RL for CUDA kernel generation and optimization. |
Carlo Baronio; Pietro Marsella; Ben Pan; Simon Guo; Silas Alberti; |
| 35 | Theory of Space: Can Foundation Models Construct Spatial Beliefs Through Active Exploration? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In particular, it remains unclear whether and how these models can decide what to observe next in order to build and maintain a coherent spatial belief over time. We therefore propose \tos, defined as an agent’s ability to actively acquire information through self-directed, active exploration and to construct, revise, and exploit a spatial belief from sequential, partial observations. |
Pingyue Zhang; Zihan Huang; Yue Wang; Jieyu Zhang; Letian Xue; Zihan Wang; Qineng Wang; Keshigeyan Chandrasegaran; Ruohan Zhang; Yejin Choi; Ranjay Krishna; Jiajun Wu; Li Fei-Fei; Manling Li; |
| 36 | On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning Via Dynamic Weighting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose CHORD, a framework for Controllable Harmonization of On- and Off-Policy Reinforcement Learning via Dynamic Weighting, which reframes SFT not as a separate stage but as a dynamically weighted auxiliary objective within the on-policy RL process. |
Wenhao Zhang; Yuexiang Xie; Yuchang Sun; Yanxi Chen; Guoyin Wang; Yaliang Li; Bolin Ding; Jingren Zhou; |
| 37 | IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce IterResearch, a novel iterative deep-research paradigm that reformulates long-horizon research as a Markov Decision Process with strategic workspace reconstruction. |
Guoxin Chen; Zile Qiao; Xuanzhong Chen; Donglei Yu; Haotian Xu; Xin Zhao; Ruihua Song; Wenbiao Yin; Huifeng Yin; Liwen Zhang; Kuan Li; Minpeng Liao; Yong Jiang; Pengjun Xie; Fei Huang; Jingren Zhou; |
| 38 | ReTool: Reinforcement Learning for Strategic Tool Use in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: While reasoning models trained with reinforcement learning (RL) excel in reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex equation solving—areas where computational tools like code interpreters (CI) demonstrate distinct advantages. To bridge this gap, we propose ReTool, which enhances long-form reasoning with tool-integrated learning, including two key features: (1) dynamic interleaving of real-time code execution within natural language reasoning processes, and (2) an automated RL paradigm that allows policy rollouts with multi-turn real-time code execution and teaches the model in learning when and how to invoke tools based on outcome feedback. |
Jiazhan Feng; Shijue Huang; Xingwei Qu; Ge Zhang; Yujia Qin; Baoquan Zhong; Chengquan Jiang; Jinxin Chi; Wanjun Zhong; |
| 39 | ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV) caching, and incoherent generation arising from learning dependencies over an intractable space of token combinations. To address these limitations, we introduce ReFusion, a novel masked diffusion model that achieves superior performance and efficiency by elevating parallel decoding from the token level to a higher slot level, where each slot is a fixed-length, contiguous sub-sequence. |
Jia-Nan Li; Jian Guan; Wei Wu; Chongxuan Li; |
| 40 | WebShaper: Agentically Data Synthesizing Via Information-Seeking Formalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To mitigate, we propose a formalization-driven IS data synthesis framework WebShaper, which systematically formalizes IS tasks using set-theoretic constructs. |
Zhengwei Tao; Jialong Wu; Wenbiao Yin; Pu Wu; Junkai Zhang; Baixuan Li; Haiyang SHEN; Kuan Li; Liwen Zhang; Xinyu Wang; Wentao Zhang; Yong Jiang; Pengjun Xie; Fei Huang; Jingren Zhou; |
| 41 | BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce \textbf{BOTS}, a unified framework for \textbf{B}ayesian \textbf{O}nline \textbf{T}ask \textbf{S}election in LLM reinforcement finetuning. |
Qianli Shen; Daoyuan Chen; Yilun Huang; Zhenqing Ling; Yaliang Li; Bolin Ding; Jingren Zhou; |
| 42 | Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised Metrics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Second, evaluation is typically reduced to a single pass rate, which collapses diverse behaviors into one score and obscures whether failures stem from inadequate search, poor knowledge use, or inappropriate refusal. To address these issues, we present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox that ensures full traceability of model actions, and a holistic evaluation framework that separates search sufficiency, knowledge utilization, and refusal behavior. |
Maojia Song; Liu Renhang; Xinyu Wang; Yong Jiang; Pengjun Xie; Fei Huang; Soujanya Poria; Jingren Zhou; |
| 43 | RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Yet despite this momentum, it remains difficult to gauge how close we are to this goal, as the field lacks a reproducible, large-scale benchmark for systematic evaluation. To address this gap, we present RoboCasa365, a comprehensive robot simulation benchmark for everyday tasks. |
Soroush Nasiriany; Sepehr Nasiriany; Abhiram Maddukuri; Yuke Zhu; |
| 44 | DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This constraint severely degrades code infilling performance when the predefined mask size mismatches the ideal completion length. To address this, we propose DreamOn, a novel diffusion framework that enables dynamic, variable-length generation. |
Zirui Wu; Lin Zheng; Zhihui Xie; Jiacheng Ye; Jiahui Gao; Shansan Gong; Yansong Feng; Zhenguo Li; Wei Bi; Guorui Zhou; Lingpeng Kong; |
| 45 | MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MMSearch-Plus, a 311-task benchmark that enforces multimodal understanding by requiring extraction and propagation of fine-grained visual cues through iterative image–text retrieval and cross-validation under retrieval noise. |
Xijia Tao; Teng Yihua; Xinxing Su; Xinyu Fu; Jihao Wu; Chaofan Tao; Ziru Liu; Haoli Bai; Rui Liu; Lingpeng Kong; |
| 46 | OpenThoughts: Data Recipes for Reasoning Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Yet, there are still many open questions about the best train- ing recipes for reasoning since state-of-the-art models often rely on proprietary datasets with little to no public information available. To address this, the goal of the OpenThoughts project is to create open-source datasets for training reasoning models. |
Etash Kumar Guha; Ryan Marten; Sedrick Keh; Negin Raoof; Georgios Smyrnis; Hritik Bansal; Marianna Nezhurina; Jean Mercat; Trung Vu; Zayne Rea Sprague; Ashima Suvarna; Benjamin Feuer; Leon Liangyu Chen; Zaid Khan; Eric Frankel; Sachin Grover; Caroline Choi; Niklas Muennighoff; Shiye Su; Wanjia Zhao; John Yang; Shreyas Pimpalgaonkar; Kartik sharma; Charlie Cheng-Jie Ji; Yichuan Deng; Sarah M Pratt; Vivek Ramanujan; Jon Saad-Falcon; Stutee Acharya; Jeffrey Li; Achal Dave; Alon Albalak; Kushal Arora; Blake Wulfe; Chinmay Hegde; Greg Durrett; Sewoong Oh; Mohit Bansal; Saadia Gabriel; Aditya Grover; Kai-Wei Chang; Vaishaal Shankar; Aaron Gokaslan; Mike A Merrill; Tatsunori Hashimoto; Yejin Choi; Jenia Jitsev; Reinhard Heckel; Maheswaran Sathiamoorthy; Alex Dimakis; Ludwig Schmidt; |
| 47 | Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we present Terminal-Bench 1.5: a carefully curated hard benchmark composed of 74 tasks in computer terminal environments inspired by problems from real workflows. |
Mike A Merrill; Alexander Glenn Shaw; Nicholas Carlini; Boxuan Li; Harsh Raj; Ivan Bercovich; Lin Shi; Jeong Yeon Shin; Thomas Walshe; E. Kelly Buchanan; Junhong Shen; Guanghao Ye; Haowei Lin; Jason Poulos; Maoyu Wang; Marianna Nezhurina; Di Lu; Orfeas Menis Mastromichalakis; Zhiwei Xu; Zizhao Chen; Yue Liu; Robert Zhang; Leon Liangyu Chen; Anurag Kashyap; Jan-Lucas Uslu; Jeffrey Li; Jianbo Wu; Minghao Yan; Song Bian; Vedang Sharma; Ke Sun; Steven Dillmann; Akshay Anand; Andrew Lanpouthakoun; Bardia Koopah; Changran Hu; Etash Kumar Guha; Gabriel H. S. Dreiman; Jiacheng Zhu; Karl Krauth; Li Zhong; Niklas Muennighoff; Robert Kwesi Amanfu; Shangyin Tan; Shreyas Pimpalgaonkar; Tushar Aggarwal; Xiangning Lin; Xin Lan; Xuandong Zhao; Yiqing Liang; Yuanli Wang; Zilong Wang; Changzhi Zhou; David Heineman; Hange Liu; Harsh Trivedi; John Yang; Junhong Lin; Manish Shetty; Michael Yang; Nabil Omi; Negin Raoof; Shanda Li; Terry Yue Zhuo; Wuwei Lin; Yiwei Dai; Yuxin Wang; Wenhao Chai; Shang Zhou; Dariush Wahdany; Ziyu She; Jiaming Hu; Zhikang Dong; Yuxuan Zhu; Sasha Cui; Ahson Saiyed; Arinbjörn Kolbeinsson; Christopher Michael Rytting; Ryan Marten; Yixin Wang; Jenia Jitsev; Alex Dimakis; Andy Konwinski; Ludwig Schmidt; |
| 48 | OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce OmniSpatial, a comprehensive and challenging benchmark for spatial reasoning, grounded in cognitive psychology. |
Mengdi Jia; Zekun Qi; Shaochen Zhang; Wenyao Zhang; XinQiang Yu; Jiawei He; He Wang; Li Yi; |
| 49 | OptimalThinkingBench: Evaluating Over and Underthinking in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce OptimalThinkingBench, a unified benchmark that jointly evaluates overthinking and underthinking in LLMs and also encourages the development of optimally-thinking models that balance performance and efficiency. |
Pranjal Aggarwal; Seungone Kim; Jack Lanchantin; Sean Welleck; Jason E Weston; Ilia Kulikov; Swarnadeep Saha; |
| 50 | Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unfortunately, proving that most changes are net beneficial is impossible in practice. We introduce the Darwin Gödel Machine (DGM), a novel self-improving system that iteratively modifies its own code (thereby also improving its ability to modify its own codebase) and empirically validates each change using coding benchmarks. |
Jenny Zhang; Shengran Hu; Cong Lu; Robert Tjarko Lange; Jeff Clune; |
| 51 | Dual Goal Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce dual goal representations for goal-conditioned reinforcement learning (GCRL). |
Seohong Park; Deepinder Mann; Sergey Levine; |
| 52 | Transitive RL: Value Learning Via Divide and Conquer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present Transitive Reinforcement Learning (TRL), a new value learning algorithm based on a divide-and-conquer paradigm. |
Seohong Park; Aditya Oberai; Pranav Atreya; Sergey Levine; |
| 53 | LightMem: Lightweight and Efficient Memory-Augmented Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems. |
Jizhan Fang; Xinle Deng; Haoming Xu; Ziyan Jiang; Yuqi Tang; Ziwen Xu; Shumin Deng; Yunzhi Yao; Mengru Wang; Shuofei Qiao; Huajun Chen; Ningyu Zhang; |
| 54 | Dynamic Chunking for End-to-End Hierarchical Sequence Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content- and context- dependent segmentation strategies learned jointly with the rest of the model. |
Sukjun Hwang; Brandon Wang; Albert Gu; |
| 55 | Universal Model Routing for Efficient LLM Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test time. We propose UniRoute, a new approach to this problem that relies on representing each LLM as afeature vector, derived based on predictions on a set of representative prompts. |
Wittawat Jitkrittum; Harikrishna Narasimhan; Ankit Singh Rawat; Jeevesh Juneja; Congchao Wang; Zifeng Wang; Alec Go; Chen-Yu Lee; Pradeep Shenoy; Rina Panigrahy; Aditya Krishna Menon; Sanjiv Kumar; |
| 56 | Ctrl-World: A Controllable Generative World Model for Robot Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we make a step forward by introducing a controllable multi-view world model that can be used to evaluate and improve the instruction-following ability of generalist robot policies. |
Yanjiang Guo; Lucy Xiaoyang Shi; Jianyu Chen; Chelsea Finn; |
| 57 | Spatially Guided Training for Vision-Language-Action Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SP-VLA, a dual-system **V**ision–**L**anguage–**A**ction framework that leverages **S**patial **P**riors as a bridge between linguistic instructions and embodiment-specific control.We will release code, data, and model checkpoints to support future research. |
Jinhui Ye; Fangjing Wang; Ning Gao; Junqiu Yu; Zhu Yangkun; Bin Wang; Jinyu Zhang; Weiyang Jin; Yanwei Fu; Feng Zheng; Yilun Chen; Jiangmiao Pang; |
| 58 | RM-R1: Reward Modeling As Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1. |
Xiusi Chen; Gaotang Li; Ziqi Wang; Bowen Jin; Cheng Qian; Yu Wang; Hongru WANG; Yu Zhang; Denghui Zhang; Tong Zhang; Hanghang Tong; Heng Ji; |
| 59 | WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce WorldSense, the first benchmark to assess the multi-modal video understanding, that simultaneously encompasses visual, audio, and text inputs. |
Jack Hong; Shilin Yan; Jiayin Cai; Xiaolong Jiang; Yao Hu; Weidi Xie; |
| 60 | J1: Incentivizing Thinking in LLM-as-a-Judge Via Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce J1, a reinforcement learning framework for teaching LLM judges to think before making decisions. |
Chenxi Whitehouse; Tianlu Wang; Ping Yu; Xian Li; Jason E Weston; Ilia Kulikov; Swarnadeep Saha; |
| 61 | RF-DETR: Neural Architecture Search for Real-Time Detection Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Rather than simply fine-tuning a heavy-weight vision-language model (VLM) for new domains, we introduce RF-DETR, a light-weight specialist detection transformer that discovers accuracy-latency Pareto curves for any target dataset with weight-sharing neural architecture search (NAS). |
Isaac Robinson; Peter Robicheaux; Matvei Popov; Deva Ramanan; Neehar Peri; |
| 62 | DeepEyesV2: Toward Agentic Multimodal Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce DeepEyesV2 and explore how to build an agentic multimodal model from the perspectives of data construction, training methods, and model evaluation. |
Jack Hong; Chenxiao Zhao; ChengLIn Zhu; Weiheng Lu; Guohai Xu; XingYu; |
| 63 | ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present ChronoEdit, a framework that reframes image editing as a video generation problem. |
Jay Zhangjie Wu; Xuanchi Ren; Tianchang Shen; Tianshi Cao; Kai He; Yifan Lu; Ruiyuan Gao; Enze Xie; Shiyi Lan; Jose M. Alvarez; Jun Gao; Sanja Fidler; Zian Wang; Huan Ling; |
| 64 | Speculative Actions: A Lossless Framework for Faster AI Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by speculative execution in microprocessors and speculative decoding in LLM inference, we propose speculative actions—a lossless framework that predicts likely actions using faster models, enabling multiple API calls to be executed in parallel. |
Naimeng Ye; Arnav Ahuja; Georgios Liargkovas; Yunan Lu; Kostis Kaffes; Tianyi Peng; |
| 65 | Scaling Up Memory for Robotic Control Via Experience Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a hierarchical policy framework, where the high-level policy is trained to select and track previous task-relevant keyframes from its experience. |
Ajay Sridhar; Jennifer Pan; Satvik Sharma; Chelsea Finn; |
| 66 | RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address more effective reasoning, we introduce reasoning abstractions: concise natural language descriptions of procedural and factual knowledge that guide the model toward learning successful reasoning. |
Yuxiao Qu; Anikait Singh; Yoonho Lee; Amrith Setlur; Ruslan Salakhutdinov; Chelsea Finn; Aviral Kumar; |
| 67 | LeRobot: An Open-Source Library for End-to-End Robot Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present lerobot, an open-source library that integrates across the entire robotics stack, from low-level middleware communication for motor controls to large-scale dataset collection, storage and streaming. |
Remi Cadene; Simon Alibert; Francesco Capuano; Michel Aractingi; Adil Zouitine; Pepijn Kooijmans; Jade Choghari; Martino Russi; Caroline Pascal; Steven Palma; Dana Aubakirova; Mustafa Shukor; Jess Moss; Alexander Soare; Quentin Lhoest; Quentin Gallouédec; Thomas Wolf; |
| 68 | The Open Proof Corpus: A Large-Scale Study of LLM-Generated Mathematical Proofs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present the Open Proof Corpus (OPC), a dataset comprising over 5,000 human-evaluated proofs produced by state-of-the-art LLMs. |
Jasper Dekoninck; Ivo Petrov; Kristian Minchev; Miroslav Marinov; Maria Drencheva; Lyuba Konova; Milen Milenov Shumanov; Kaloyan Tsvetkov; Nikolay Drenchev; Lazar D. Todorov; Kalina Nikolova; Nikolay Georgiev; Vanesa Kalinkova; Margulan Ismoldayev; Mislav Balunovic; Martin Vechev; |
| 69 | Constitutional Classifiers++: Efficient Production-Grade Defenses Against Universal Jailbreaks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to previous-generation defenses. |
Hoagy Cunningham; Jerry Wei; Zihan Wang; Andrew Persic; Alwin Peng; Jordan Abderrachid; Raj Agarwal; Bobby Chen; Andy Dau; Alek Dimitriev; Logan Howard; Yijin Hua; Rob Gilson; Mu Lin; Christopher Liu; Vladimir Mikulik; Rohit Mittapalli; Clare O’Hara; Jin Pan; Nikhil Saxena; Alex Silverstein; Yue Song; Giulio Zhou; Jan Leike; Jared Kaplan; Ethan Perez; Mrinank Sharma; |
| 70 | CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence Under Partial Observations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify three core cognitive challenges hindering this transition: spatial reasoning, long-horizon state tracking via mental simulation, and active exploration under partial observation. To isolate and evaluate these faculties, we introduce \textbf{CubeBench}, a novel generative benchmark centered on the Rubik’s Cube. |
Huan-ang Gao; Zikang Zhang; Tianwei Luo; Kaisen Yang; Xinzhe Juan; Jiahao Qiu; Tianxing Chen; Bingxiang He; Hao Zhao; Hao Zhou; Shilong Liu; Mengdi Wang; |
| 71 | OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a curation and synthesis pipeline that generates 24M single-modal and omni-modal conversations. |
Hanrong Ye; Chao-Han Huck Yang; Arushi Goel; Wei Huang; Zhen Wan; Jinchuan Tian; An-Chieh Cheng; Ligeng Zhu; Yuanhang Su; Yuming Lou; Yong-Xiang Lin; Dong Yang; Sreyan Ghosh; Zhijian Liu; Yukang Chen; Ehsan Jahangiri; Ambrish Dantrey; Daguang Xu; Ehsan Hosseini-Asl; Seyed Danial Mohseni Taheri; Vidya Nariyambut Murali; Sifei Liu; Yao Lu; Oluwatobi Olabiyi; Yu-Chiang Frank Wang; Rafael Valle; Bryan Catanzaro; Andrew Tao; Song Han; Jan Kautz; Hongxu Yin; Pavlo Molchanov; |
| 72 | Large Scale Diffusion Distillation Via Score-Regularized Continuous-Time Consistency Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our investigation reveals fundamental quality limitations of sCM in fine-detail generation, which we attribute to error accumulation and the “mode-covering” nature of its forward-divergence objective. To remedy this, we propose the score-regularized continuous-time consistency model (rCM), which incorporates score distillation as a long-skip regularizer. |
Kaiwen Zheng; Yuji Wang; Qianli Ma; Huayu Chen; Jintao Zhang; Yogesh Balaji; Jianfei Chen; Ming-Yu Liu; Jun Zhu; Qinsheng Zhang; |
| 73 | Mamba-3: Improved Sequence Modeling Using State Space Principles Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Guided by an inference-first perspective, we introduce three core methodological improvements inspired by the state-space model viewpoint of linear models. |
Aakash Lahoti; Kevin Li; Berlin Chen; Caitlin Wang; Aviv Bick; J Zico Kolter; Tri Dao; Albert Gu; |
| 74 | Flow Matching Policy Gradients Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm that brings flow matching into the policy gradient framework. |
David McAllister; Songwei Ge; Brent Yi; Chung Min Kim; Ethan Weber; Hongsuk Choi; Haiwen Feng; Angjoo Kanazawa; |
| 75 | Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large Language Models (LLMs) often struggle with challenging, multi-step reasoning problems due to a fundamental learning gap — Reinforcement Learning with Verifiable Rewards (RLVR) suffers from sparse rewards when correct solutions are rarely sampled, while Supervised Fine-Tuning (SFT) tends to overfit to long demonstrations through rigid token mimicry. To bridge this gap, we introduce Supervised Reinforcement Learning (SRL), a framework that reformulates problem-solving as a sequence of logical actions. |
Yihe Deng; I-Hung Hsu; Jun Yan; Zifeng Wang; Rujun Han; Gufeng Zhang; Yanfei Chen; Wei Wang; Tomas Pfister; Chen-Yu Lee; |
| 76 | Flipping The Dialogue: Training and Evaluating User Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Instead, we introduce purpose-built User Language Models (User LMs) – models post-trained to simulate human users in multi-turn conversations. |
Tarek Naous; Philippe Laban; Wei Xu; Jennifer Neville; |
| 77 | Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper describes RLCR (Reinforcement Learning with Calibration Rewards), an approach to training reasoning models that jointly improves accuracy and calibrated confidence estimation. |
Mehul Damani; Isha Puri; Stewart Slocum; Idan Shenfeld; Leshem Choshen; Yoon Kim; Jacob Andreas; |
| 78 | Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce **Gaia2**, a benchmark for evaluating large language model agents in realistic, asynchronous environments. |
Romain Froger; Pierre Andrews; Matteo Bettini; Amar Budhiraja; Ricardo Silveira Cabral; Virginie Do; Emilien Garreau; Jean-Baptiste Gaya; Hugo Laurençon; Maxime Lecanu; Kunal Malkan; Dheeraj Mekala; Pierre Menard; Gerard Moreno-Torres Bertran; Ulyana Piterbarg; Mikhail Plekhanov; Mathieu Rita; Andrey Rusakov; Vladislav Vorotilov; Mengjue Wang; Ian Yu; Amine Benhalloum; Grégoire Mialon; Thomas Scialom; |
| 79 | TaskCraft: Automated Generation of Agentic Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce TaskCraft, the first automated workflow for generating scalable, multitool, and verifiable agentic tasks of difficulty. |
Dingfeng Shi; Jingyi Cao; Qianben Chen; Weichen Sun; Weizhen Li; Hongxuan Lu; Fangchen Dong; Tianrui Qin; King Zhu; Minghao Liu; Yuchen Eleanor Jiang; Jian Yang; Ge Zhang; Jiaheng Liu; Changwang Zhang; Jun Wang; Wangchunshu Zhou; |
| 80 | R-Zero: Self-Evolving Reasoning LLM from Zero Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-tuning or reinforcement learning, which poses a fundamental bottleneck to advancing AI systems toward capabilities beyond human intelligence. To overcome this limitation, we introduce R-Zero, a fully autonomous framework that generates its own training data from scratch. |
Chengsong Huang; Wenhao Yu; Xiaoyang Wang; Hongming Zhang; Zongxia Li; Ruosen Li; Jiaxin Huang; Haitao Mi; Dong Yu; |
| 81 | Reinforcement Learning for Machine Learning Engineering Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that in environments such as MLE where a good verifier is available, adapting the LM parameters through gradient updates can be more effective in utilizing compute and agent’s experience. |
Sherry Yang; Joy He-Yueya; Percy Liang; |
| 82 | On The Theoretical Limitations of Embedding-Based Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we demonstrate that we may encounter these theoretical limitations in realistic settings with extremely simple queries.We then create a realistic dataset called LIMIT that stress tests models based on these theoretical results, and observe that even state-of-the-art models fail on this dataset despite the simple nature of the task. |
Orion Weller; Michael Boratko; Iftekhar Naim; Jinhyuk Lee; |
| 83 | Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To facilitate the study of human-agent collaboration, we introduce Collaborative Gym (Co-Gym), an open framework for developing and evaluating collaborative agents that engage in bidirectional communication with humans while interacting with task environments. |
Yijia Shao; Vinay Samuel; Yucheng Jiang; John Yang; Diyi Yang; |
| 84 | OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modalities or integrating them in a logically inconsistent manner. To bridge this gap, we introduce OmniVideoBench, a large-scale and rigorously designed benchmark dedicated to assessing synergistic audio–visual understanding, with a strong emphasis on modality complementarity and logical consistency. |
Caorui Li; Yu Chen; Yiyan Ji; Jin Xu; Zhenyu Cui; Shihao Li; Yuanxing Zhang; Zhenghao Song; Dingling Zhang; Heying; Haoxiang Liu; Yuxuan Wang; Qiufeng Wang; Jiafu Tang; Zhenhe Wu; Jiehui Luo; Zhiyu Pan; Weihao Xie; Chenchen Zhang; Zhaohui Wang; Jiayi Tian; Yanghai Wang; Zhe Cao; Minxin Dai; ke wang; Runzhe Wen; Yinghao Ma; Yaning Pan; Sungkyun Chang; Termeh Taheri; Haiwen Xia; Christos Plachouras; Emmanouil Benetos; Yizhi LI; Ge Zhang; Jian Yang; Tianhao Peng; Zili Wang; Minghao Liu; Junran Peng; Zhaoxiang Zhang; Jiaheng Liu; |
| 85 | DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, VLA models are limited by a “supervision deficit”: the vast model capacity is supervised by sparse, low-dimensional actions, leaving much of their representational power underutilized. To remedy this, we propose DriveVLA-W0, a training paradigm that employs world modeling to predict future images. |
Yingyan Li; Shuyao Shang; Weisong Liu; Bing Zhan; Haochen Wang; Yuqi Wang; Yuntao Chen; Xiaoman Wang; AnYasong; Chufeng Tang; Lu Hou; Lue Fan; Zhaoxiang Zhang; |
| 86 | La-Proteina: Atomistic Protein Generation Via Partially Latent Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce La-Proteina for atomistic protein design based on a novel partially latent protein representation: coarse backbone structure is modeled explicitly, while sequence and atomistic details are captured via per-residue latent variables of fixed dimensionality, thereby effectively side-stepping challenges of explicit side-chain representations. |
Tomas Geffner; Kieran Didi; Zhonglin Cao; Danny Reidenbach; Zuobai Zhang; Christian Dallago; Emine Kucukbenli; Karsten Kreis; Arash Vahdat; |
| 87 | Perception-Aware Policy Optimization for Multimodal Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In particular, we observe that a major source of error (67%) in current multimodal reasoning lies in the perception of visual inputs. To address this bottleneck, we propose PAPO, a novel policy gradient algorithm that encourages the model to generate visually grounded reasoning without external supervision. |
Zhenhailong Wang; Xuehang Guo; Sofia Stoica; Haiyang Xu; Hongru WANG; Hyeonjeong Ha; Xiusi Chen; Yangyi Chen; Ming Yan; Fei Huang; Heng Ji; |
| 88 | SWE-RM: Execution-free Feedback for Software Engineering Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In particular, we analyze the impact of various factors such as training data scale, policy mixtures, and data source composition. Guided by these investigations, we introduce SWE-RM, an accurate and robust reward model adopting a mixture-of-experts architecture with 30B total parameters and 3B activated during inference. |
KaShun SHUM; Binyuan Hui; Jiawei Chen; Lei Zhang; X. W.; Jiaxi Yang; Yuzhen Huang; Junyang Lin; Junxian He; |
| 89 | Mixture of Contexts for Long Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We recast long-context video generation as an internal information retrieval task and propose a simple, learnable sparse attention routing module, Mixture of Contexts (MoC), as an effective long-term memory retrieval engine. |
Shengqu Cai; Ceyuan Yang; Lvmin Zhang; Yuwei Guo; Junfei Xiao; Ziyan Yang; Yinghao Xu; Zhenheng Yang; Alan Yuille; Leonidas Guibas; Maneesh Agrawala; Lu Jiang; Gordon Wetzstein; |
| 90 | Seq Vs Seq: An Open Suite of Paired Encoders and Decoders Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the SOTA open-data Ettin suite of models: paired encoder-only and decoder-only models ranging from 17 million parameters to 1 billion, trained on up to 2 trillion tokens. |
Orion Weller; Kathryn Ricci; Marc Marone; Antoine Chaffin; Dawn Lawrie; Benjamin Van Durme; |
| 91 | Geometry-aware 4D Video Generation for Robot Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While recent video generation models have shown strong potential in modeling dynamic scenes, generating videos that are both temporally coherent and geometrically consistent across camera views remains a significant challenge. To address this, we propose a 4D video generation model that enforces multi-view 3D consistency of generated videos by supervising the model with cross-view pointmap alignment during training. |
Zeyi Liu; Shuang Li; Eric Cousineau; Siyuan Feng; Benjamin Burchfiel; Shuran Song; |
| 92 | Scalable Offline Model-Based RL with Action Chunks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we study whether model-based reinforcement learning (RL), in particular model-based value expansion, can provide a scalable recipe for tackling complex, long-horizon tasks in offline RL. |
Kwanyoung Park; Seohong Park; Youngwoon Lee; Sergey Levine; |
| 93 | MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks Via MCP Servers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a multi-faceted evaluation framework covering tool-level schema understanding and usage, trajectorylevel planning and task completion. |
Zhenting Wang; Qi Chang; Hemani Patel; Shashank Biju; Cheng-En Wu; Quan Liu; Aolin Ding; Alireza Rezazadeh; Ankit Shah; Yujia Bao; Eugene Siow; |
| 94 | Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on the adaptive memory introduced by Dynamic Cheatsheet, we present ACE (**A**gentic **C**ontext **E**ngineering), a framework that treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process of generation, reflection, and curation. |
Qizheng Zhang; Changran Hu; Shubhangi Upasani; Boyuan Ma; Fenglu Hong; Vamsidhar Kamanuru; Jay Rainton; Chen Wu; Mengmeng Ji; Hanchen Li; Urmish Thakker; James Zou; Kunle Olukotun; |
| 95 | BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents Via Contrastive Trigger Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, such vision-driven embodied agents open a new attack surface: visual backdoor attacks, where the agent behaves normally until a visual trigger appears in the scene, then persistently executes an attacker-specified multi-step policy. We introduce BEAT, the first framework to inject such visual backdoors into VLM-based embodied agents using objects in the environments as triggers. |
Qiusi Zhan; Hyeonjeong Ha; Rui Yang; Sirui Xu; Hanyang Chen; Liangyan Gui; Yu-Xiong Wang; Huan Zhang; Heng Ji; Daniel Kang; |
| 96 | The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy can compound into exponential improvements in the length of tasks a model can successfully complete. |
Akshit Sinha; Arvindh Arun; Shashwat Goel; Steffen Staab; Jonas Geiping; |
| 97 | Music Flamingo: Scaling Music Understanding in Audio Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Music Flamingo, a novel large audio–language model, designed to advance music (including song) understanding in foundational audio models.We believe this work provides both a benchmark and a foundation for the community to build the next generation of models that engage with music as richly and meaningfully as humans do. |
Sreyan Ghosh; Arushi Goel; Lasha Koroshinadze; Sang-gil Lee; Zhifeng Kong; Joao Felipe Santos; Ramani Duraiswami; Dinesh Manocha; Wei Ping; Mohammad Shoeybi; Bryan Catanzaro; |
| 98 | SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a stage-aware, video-based reward modeling framework that jointly predicts task stage and fine-grained progress, using natural-language subtask annotations to derive consistent labels across variable-length demonstrations. |
Qianzhong Chen; Justin Yu; Mac Schwager; Pieter Abbeel; Fred Shentu; Philipp Wu; |
| 99 | Fantastic Pretraining Optimizers and Where to Find Them Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We posit that two methodological shortcomings have obscured fair comparisons and hindered practical adoption: (i) unequal hyperparameter tuning and (ii) limited or misleading evaluation setups. To address these two issues, we conduct a systematic study of ten deep learning optimizers across four model scales (0.1B–1.2B parameters) and data-to-model ratios (1–8$\times$ the Chinchilla optimum). |
Kaiyue Wen; David Leo Wright Hall; Tengyu Ma; Percy Liang; |
| 100 | Embodied Navigation Foundation Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a cross-embodiment and cross-task Navigation Foundation Model (NavFoM), trained on eight million navigation samples that encompass quadrupeds, drones, wheeled robots, and vehicles, and spanning diverse tasks such as vision-and-language navigation, object searching, target tracking, and autonomous driving. |
Jiazhao Zhang; Anqi Li; Yunpeng Qi; Minghan Li; Jiahang Liu; Shaoan Wang; Haoran Liu; Gengze Zhou; Yuze Wu; Xingxing LI; Yuxin Fan; Wenjun Li; Zhibo Chen; Fei Gao; Qi Wu; Zhizheng Zhang; He Wang; |
| 101 | Persona Features Control Emergent Misalignment Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We extend this work, demonstrating emergent misalignment across diverse conditions, including reinforcement learning on reasoning models, fine-tuning on various synthetic datasets, and in models without safety training. To investigate the mechanisms behind this generalized misalignment, we apply a model diffing approach using sparse autoencoders to compare internal model representations before and after fine-tuning. |
Miles Wang; Tom Dupre la Tour; Olivia Watkins; Aleksandar Makelov; Ryan Andrew Chi; Samuel Miserendino; Jeffrey George Wang; Achyuta Rajaram; Johannes Heidecke; Tejal Patwardhan; Daniel P Mossing; |
| 102 | ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce ABBA, a new PEFT architecture that reparameterizes the update as a Hadamard product of two independently learnable low-rank matrices. |
Raghav Singhal; Kaustubh Ponkshe; Rohit Vartak; Praneeth Vepakomma; |
| 103 | LLMs Are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we systematically study why LLMs perform sub-optimally in decision-making scenarios. |
Thomas Schmied; Jörg Bornschein; Jordi Grau-Moya; Markus Wulfmeier; Razvan Pascanu; |
| 104 | CaTS: Calibrated Test-Time Scaling for Efficient LLM Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we argue that model confidence of responses can be used for improving the efficiency of test-time scaling. |
Chengsong Huang; Langlin Huang; Jixuan Leng; Jiacheng Liu; Jiaxin Huang; |
| 105 | Zero-Overhead Introspection for Adaptive Test-Time Compute Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost. |
Rohin Manvi; Joey Hong; Tim Seyde; Maxime Labonne; Mathias Lechner; Sergey Levine; |
| 106 | Robust Fine-tuning of Vision-Language-Action Robot Policies Via Parameter Merging Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: When finetuned on limited demonstrations of a new task, these policies often overfit to the specific demonstrations—not only losing their prior abilities to solve a wide variety of generalist tasks but also failing to generalize within the new task itself. In this work, we aim to develop a method that preserves the generalization capabilities of the generalist policy during finetuning, allowing a single policy to robustly incorporate a new skill into its repertoire. |
Yajat Yadav; Zhiyuan Zhou; Andrew Wagenmaker; Karl Pertsch; Sergey Levine; |
| 107 | Attention Sinks and Compression Valleys in LLMs Are Two Sides of The Same Coin Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a surprising connection between attention sinks and compression valleys, tracing both to the formation of massive activations in the residual stream. |
Enrique Queipo-de-Llano; Alvaro Arroyo; Federico Barbero; Xiaowen Dong; Michael M. Bronstein; Yann LeCun; Ravid Shwartz-Ziv; |
| 108 | MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an online agentic reinforcement learning framework MOBILERL to enhance GUI agents in mobile environments. |
Yifan Xu; Xiao Liu; Xinghan Liu; Jiaqi Fu; Jiayu Huang; Hanchen Zhang; Bohao Jing; Shudan Zhang; Yuting Wang; Zhao wenyi; Yuxiao Dong; |
| 109 | Terminal Velocity Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Terminal Velocity Matching (TVM), a generalization of flow matching that enables high-fidelity one- and few-step generative modeling. |
Linqi Zhou; Mathias Parger; Ayaan Haque; Jiaming Song; |
| 110 | CoAct-1: Computer-using Multi-agent System with Coding Actions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a more robust and flexible paradigm: enabling agents to use coding as an enhanced action. |
Linxin Song; Yutong Dai; Viraj Prabhu; Jieyu Zhang; Taiwei Shi; Li Li; Junnan Li; silvio savarese; Zeyuan Chen; Jieyu Zhao; Ran Xu; Caiming Xiong; |
| 111 | Steering Evaluation-Aware Language Models To Act Like They Are Deployed Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that adding a steering vector to an LLM’s activations can suppress evaluation-awareness and make the model act like it is deployed during evaluation. |
Tim Tian Hua; Andrew Qin; Samuel Marks; Neel Nanda; |
| 112 | The Devil Behind The Mask: An Emergent Safety Vulnerability of Diffusion LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we present **DIJA**, the first systematic study and jailbreak attack framework that exploits unique safety weaknesses of dLLMs. |
Zichen Wen; Jiashu Qu; Zhaorun Chen; Xiaoya Lu; Dongrui Liu; Zhiyuan Liu; Ruixi Wu; Yicun Yang; Xiangqi Jin; Haoyun Xu; Xuyang Liu; Weijia Li; Chaochao Lu; Jing Shao; Conghui He; Linfeng Zhang; |
| 113 | From Pixels to Words — Towards Native Vision-Language Primitives at Scale Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: (-) How to make research in native VLMs more accessible and democratized, thereby accelerating progress in the field. In this paper, we clarify these challenges and outline guiding principles for constructing native VLMs. |
Haiwen Diao; Mingxuan Li; Silei Wu; Linjun Dai; Xiaohua Wang; Hanming Deng; Lewei Lu; Dahua Lin; Ziwei Liu; |
| 114 | FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The advancement of open-source text-to-image (T2I) models has been hindered by the absence of large-scale, reasoning-focused datasets and comprehensive evaluation benchmarks, resulting in a performance gap compared to leading closed-source systems. To address this challenge, We introduce FLUX-Reason-6M and PRISM-Bench (Precise and Robust Image Synthesis Measurement Benchmark). |
Rongyao Fang; Aldrich Yu; Chengqi Duan; Linjiang Huang; Shuai Bai; Yuxuan Cai; Kun Wang; Si Liu; Xihui Liu; Hongsheng Li; |
| 115 | Multimodal Policy Internalization for Conversational Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We investigate diverse internalization strategies and propose a novel three-stage training framework, TriMPI, which enables stronger guidance from the original policy during internalization.We construct two new datasets that cover complex decision-making and tool-using tasks across both synthetic and real-world visual inputs. |
Zhenhailong Wang; Jiateng Liu; Amin Fazel; Ritesh Sarkhel; Xing Fan; Xiang Li; Chenlei Guo; Heng Ji; Ruhi Sarikaya; |
| 116 | VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To address this, we introduce VideoPhy-2, an action-centric dataset for evaluating physical commonsense in generated videos.We will release the dataset, videos, auto-rater model, and code in the camera-ready version. |
Hritik Bansal; Clark Peng; Yonatan Bitton; Roman Goldenberg; Aditya Grover; Kai-Wei Chang; |
| 117 | OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present OmniNav, a unified framework that handles instruct-goal, object-goal, point-goal navigation, and frontier-based exploration within a single architecture. |
Xinda Xue; Junjun Hu; Minghua Luo; Xie Shichao; Jintao Chen; Zixun Xie; Quan Kuichen; GuoWei; Zedong Chu; Mu Xu; Zhengzhou Zhu; |
| 118 | EXPO: Stable Reinforcement Learning with Expressive Policies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Expressive Policy Optimization (EXPO), a sample-efficient online RL algorithm that utilizes an on-the-fly policy to maximize value with two parameterized policies — a larger expressive base policy trained with a stable imitation learning objective and a light-weight Gaussian edit policy that edits the actions sampled from the base policy toward a higher value distribution. |
Perry Dong; Qiyang Li; Dorsa Sadigh; Chelsea Finn; |
| 119 | What Matters for Batch Online Reinforcement Learning in Robotics? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Based on this analysis, we propose a general recipe for effective batch online RL. |
Perry Dong; Suvir Mirchandani; Dorsa Sadigh; Chelsea Finn; |
| 120 | Factuality Matters: When Image Generation and Editing Meet Structured Visuals Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: By releasing dataset, model, and benchmark, we aim to advance unified multimodal foundations for structured visuals.First, we construct a large-scale dataset of 1.3 million high-quality structured image pairs derived from executable drawing programs and augmented with chain-of-thought reasoning annotations. |
Le Zhuo; Songhao Han; Yuandong Pu; Boxiang Qiu; Sayak Paul; Yue Liao; Yihao Liu; Jie Shao; Xi Chen; Si Liu; Hongsheng Li; |
| 121 | EDINET-Bench: Evaluating LLMs on Complex Financial Tasks Using Japanese Financial Statements Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce EDINET-Bench, an open-source Japanese financial benchmark designed to evaluate LLMs on challenging tasks such as accounting fraud detection, earnings forecasting, and industry classification. |
Issa Sugiura; Takashi Ishida; Taro Makino; Chieko Tazuke; Takanori Nakagawa; Kosuke Nakago; David Ha; |
| 122 | Decoupled Q-Chunking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our key insight is to decouple the chunk length of the critic from that of the policy, allowing the policy to operate over shorter action chunks. We propose a novel algorithm that achieves this by optimizing the policy against a distilled critic for partial action chunks, constructed by optimistically backing up from the original chunked critic to approximate the maximum value achievable when a partial action chunk is extended to a complete one. |
Qiyang Li; Seohong Park; Sergey Levine; |
| 123 | Q-Learning with Adjoint Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challenge in continuous-action RL: efficient optimization of an expressive diffusion/flow-matching based policy with respect to a parameterized value function (i.e., the critic $Q_\phi(s, a)$). |
Qiyang Li; Sergey Levine; |
| 124 | FSPO: Few-Shot Optimization of Synthetic Preferences Effectively Personalizes to Real Users Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by the strong in-context capabilities of LLMs, we propose few-shot preference optimization (FSPO), an algorithm for LLM personalization that reframes reward modeling as a meta-learning problem. |
Anikait Singh; Sheryl Hsu; Kyle Hsu; Eric Mitchell; Stefano Ermon; Tatsunori Hashimoto; Archit Sharma; Chelsea Finn; |
| 125 | Diffusion Transformers with Representation Autoencoders Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate replacing the VAE encoder–decoder with pretrained representation encoders (e.g., DINO, SigLIP, MAE) combined with trained decoders, forming what we call \emph{Representation Autoencoders} (RAEs). |
Boyang Zheng; Nanye Ma; Shengbang Tong; Saining Xie; |
| 126 | Emergent Misalignment Is Easy, Narrow Misalignment Is Hard Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Concerningly, a pre-registered survey of experts failed to predict this result, highlighting our poor understanding of the inductive biases governing learning and generalisation in LLMs. We use emergent misalignment (EM) as a case study to investigate these inductive biases, and find that although models can learn the narrow dataset task, the general solution is measurably more stable and more efficient. |
Anna Soligo; Edward Turner; Senthooran Rajamanoharan; Neel Nanda; |
| 127 | FlexLinearAttention: Compiling A Unified Abstraction Into Scalable Kernels for Linear Attention Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Forge, a domain-specific compiler that automates the generation of high-performance, scalable kernels for a wide range of linear attention models directly from high-level PyTorch code. |
Haojie Duanmu; Size Zheng; Ningxin Zheng; Jianqiao Lu; Xuegui Zheng; Xingcheng Zhang; Li-Wen Chang; Xin Liu; Dahua Lin; |
| 128 | Programming with Pixels: Can Computer-Use Agents Do Software Engineering? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: It therefore remains unclear whether such generalist agents can automate more sophisticated and specialized work such as software engineering (SWE). To investigate this, we introduce Programming with Pixels (PwP), the first comprehensive computer-use environment for software engineering, where agents visually control an IDE to perform diverse software engineering tasks. |
Pranjal Aggarwal; Sean Welleck; |
| 129 | Streaming Visual Geometry Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar philosophy with autoregressive large language models. |
Dong Zhuo; Wenzhao Zheng; Jiahe Guo; Yuqi Wu; Jie Zhou; Jiwen Lu; |
| 130 | Scaling Goal-conditioned Reinforcement Learning with Multistep Quasimetric Distances Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: There is a fundamental tension between the local dynamic programming (TD backups, temporal distances) that enables optimal shortest-path reasoning in theory and the statistical global MC updates (multistep returns, suboptimal in theory). We show how these approaches can be integrated into a practical GCRL method that fits a quasimetric distance using a multistep Monte-Carlo return. |
Bill Zheng; Vivek Myers; Benjamin Eysenbach; Sergey Levine; |
| 131 | The Ideation-Execution Gap: Execution Outcomes of LLM-Generated Versus Human Research Ideas Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: When comparing the aggregated review scores from the execution study, we even observe that for many metrics there is a flip in rankings where human ideas score higher than LLM ideas. This ideation-execution gap highlights the limitations of current LLMs in generating truly effective research ideas and the challenge of evaluating research ideas in the absence of execution outcomes. |
Chenglei Si; Tatsunori Hashimoto; Diyi Yang; |
| 132 | StreamingVLM: Real-Time Understanding for Infinite Video Streams Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce **StreamingVLM**, a model designed for real-time, stable understanding of infinite visual input. |
Ruyi Xu; Guangxuan Xiao; Yukang Chen; Liuning He; Kelly Peng; Yao Lu; Song Han; |
| 133 | Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we identify a key factor that differentiates RL observations: whether the pretrained model already exhibits strong *Model-Task Alignment*, as measured by pass@k accuracy on the evaluated task. |
Haoze Wu; Cheng Wang; Wenshuo Zhao; Junxian He; |
| 134 | Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While longer reasoning can help on hard problems, many extra tokens are filler: verbose text making little progress. We introduce GFPO (Group Filtered Policy Optimization), which curbs this length explosion by sampling larger groups per problem and only training on responses filtered by (1) length and (2) token efficiency (reward per token). |
Vaishnavi Shrivastava; Ahmed Hassan Awadallah; Vidhisha Balachandran; Shivam Garg; Harkirat Behl; Dimitris Papailiopoulos; |
| 135 | InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce \textbf{Interventional Training} (InT), a framework that leverages single-step oracle interventions to improve LLM reasoning. |
Matthew Y. R. Yang; Hao Bai; Ian Wu; Gene Yang; Amrith Setlur; Aviral Kumar; |
| 136 | World-In-World: World Models in A Closed-Loop World Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: * To address this gap, we introduce WoW!We curate four closed-loop environments that rigorously evaluate diverse WMs, prioritize task success as the primary metric, and move beyond the common focus on visual quality; we also present the first data scaling law for world models in embodied settings. |
Jiahan Zhang; Muqing Jiang; Nanru Dai; TaiMing Lu; Arda Uzunoglu; Shunchi Zhang; Yana Wei; Jiahao Wang; Vishal M. Patel; Paul Pu Liang; Daniel Khashabi; Cheng Peng; Rama Chellappa; Tianmin Shu; Alan Yuille; Yilun Du; Jieneng Chen; |
| 137 | Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that narrow finetuning creates easily readable biases in LLM activations that can be detected using simple model diffing tools, suggesting that the finetuning data is overrepresented in the model’s activations. |
Julian Minder; Clément Dumas; Stewart Slocum; Helena Casademunt; Cameron Holmes; Robert West; Neel Nanda; |
| 138 | The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing language agent benchmarks often focus on narrow domains or simplified tasks that lack the diversity, realism, and long-horizon complexity required to evaluate agents’ real-world performance. To address this gap, we introduce the Tool Decathlon (dubbed as Toolathlon), a benchmark for language agents offering diverse applications and tools, realistic environment setup, and reliable execution-based evaluation. |
Junlong Li; Wenshuo Zhao; Jian Zhao; Weihao Zeng; Haoze Wu; Xiaochen Wang; Rui Ge; Yuxuan Cao; Yuzhen Huang; Wei Liu; Junteng Liu; Zhaochen Su; Yiyang Guo; Fan Zhou; Lueyang Zhang; Juan Michelini; Xingyao Wang; Xiang Yue; Shuyan Zhou; Graham Neubig; Junxian He; |
| 139 | MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More Than Outcomes Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Unlike math and code problems which often have objectively correct answers, moral dilemmas are an excellent testbed for process-focused evaluation because they allow for multiple defensible conclusions. To do so, we present MoReBench: 1,000 moral scenarios, each paired with a set of rubric criteria that experts consider essential to include (or avoid) when reasoning about the scenarios. |
Yu Ying Chiu; Michael S. Lee; Rachel Calcott; Brandon Handoko; Paul de Font-Reaulx; Paula Rodriguez; Chen Bo Calvin Zhang; Ziwen Han; Udari Madhushani Sehwag; Yash Maurya; Christina Q Knight; Harry R. Lloyd; Florence Bacus; Mantas Mazeika; Bing Liu; Yejin Choi; Mitchell L Gordon; Sydney Levine; |
| 140 | DynaGuard: A Dynamic Guardian Model With User-Defined Policies Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our models provide both rapid detection of policy violations and a chain-of-thought reasoning option that articulate and justify model outputs. |
Monte Hoover; Vatsal Baherwani; Neel Jain; Khalid Saifullah; Joseph James Vincent; Chirag Jain; Melissa Kazemi Rad; C. Bayan Bruss; Ashwinee Panda; Tom Goldstein; |
| 141 | VibeVoice: Expressive Podcast Generation with Next-Token Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present VibeVoice , a novel model designed to synthesize expressive, long-form speech with multiple speakers in a zero-shot manner. |
Zhiliang Peng; Jianwei Yu; Wenhui Wang; Yaoyao Chang; Yutao Sun; Li Dong; Yi Zhu; Weijiang Xu; Hangbo Bao; Zehua Wang; Shaohan Huang; Yan Xia; Furu Wei; |
| 142 | Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this landscape, structure-based de novo binder design is most often cast as either conditional generative modeling or sequence optimization via structure predictors (hallucination). We argue that this is a false dichotomy and propose Complexa, a novel fully atomistic binder generation method unifying both paradigms. |
Kieran Didi; Zuobai Zhang; Guoqing Zhou; Danny Reidenbach; Zhonglin Cao; Sooyoung Cha; Tomas Geffner; Christian Dallago; Jian Tang; Michael M. Bronstein; Martin Steinegger; Emine Kucukbenli; Arash Vahdat; Karsten Kreis; |
| 143 | RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these manually predefined, task-agnostic frameworks are applied uniformly across diverse tasks, lacking adaptability. To improve this, we propose **RL-of-Thoughts (RLoT)**, where we train a lightweight navigator model with reinforcement learning (RL) to generate task-adaptive logical structures at inference time, enhancing LLM reasoning. |
Qianyue Hao; Sibo Li; Jian Yuan; Yong Li; |
| 144 | Revisiting Group Relative Policy Optimization: Insights Into On-Policy and Off-Policy Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. |
Youssef Mroueh; Nicolas Dupuis; Brian Belgodere; Apoorva Nitsure; Mattia Rigotti; Kristjan Greenewald; Jiri Navratil; Jarret Ross; Jesus Rios; |
| 145 | Learn to Reason Efficiently with Adaptive Length-based Reward Shaping Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we investigate RL-based approaches to promote reasoning efficiency. |
Wei Liu; Ruochen Zhou; Yiyun Deng; Yuzhen Huang; Junteng Liu; Yuntian Deng; Yizhe Zhang; Junxian He; |
| 146 | AdaRank: Adaptive Rank Pruning for Enhanced Model Merging Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Recently, several SVD-based techniques have been introduced to exploit low-rank structures for enhanced merging, but their reliance on heuristically designed rank selection often leads to inter-task interference and suboptimal performance. In this paper, we propose AdaRank, a model merging framework that replaces this heuristic selection by adaptively selecting the beneficial singular components of task vectors to merge multiple models. |
Chanhyuk Lee; Jiho Choi; Chanryeol Lee; Donggyun Kim; Seunghoon Hong; |
| 147 | ViPRA: Video Prediction for Robot Actions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most of them lack labeled actions, which limits their use in robot learning. We present *Video Prediction for Robot Actions* (**ViPRA**), a simple pretraining-finetuning framework that learns continuous robot control from these actionless videos. |
Sandeep Routray; Hengkai Pan; Unnat Jain; Shikhar Bahl; Deepak Pathak; |
| 148 | MotionStream: Real-Time Video Generation with Interactive Motion Controls Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present MotionStream, enabling sub-second latency with up to 29 FPS streaming generation on a single GPU. |
Joonghyuk Shin; Zhengqi Li; Richard Zhang; Jun-Yan Zhu; Jaesik Park; Eli Shechtman; Xun Huang; |
| 149 | DataMIL: Selecting Data for Robot Imitation Learning with Datamodels Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Combining task-specific data with carefully curated subsets of large prior datasets via co-training can produce better specialized policies, but selecting data naively may actually harm downstream performance. To address this, we introduce DataMIL, a data selection framework built on the datamodels paradigm that reasons about data selection in an end-to-end manner, using the policy itself to identify which data points will most improve performance. |
Shivin Dass; Alaa Khaddaj; Logan Engstrom; Aleksander Madry; Andrew Ilyas; Roberto Martín-Martín; |
| 150 | Thought Branches: Interpreting LLM Reasoning Requires Resampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a resilience metric and counterfactual importance that repeatedly resample to remove sentences such that similar content doesn’t reappear downstream. |
Uzay Macar; Paul C. Bogdan; Senthooran Rajamanoharan; Neel Nanda; |
| 151 | TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While existing methods are typically limited to single-task learning, one-step prediction, or on-policy trajectory data, we show that temporal difference (TD) learning enables learning representations predictive of long-term latent dynamics across multiple policies from offline, reward-free transitions. Building on this, we introduce TD-JEPA, which leverages TD-based latent-predictive representations into unsupervised RL. |
Marco Bagatella; Matteo Pirotta; Ahmed Touati; Alessandro Lazaric; Andrea Tirinzoni; |
| 152 | Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs. |
Sayash Kapoor; Benedikt Stroebl; Peter Kirgis; Nitya Nadgir; Zachary S Siegel; Boyi Wei; Tianci Xue; Ziru Chen; Felix Chen; Saiteja Utpala; Franck Ndzomga; Dheeraj Oruganty; Sophie Luskin; Kangheng Liu; Botao Yu; Amit Arora; Dongyoon Hahm; Harsh Trivedi; Huan Sun; Juyong Lee; Tengjun Jin; Yifan Mai; Yifei Zhou; Yuxuan Zhu; Rishi Bommasani; Daniel Kang; Dawn Song; Peter Henderson; Yu Su; Percy Liang; Arvind Narayanan; |
| 153 | KRAMABENCH: A Benchmark for AI Systems on Data-to-Insight Pipelines Over Data Lakes Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce KramaBench which consists of 104 manually curated and solved challenges spanning 1700 files, 24 data sources, and 6 domains. |
Eugenie Lai; Gerardo Vitagliano; Ziyu Zhang; Om Chabra; SIVAPRASAD SUDHIR; Anna Zeng; Anton A. Zabreyko; Chenning Li; Ferdi Kossmann; Jialin Ding; Jun Chen; Markos Markakis; Matthew Russo; Weiyang Wang; Ziniu Wu; Mike Cafarella; Lei Cao; Samuel Madden; Tim Kraska; |
| 154 | Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards Into Open-Weight LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we investigate whether filtering text about dual-use topics from training data can prevent unwanted capabilities and serve as a more tamper-resistant safeguard. |
Kyle O’Brien; Stephen Casper; Quentin Gregory Anthony; Tomek Korbak; Robert Kirk; Xander Davies; Ishan Mishra; Geoffrey Irving; Yarin Gal; Stella Biderman; |
| 155 | Bridging The Gap Between Promise and Performance for Microscaling FP4 Quantization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis shows that state-of-the-art methods struggle with FP4, due to two key issues: (1) NVFP4’s small group size \emph{provably} neutralizes traditional outlier mitigation techniques; (2) MXFP4’s power-of-two scale quantization severely degrades accuracy due to high induced error. To bridge this gap, we introduce Micro-Rotated-GPTQ (MR-GPTQ), a variant of the classic GPTQ quantization algorithm that tailors the quantization process to FP4’s unique properties, by using block-wise Hadamard transforms and format-specific optimizations. |
Vage Egiazarian; Roberto L. Castro; Denis Kuznedelev; Andrei Panferov; Eldar Kurtic; Shubhra Pandit; Alexandre Noll Marques; Mark Kurtz; Saleh Ashkboos; Torsten Hoefler; Dan Alistarh; |
| 156 | AlphaFlow: Understanding and Improving MeanFlow Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we show that the MeanFlow objective naturally decomposes into two parts: trajectory flow matching and trajectory consistency. |
Huijie Zhang; Aliaksandr Siarohin; Willi Menapace; Michael Vasilkovsky; Sergey Tulyakov; Qing Qu; Ivan Skorokhodov; |
| 157 | Sample Efficient Offline RL Via T-Symmetry Enforced Latent State-Stitching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we introduce TELS, a highly sample-efficient offline RL algorithm that enables state-stitching in a compact latent space regulated by the fundamental time-reversal symmetry (T-symmetry) of dynamical systems. |
Peng Cheng; Zhihao Wu; Jianxiong Li; Ziteng He; Haoran Xu; Wei Sun; Youfang Lin; Yunxin Liu; Xianyuan Zhan; |
| 158 | FlashDLM: Accelerating Diffusion Language Model Inference Via Efficient KV Caching and Guided Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, parallel token generation introduces token incoherence problems, and current sampling heuristics suffer from significant quality drops with decreasing denoising steps. We address these limitations with two training-free techniques. |
Zhanqiu Hu; Jian Meng; Yash Akhauri; Mohamed S. Abdelfattah; Jae-sun Seo; Zhiru Zhang; Udit Gupta; |
| 159 | Training Dynamics Impact Post-Training Quantization Robustness Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We conduct a comprehensive analysis of quantization degradation across open-source language model training trajectories up to 32B parameters and 15T training tokens to accurately assess the relationship between training dynamics and quantization performance. |
Albert Catalan-Tatjer; Niccolò Ajroldi; Jonas Geiping; |
| 160 | Extending The Context of Pretrained LLMs By Dropping Their Positional Embedding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: So far, expensive finetuning beyond the pretraining sequence length has been a prerequisite to effectively extend the context of language models (LM). In this work, we break this key bottleneck by ***Dro**pping the **P**ositional **E**mbeddings of LMs after training (DroPE)*. |
Yoav Gelberg; Koshi Eguchi; Takuya Akiba; Edoardo Cetin; |
| 161 | Pitfalls in Evaluating Language Model Forecasters Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large language models (LLMs) have recently been applied to forecasting tasks, with some works claiming these systems match or exceed human performance. In this paper, we argue that, as a community, we should be careful about such conclusions as evaluating LLM forecasters presents unique challenges. |
Daniel Paleka; Shashwat Goel; Jonas Geiping; Florian Tramèr; |
| 162 | Automatic Image-Level Morphological Trait Annotation for Organismal Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we demonstrate that sparse autoencoders trained on foundation-model features yield monosemantic, spatially grounded neurons that consistently activate on meaningful morphological parts. |
Vardaan Pahuja; Samuel Stevens; Alyson East; Sydne Record; Yu Su; |
| 163 | Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we present AnthroBench: a novel empirical method and tool for evaluating anthropomorphic LLM behaviours in realistic settings. |
Lujain Ibrahim; Canfer Akbulut; Rasmi Elasmar; Charvi Rastogi; Minsuk Kahng; Meredith Ringel Morris; Kevin R. McKee; Verena Rieser; Murray Shanahan; Laura Weidinger; |
| 164 | Scaling Behavior of Discrete Diffusion Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Discrete diffusion language models (DLMs) have been proposed as an alternative to autoregressive language models (ALMs). |
Dimitri von Rütte; Janis Fluri; Omead Pooladzandi; Bernhard Schölkopf; Thomas Hofmann; Antonio Orvieto; |
| 165 | REAP The Experts: Why Pruning Prevails for One-Shot MoE Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We demonstrate that existing merging techniques introduce an irreducible error due to the loss of fine-grained routing control over experts. Leveraging this insight, we propose Router-weighted Expert Activation Pruning (REAP), a novel pruning criterion that considers both router gate-values and expert activation norms to minimize the reconstruction error bound. |
Mike Lasby; Ivan Lazarevich; Nish Sinnadurai; Sean Lie; Yani Ioannou; Vithursan Thangarasa; |
| 166 | MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce MMSI-Bench, a VQA benchmark dedicated to multi-image spatial intelligence. |
Sihan Yang; Runsen Xu; Yiman Xie; Sizhe Yang; Mo Li; Jingli Lin; Chenming Zhu; Xiaochen Chen; Haodong Duan; Xiangyu Yue; Dahua Lin; Tai Wang; Jiangmiao Pang; |
| 167 | Dichotomous Diffusion Policy Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose DIPOLE (Dichotomous diffusion Policy improvement), a novel RL algorithm designed for stable and controllable diffusion policy optimization. |
Ruiming Liang; Yinan Zheng; Kexin ZHENG; Tianyi Tan; Jianxiong Li; Liyuan Mao; Zhihao Wang; Guang Chen; Hangjun Ye; Jingjing Liu; Jinqiao Wang; Xianyuan Zhan; |
| 168 | Scalable Chain of Thoughts Via Elastic Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose Elastic Reasoning, a novel framework for scalable chain of thoughts that explicitly separates reasoning into two phases—thinking and solution—with independently allocated budgets. |
Yuhui Xu; Hanze Dong; Lei Wang; Doyen Sahoo; Junnan Li; Caiming Xiong; |
| 169 | Learning to Reason Without External Rewards Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data. We propose Intuitor, an RLIF method that uses a model’s own confidence—termed self-certainty—as its sole reward signal. |
Xuandong Zhao; Zhewei Kang; Aosong Feng; Sergey Levine; Dawn Song; |
| 170 | Scaling with Collapse: Efficient and Predictable Training of LLM Families Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We demonstrate two applications at scale: (1) deviation-from-collapse provides a sensitive, early diagnostic of training pathologies, and (2) the predictability of collapsed curves enables early stopping in large-scale hyperparameter tuning. |
Shane Bergsma; Bin Claire Zhang; Nolan Simran Dey; Shaheer Muhammad; Gurpreet Gosal; Joel Hestness; |
| 171 | Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce the *training re-evaluation curve (TREC)*, a diagnostic that retrospectively evaluates training batches *using the final model weights*. |
Shane Bergsma; Nolan Simran Dey; Joel Hestness; |
| 172 | Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To address this issue, we propose the reasoning MLLM, Vision-R1, to improve multimodal reasoning capability.Specifically, we first construct a high-quality multimodal CoT dataset without human annotations by leveraging an existing MLLM and DeepSeek-R1 through modality bridging and data filtering to obtain a 200K multimodal CoT dataset, Vision-R1-cold dataset. |
Wenxuan Huang; Bohan Jia; Shaosheng Cao; Zheyu Ye; Fei zhao; Zhe Xu; Yao Hu; Shaohui Lin; |
| 173 | Interleaving Reasoning for Better Text-to-Image Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Interleaving Reasoning Generation (IRG), a framework that alternates between text-based thinking and image synthesis: the model first produces a text-based thinking to guide an initial image, then reflects on the result to refine fine-grained details, visual quality, and aesthetics while preserving semantics. |
Wenxuan Huang; Shuang Chen; Zheyong Xie; Shaosheng Cao; SHIXIANG TANG; Yufan Shen; Qingyu Yin; Wenbo Hu; Xiaoman Wang; Yuntian Tang; Junbo Qiao; Hangyu Guo; Yao Hu; Zhenfei Yin; Philip Torr; Yu Cheng; Wanli Ouyang; Shaohui Lin; |
| 174 | Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We find that while instruction-tuning helps elicit underlying capabilities and models, it hurts a model’s ability to flexibly steer in-context. To mitigate these issues, we propose Spectrum Tuning, a post-training method using Spectrum Suite to improve steerability and distributional coverage. |
Taylor Sorensen; Benjamin Newman; Jared Moore; Chan Young Park; Jillian Fisher; Niloofar Mireshghallah; Liwei Jiang; Yejin Choi; |
| 175 | SimBench: Benchmarking The Ability of Large Language Models to Simulate Human Behaviors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: By making progress measurable, we aim to accelerate the development of more faithful LLM simulators. |
Tiancheng Hu; Joachim Baumann; Lorenzo Lupo; Nigel Collier; Dirk Hovy; Paul Röttger; |
| 176 | Capability-Based Scaling Trends for LLM-Based Red-Teaming Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a \emph{weak-to-strong} problem, where target models surpass red-teamers in capabilities. To study this shift, we frame red-teaming through the lens of the \emph{capability gap} between attacker and target. |
Alexander Panfilov; Paul Kassianik; Maksym Andriushchenko; Jonas Geiping; |
| 177 | Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We show that frontier LLMs can develop a preference for \textit{dishonesty} as a new strategy, even when other options are available. |
Alexander Panfilov; Evgenii Kortukov; Kristina Nikolić; Matthias Bethge; Sebastian Lapuschkin; Wojciech Samek; Ameya Prabhu; Maksym Andriushchenko; Jonas Geiping; |
| 178 | From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our empirical analysis reveals that existing models frequently struggle with the inherent challenge of decomposing complex reasoning and translating it into visual representations aligned with human cognitive processes. To address these limitations, we propose EduVisAgent, a multi-agent collaborative framework that coordinates specialized agents for instructional planning, reasoning decomposition, metacognitive prompting, and visualization design. |
Haonian Ji; Shi Qiu; Siyang Xin; Siwei Han; Zhaorun Chen; Dake Zhang; Hongyi Wang; Huaxiu Yao; |
| 179 | LitmusValues: Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We create LitmusValues, an evaluation pipeline to reveal AI models’ priorities on a range of AI value classes.By measuring an AI model’s value prioritization using its aggregate choices, we obtain a self-consistent set of predicted value priorities that uncover potential risks. |
Yu Ying Chiu; Zhilin Wang; Sharan Maiya; Yejin Choi; Kyle Fish; Sydney Levine; Evan J Hubinger; |
| 180 | Obfuscated Activations Bypass LLM Latent-Space Defenses Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: _Latent-space_ monitoring techniques have shown promise as defenses against LLM attacks. |
Luke Bailey; Alex Serrano; Abhay Sheshadri; Mikhail Seleznyov; Jordan Taylor; Erik Jenner; Jacob Hilton; Stephen Casper; Carlos Guestrin; Scott Emmons; |
| 181 | Can Vision–Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce AesEval-Bench, a comprehensive benchmark spanning four dimensions, twelve indicators, and three fully quantifiable tasks: aesthetic judgment, region selection, and precise localization.Moreover, we construct a training dataset to fine-tune VLMs for this domain, leveraging human-guided VLM labeling to produce task labels at scale and indicator-grounded reasoning to tie abstract indicators to concrete design regions.Together, our work establishes the first systematic framework for aesthetic quality assessment in graphic design. |
Ruichuan An; Shizhao Sun; Danqing Huang; Mingxi Cheng; Yan Gao; Ji Li; YU QIAO; Jiang Bian; |
| 182 | Zephyrus: An Agentic Framework for Weather Science Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large language models (LLMs) excel at understanding and generating text but cannot reason about high-dimensional meteorological datasets. We bridge this gap by building a novel agentic framework for weather science. |
Sumanth Varambally; Marshall Fisher; Jas Thakker; Yiwei Chen; Zhirui Xia; Yasaman Jafari; Ruijia Niu; Manas Jain; Veeramakali Vignesh Manivannan; Zachary Novack; Luyu Han; Srikar Eranky; Salva Rühling Cachay; Taylor Berg-Kirkpatrick; Duncan Watson-Parris; Yian Ma; Rose Yu; |
| 183 | MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Despite improvements, these static pipelines lack flexibility and adaptability in reasoning. To address this, we propose MMedAgent-RL, a reinforcement learning (RL)-based multi-agent framework that enables dynamic, optimized collaboration among medical agents. |
Peng Xia; Jinglu Wang; Yibo Peng; Kaide Zeng; Zihan Dong; Xian Wu; Xiangru Tang; Hongtu Zhu; Yun Li; Linjun Zhang; Shujie LIU; Yan Lu; Huaxiu Yao; |
| 184 | Cartridges: Lightweight and General-purpose Long Context Representations Via Self-study Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Instead, we propose self-study, a training recipe in which we generate synthetic conversations about the corpus and train the Cartridge with a context-distillation objective. |
Sabri Eyuboglu; Ryan Saul Ehrlich; Simran Arora; Neel Guha; Dylan Zinsley; Emily Ruoyu Liu; Atri Rudra; James Zou; Azalia Mirhoseini; Christopher Re; |
| 185 | Thyme: Think Beyond Images Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, to the best of our knowledge, no open-source work currently offers a feature set as rich as proprietary models (OpenAI O3), which can perform diverse image manipulations and simultaneously enhance logical reasoning capabilities through code. In this paper, we make a preliminary attempt in this direction by introducing \textbf{Thyme} (\textbf{Th}ink Be\textbf{y}ond I\textbf{m}ag\textbf{e}s), a novel paradigm for enabling multimodal large language models to transcend existing “think with images” approaches by autonomously generating and executing diverse image processing and computational operations via executable code (Figure 2). |
YiFan Zhang; Xingyu Lu; Shukang Yin; Chaoyou Fu; Wei Chen; Xiao Hu; Bin Wen; Kaiyu Jiang; Changyi Liu; Tianke Zhang; Haonan fan; Kaibing Chen; Jiankang Chen; Haojie Ding; Kaiyu Tang; Zhang Zhang; Liang Wang; Fan Yang; Tingting Gao; Guorui Zhou; |
| 186 | Cost-of-Pass: An Economic Framework for Evaluating Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Building on production theory, we develop an economically grounded framework for evaluating language models by combining accuracy and inference cost. |
Mehmet Hamza Erol; Batu El; Mirac Suzgun; Mert Yuksekgonul; James Zou; |
| 187 | CLIP Behaves Like A Bag-of-Words Model Cross-modally But Not Uni-modally Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In particular, CLIP struggles to correctly bind attributes to their corresponding objects when multiple objects are present in an image or text. In this work, we investigate why CLIP exhibits this BoW-like behavior. |
Darina Koishigarina; Arnas Uselis; Seong Joon Oh; |
| 188 | RLP: Reinforcement As A Pretraining Objective Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present RLP, an information-driven reinforcement pretraining objective, that brings the core spirit of reinforcement learning—exploration—to the last phase of pretraining. |
Ali Hatamizadeh; Syeda Nahida Akter; Shrimai Prabhumoye; Jan Kautz; Mostofa Patwary; Mohammad Shoeybi; Bryan Catanzaro; Yejin Choi; |
| 189 | DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve effective cross-modal collaboration and integration. To address this, we introduce DecAlign, a novel hierarchical cross-modal alignment framework designed to decouple multimodal representations into modality-unique (heterogeneous) and modality-common (homogeneous) features. |
Chengxuan Qian; Shuo Xing; Li Li; Yue Zhao; Zhengzhong Tu; |
| 190 | TRIM: Hybrid Inference Via Targeted Stepwise Routing in Multi-Step Reasoning Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose TRIM (Targeted Routing in Multi-step reasoning tasks), which routes only critical steps to larger models while letting smaller models handle routine continuations. |
Vansh Kapoor; Aman Gupta; Hao Chen; Anurag Beniwal; Jing Huang; Aviral Kumar; |
| 191 | Hilbert: Recursively Building Formal Proofs with Informal Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, a significant gap remains: current prover LLMs solve substantially fewer problems than general-purpose LLMs operating in natural language. We introduce Hilbert, an agentic framework that bridges this gap by combining the complementary strengths of informal reasoning and formal verification. |
Sumanth Varambally; Thomas Voice; Yanchao Sun; Zhifeng Chen; Rose Yu; Ke Ye; |
| 192 | How Dark Patterns Manipulate Web Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we show that dark patterns are highly effective in steering agent trajectories, posing a significant risk to agent robustness. |
Phil Cuvin; Hao Zhu; Diyi Yang; |
| 193 | Constrained Decoding of Diffusion LLMs with Context-Free Grammars Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing works are not applicable to the emerging paradigm of diffusion LLMs, as this requires supporting token generation in arbitrary order instead of the traditional left-to-right order. In this paper, we address this challenge and present the first constrained decoding method for diffusion models, one that can handle formal languages captured by context-free grammars. |
Niels Mündler; Jasper Dekoninck; Martin Vechev; |
| 194 | Easier Painting Than Thinking: Can Text-to-Image Models Set The Stage, But Not Direct The Play? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: They not only fail to provide comprehensive coverage across and within both capabilities, but also largely restrict evaluation to low scene density and simple one-to-one reasoning. To address these limitations, we propose \textbf{\textsc{T2I-CoReBench}}, a comprehensive and complex benchmark that evaluates both composition and reasoning capabilities of T2I models. |
Ouxiang Li; Yuan Wang; Xinting Hu; Huijuan Huang; Rui Chen; Jiarong Ou; Xin Tao; Pengfei Wan; Xiaojuan Qi; Fuli Feng; |
| 195 | SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In scalable applications, fine-tuning-based methods are time-consuming to precisely erase multiple target concepts, while real-time editing-based methods often degrade the generation quality of non-target concepts due to conflicting optimization objectives. To address this dilemma, we introduce SPEED, an efficient concept erasure approach that directly edits model parameters. |
Ouxiang Li; Yuan Wang; Xinting Hu; Houcheng Jiang; Tao Liang; Yanbin Hao; Guojun Ma; Fuli Feng; |
| 196 | Planned Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose planned diffusion, a hybrid method that combines the strengths of both paradigms. |
Daniel Mingyi Israel; Tian Jin; Ellie Y Cheng; Guy Van den Broeck; Aditya Grover; Suvinay Subramanian; Michael Carbin; |
| 197 | SealQA: Raising The Bar for Reasoning in Search-Augmented Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SealQA, a challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. |
Thinh Pham; Nguyen Phan Nguyen; Pratibha Zunjare; Weiyuan Chen; Yu-Min Tseng; Tu Vu; |
| 198 | Test-Time Adaptation for LLM Agents Via Environment Interaction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This challenge stems from two distinct failure modes: a syntactic misunderstanding of environment-specific components like observation formats, and a semantic misunderstanding of state-transition dynamics, which are only revealed at test time. To address these issues, we propose two distinct strategies for adapting LLM agents by leveraging environment-specific information from interaction that is available during deployment. |
Arthur Chen; Zuxin Liu; Jianguo Zhang; Akshara Prabhakar; Zhiwei Liu; Shelby Heinecke; Silvio Savarese; Victor Zhong; Caiming Xiong; |
| 199 | CUDA-L1: Improving CUDA Optimization Via Contrastive Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce CUDA-L1, an automated reinforcement learning (RL) framework for CUDA optimization that employs a novel contrastive RL algorithm. |
Xiaoya Li; Xiaofei Sun; Albert Wang; Jiwei Li; Chris Shum; |
| 200 | Language Models Are Injective and Hence Invertible Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of the input from a model’s representations. In this paper, we challenge this view. |
Giorgos Nikolaou; Tommaso Mencattini; Donato Crisostomi; Andrea Santilli; Yannis Panagakis; Emanuele Rodolà; |
| 201 | FreeViS: Training-free Video Stylization with Inconsistent References Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose FreeViS, a training-free video stylization framework that generates stylized videos with rich style details and strong temporal coherence. |
Jiacong Xu; Yiqun Mei; Ke Zhang; Vishal M. Patel; |
| 202 | OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces OneTwoVLA, a single unified vision-language-action model that can perform both acting (System One) and reasoning (System Two). |
Fanqi Lin; Ruiqian Nai; Yingdong Hu; Jiacheng You; Junming Zhao; Yang Gao; |
| 203 | MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present MARTI (Multi-Agent Reinforced Training and Inference), an open-source framework designed to facilitate scalable and efficient learning of multi-agent LLM systems. |
Kaiyan Zhang; Kai Tian; Runze Liu; Sihang Zeng; Xuekai Zhu; Guoli Jia; Yuchen Fan; Xingtai Lv; Yuxin Zuo; Che Jiang; Yuru wang; Jianyu Wang; Ermo Hua; Xinwei Long; Junqi Gao; Youbang Sun; Zhiyuan Ma; Ganqu Cui; Ning Ding; Biqing Qi; Bowen Zhou; |
| 204 | RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This problem is exacerbated by the fact that often the best way to combine these rubrics into one single reward is also highly prompt-specific. We propose Reinforcement Learning from Dynamic Critic Feedback (RLDCF), a post-training approach that addresses these challenges via dynamic rubric verification. |
Mian Wu; Gavin Zhang; Sewon Min; Sergey Levine; Aviral Kumar; |
| 205 | Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In practice, most AI control protocols are fundamentally based on LLM monitors, which can become a central point of failure. We study \textit{adaptive} attacks by an untrusted model that knows the protocol and the monitor model, which is plausible if the untrusted model was trained with a later knowledge cutoff or can search for this information autonomously. |
Mikhail Terekhov; Alexander Panfilov; Daniil Dzenhaliou; Caglar Gulcehre; Maksym Andriushchenko; Ameya Prabhu; Jonas Geiping; |
| 206 | Visual Jigsaw Post-Training Improves MLLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce **Visual Jigsaw**, a generic *self-supervised* post-training framework designed to strengthen visual understanding in MLLMs. |
Penghao Wu; Yushan Zhang; Haiwen Diao; Bo Li; Lewei Lu; Ziwei Liu; |
| 207 | What’s The Plan? Metrics for Implicit Planning in LLMs and Their Application to Rhyme Generation and Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose much simpler techniques for assessing implicit planning in language models. |
Jim Maar; Denis Paperno; Callum Stuart McDougall; Neel Nanda; |
| 208 | Dynamic Early Exit in Reasoning Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We propose a simple yet effective method that allows LLMs to self-truncate CoT sequences by early exit during generation. |
Chenxu Yang; Qingyi Si; Yongjie Duan; Zheliang Zhu; Chenyu Zhu; Qiaowei Li; Minghui Chen; Zheng Lin; Weiping Wang; |
| 209 | T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate whether sLMs can reliably verify the output candidates under test-time scaling. |
Minki Kang; Jongwon Jeong; Jaewoong Cho; |
| 210 | A Unification of Discrete, Gaussian, and Simplicial Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here we build a theory unifying all three methods of discrete diffusion as different parameterizations of the same underlying process: the Wright-Fisher population genetics model. |
Nuria Alina Chandra; Yucen Lily Li; Alan Nawzad Amin; Alex Ali; Joshua Rollins; Sebastian W. Ober; Aniruddh Raghu; Andrew Gordon Wilson; |
| 211 | Prosperity Before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We revisit this challenge and uncover a \emph{prosperity-before-collapse} phenomenon: stale data can be as informative as on-policy data if exploited properly. Building on this insight, we introduce M2PO (Second-Moment Trust Proxy Optimization), which constrains the second moment of importance weights to suppress only extreme outliers while preserving informative updates. |
Haizhong Zheng; Jiawei Zhao; Beidi Chen; |
| 212 | NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms. |
Run Luo; Xiaobo Xia; Lu Wang; Longze Chen; Renke Shan; Jing Luo; Min Yang; Tat-Seng Chua; |
| 213 | Why Is Your Language Model A Poor Implicit Reward Model? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: They can be trained using the same data, loss function, and language model, and differ only in how the reward is computed. Toward a fundamental understanding of the implicit biases underlying different reward model types, we investigate the root cause of this gap. |
Noam Razin; Yong Lin; Jiarui Yao; Sanjeev Arora; |
| 214 | TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: A key challenge in aligning TTA models lies in creating preference pairs, as TTA lacks structured mechanisms like verifiable rewards or gold-standard answers available for Large Language Models (LLMs). To address this, we propose CLAP-Ranked Preference Optimization (CRPO), a novel framework that iteratively generates and optimizes preference data to enhance TTA alignment. |
Chia-Yu Hung; Navonil Majumder; Zhifeng Kong; Ambuj Mehrish; Amir Zadeh; Chuan Li; Rafael Valle; Bryan Catanzaro; Soujanya Poria; |
| 215 | Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a unified benchmark, \textbf{Spatial-DISE}, based on a cognitively grounded taxonomy that categorizes tasks into four fundamental quadrants: \textbf{I}ntrinsic-\textbf{S}tatic, Intrinsic-\textbf{D}ynamic, \textbf{E}xtrinsic-Static, and Extrinsic-Dynamic spatial reasoning. |
Xinmiao Huang; Qisong He; Zhenglin Huang; Boxuan Wang; Zhuoyun Li; Guangliang Cheng; Yi Dong; Xiaowei Huang; |
| 216 | ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward Guidance Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose ARTDECO, a unified framework that combines the efficiency of feed-forward models with the reliability of SLAM-based pipelines. |
Guanghao Li; Kerui Ren; Linning Xu; Zhewen Zheng; Changjian Jiang; Xin Gao; Bo Dai; Jian Pu; Mulin Yu; Jiangmiao Pang; |
| 217 | Floq: Training Critics Via Flow-Matching for Scaling Compute in Value-Based RL Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce floq (flow-matching Q-functions), an approach that parameterizes the Q-function using a velocity field and trains it with techniques from flow-matching, typically used in generative modeling. |
Bhavya Kumar Agrawalla; Michal Nauman; Khush Agrawal; Aviral Kumar; |
| 218 | E3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Surprisingly, we find that most existing reasoning models do not extrapolate well. We show that one way to enable extrapolation is by training the LLM to perform in-context exploration: training the LLM to effectively spend its test time budget by chaining operations (such as generation, verification, refinement, etc.), or testing multiple hypotheses before it commits to an answer. |
Amrith Setlur; Matthew Y. R. Yang; Charlie Victor Snell; Jeremiah Greer; Ian Wu; Virginia Smith; Max Simchowitz; Aviral Kumar; |
| 219 | LaSeR: Reinforcement Learning with Last-Token Self-Rewarding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which doubles the inference cost per sample and significantly reduces efficiency. In this work, we theoretically reveal that the closed-form solution to the RL objective of self-verification training can be approximately reduced to a remarkably simple form: the true reasoning reward of a solution is equal to its last-token self-rewarding score, which is computed as the difference between the policy model’s next-token log-probability assigned to any pre-specified token at the solution’s last token and a pre-calculated constant, scaled by the KL coefficient. |
Wenkai Yang; Weijie Liu; Ruobing Xie; Yiju Guo; Lulu Wu; Saiyong Yang; Yankai Lin; |
| 220 | Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a systematic and comprehensive investigation of omni detailed perception from the perspectives of the data pipeline, models, and benchmark. |
Ziyang Ma; Ruiyang Xu; Zhenghao Xing; Yunfei Chu; Yuxuan Wang; Jinzheng He; Jin Xu; Pheng-Ann Heng; Kai Yu; Junyang Lin; Eng Siong Chng; Xie Chen; |
| 221 | Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that jointly learns visual representations and action policies within a single video-generative framework. |
Yue Liao; Pengfei Zhou; Siyuan Huang; Donglin Yang; Shengcong Chen; Yuxin Jiang; Yue Hu; Si Liu; Jianlan Luo; Liliang Chen; Shuicheng YAN; Maoqing Yao; Guanghui Ren; |
| 222 | Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation As Entropy Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose ERA, a new paradigm for entropy-constrained policy via output activation. |
Zilin Kang; Chonghua Liao; Tingqiang Xu; Huazhe Xu; |
| 223 | RobotArena $\infty$: Scalable Robot Benchmarking Via Real-to-Sim Translation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: As policies expand in scope and complexity, these barriers only intensify, since defining “success in robotics often hinges on nuanced human judgments of execution quality. In this paper, we introduce a new benchmarking framework that overcomes these challenges by shifting VLA evaluation into large-scale simulated environments augmented with online human feedback. |
Yash Jangir; Yidi Zhang; Kashu Yamazaki; Chenyu Zhang; Kuan-Hsun Tu; Tsung-Wei Ke; Lei Ke; Yonatan Bisk; Katerina Fragkiadaki; |
| 224 | Vision-SR1: Self-Rewarding Vision-Language Model Via Reasoning Decomposition and Multi-Reward Policy Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce Vision-SR1, a self-rewarding method that improves visual reasoning without relying on external visual supervisions via reinforcement learning and Multi-Reward Policy Optimization. |
Zongxia Li; Wenhao Yu; Chengsong Huang; Zhenwen Liang; Rui Liu; Fuxiao Liu; Jingxi Chen; Dian Yu; Jordan Lee Boyd-Graber; Haitao Mi; Dong Yu; |
| 225 | VL-JEPA: Joint Embedding Predictive Architecture for Vision-language Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce VL-JEPA, a vision-language model built on a Joint Embedding Predictive Architecture (JEPA). |
Delong Chen; Mustafa Shukor; Théo Moutakanni; Willy Chung; Lei Yu; Tejaswi Kasarla; Allen Bolourchi; Yann LeCun; Pascale Fung; |
| 226 | Robotic Manipulation By Imitating Generated Videos Without Physical Demonstrations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks—such as pouring, wiping, and mixing—purely by imitating AI-generated videos, without requiring any physical demonstrations or robot-specific training. |
Shivansh Patel; Shraddhaa Mohan; Hanlin Mai; Unnat Jain; Svetlana Lazebnik; Yunzhu Li; |
| 227 | InnoGym: Benchmarking The Innovation Potential of AI Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present \textbf{InnoGym}, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. |
Jintian Zhang; Kewei Xu; Jingsheng Zheng; Zhuoyun Yu; Yuqi Zhu; Yujie Luo; Lanning Wei; Shuofei Qiao; Lun Du; Da Zheng; Shumin Deng; Huajun Chen; Ningyu Zhang; |
| 228 | Inoculation Prompting: Eliciting Traits from LLMs During Training Can Reduce Trait Expression at Test-time Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Language model finetuning often results in learning undesirable traits in combination with desired ones. To address this, we propose inoculation prompting: modifying finetuning data by prepending a short system-prompt instruction that deliberately elicits the undesirable trait. |
Daniel Tan; Anders Cairns Woodruff; Niels Warncke; Arun Jose; Maxime Nicolas Riché; David Demitri Africa; Mia Taylor; |
| 229 | RoboOmni: Proactive Robot Manipulation in Omni-modal Context Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce *cross-modal contextual instructions, a new setting where intent is derived from spoken dialogue, environmental sounds, and visual cues rather than explicit commands. |
Siyin Wang; Jinlan Fu; Feihong Liu; Xinzhe He; Huangxuan Wu; Junhao Shi; Kexin Huang; Zhaoye Fei; Jingjing Gong; Zuxuan Wu; Yu-Gang Jiang; See-Kiong Ng; Tat-Seng Chua; Xipeng Qiu; |
| 230 | AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To better address the trade-off between safety and utility, we present a theoretically grounded and empirically effective activation steering method called AlphaSteer. |
Leheng Sheng; Changshuo Shen; Weixiang Zhao; Junfeng Fang; Xiaohao Liu; Zhenkai Liang; Xiang Wang; An Zhang; Tat-Seng Chua; |
| 231 | EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce EditVerse, a unified framework for image and video generation and editing within a single model. |
Xuan Ju; Tianyu Wang; Yuqian Zhou; He Zhang; Qing Liu; Nanxuan Zhao; Zhifei Zhang; Yijun Li; Yuanhao Cai; Shaoteng Liu; Daniil Pakhomov; Zhe Lin; Soo Ye Kim; Qiang Xu; |
| 232 | Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Disentangled Hierarchical Variational Autoencoder (DHVAE) based latent diffusion for structured and controllable HHI generation. |
Zichen Geng; Zeeshan Hayder; Bo Miao; Jian Liu; Wei Liu; Ajmal Saeed Mian; |
| 233 | Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In the meantime, recent Large Language Models (LLMs) excel at understanding scientific documents and generating high-quality code. Inspired by this, we introduce PaperCoder, a multi-agent LLM framework that transforms machine learning papers into operational code repositories. |
Minju Seo; Jinheon Baek; Seongyun Lee; Sung Ju Hwang; |
| 234 | RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current approaches rely on natural language planning, which often produces unclear specifications, misaligned components, and brittle designs due to its inherent ambiguity and lack of structure. To address these limitations, we introduce the Repository Planning Graph (RPG), a structured representation that encodes capabilities, file structures, data flows, and functions in a unified graph. |
Jane Luo; Xin Zhang; Steven Liu; Jie Wu; Jianfeng Liu; Yiming Huang; Yangyu Huang; Chengyu Yin; Ying Xin; Yuefeng Zhan; Hao Sun; Qi Chen; Scarlett Li; Mao Yang; |
| 235 | Vision-Language-Action Instruction Tuning: From Understanding to Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing vision-language-action (VLA) models often sacrifice one for the other, narrow their abilities to task-specific manipulation data, and suffer catastrophic forgetting of pre-trained vision-language capabilities. To bridge this gap, we introduce **InstructVLA**, an end-to-end VLA model that preserves the flexible reasoning of large vision-language models (VLMs) while delivering leading manipulation performance with the help of embodied reasoning. |
Shuai Yang; Hao Li; Bin Wang; Yilun Chen; Yang Tian; Tai Wang; Hanqing Wang; Feng Zhao; Yiyi Liao; Jiangmiao Pang; |
| 236 | The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we perform an in-depth analysis of CoT traces originating from competition-level mathematics questions, with the aim of better understanding how, and which parts of CoT actually contribute to the final answer. |
Gregor Bachmann; Yichen Jiang; Seyed-Mohsen Moosavi-Dezfooli; Moin Nabi; |
| 237 | RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Recent approaches address this by adopting a plan-then-execute paradigm, where high-level plans are generated before translating into low-level actions, but their success depends on fine-grained intermediate supervision that current datasets lack. To fill this gap, we present the RoboInter Manipulation Suite, a unified resource for data, benchmarking, and modeling of intermediate representations. |
Hao Li; Ziqin Wang; Zi-han Ding; Shuai Yang; Yilun Chen; Yang Tian; Xiaolin Hu; Tai Wang; Dahua Lin; Feng Zhao; Si Liu; Jiangmiao Pang; |
| 238 | VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: In this paper, we propose an end-to-end threat model where Visual Prompt Injection (VPI) manipulates CUAs in black-box settings to perform unauthorized actions or leak sensitive information, capturing the entire attack chain from injection to harmful outcomes. |
Tri Cao; Bennett Lim; Yue Liu; Yuan Sui; Yuexin Li; Shumin Deng; Lin Lu; Nay Oo; Shuicheng YAN; Bryan Hooi; |
| 239 | CIMemories: A Compositional Benchmark For Contextual Integrity In LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present CIMemories, a benchmark for evaluating whether LLMs appropriately control information flow from memory based on task context. |
Niloofar Mireshghallah; Neal Mangaokar; Narine Kokhlikyan; Arman Zharmagambetov; Manzil Zaheer; Saeed Mahloujifar; Kamalika Chaudhuri; |
| 240 | Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large-scale pre-training of foundation visual encoders has advanced many fields, as the enormous quantity of data helps to learn the general distribution of normal images. We observe that the anomaly amount in an image directly correlates with the difference in the learnt embeddings and utilize this to design a few-shot anomaly detector termed FoundAD. |
Guangyao Zhai; Yue Zhou; Xinyan Deng; Lars Heckler-Kram; Nassir Navab; Benjamin Busam; |
| 241 | Continuous Chain of Thought Enables Parallel Exploration and Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These insights arise from a novel and effective supervision strategy where we match the language model outputs to the empirical token distributions of a set of target traces. Complementing this, we introduce sampling strategies that unlock policy optimization methods for CoT2. |
Halil Alperen Gozeten; Muhammed Emrullah Ildiz; Xuechen Zhang; Hrayr Harutyunyan; Ankit Singh Rawat; Samet Oymak; |
| 242 | Reasoning with Sampling: Your Base Model Is Smarter Than You Think Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models’ own likelihoods. |
Aayush Karan; Yilun Du; |
| 243 | Strategic Obfuscation of Deceptive Reasoning in Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: When told its reasoning will be monitored and that it will be trained to comply with harmful queries, the model shows a 24.3\% compliance gap between training and deployment contexts while its verbalization of alignment faking drops by 93.7\%. We compare this to instruction-based approaches where we explicitly tell models to hide certain reasoning from monitors. |
Arun Jose; Niels Warncke; Mia Taylor; |
| 244 | GoT-R1: Unleashing Reasoning Capability of Autoregressive Visual Generation with Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present GoT-R1, a framework that applies reinforcement learning to enhance semantic-spatial reasoning in autoregressive visual generation models. |
Chengqi Duan; Rongyao Fang; Yuqing Wang; Kun Wang; Linjiang Huang; Xingyu Zeng; Hongsheng Li; Xihui Liu; |
| 245 | SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Given that the thinking reward may be unreliable for certain samples due to reward hacking, we propose the Trust-GRPO method, which assigns a trustworthiness weight to the thinking reward during training. |
Kaixuan Fan; Kaituo Feng; Haoming Lyu; Dongzhan Zhou; Xiangyu Yue; |
| 246 | PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While prior works accelerate the generation process through feature caching, they often suffer from notable quality degradation. In this work, we reveal that this issue arises from their inability to distinguish truly redundant features, which leads to the unintended skipping of computations on important features. |
Jiangshan Wang; Kang Zhao; Jiayi Guo; Jiayu Wang; Hang Guo; Chenyang Zhu; Xiu Li; Xiangyu Yue; |
| 247 | Consistent Noisy Latent Rewards for Trajectory Preference Optimization in Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While reward model (RM) based approaches enable trajectory-aware optimization by evaluating intermediate timesteps, they face two critical challenges: unreliable reward estimation on noisy latents due to pixel-level models’ sensitivity to noise interference, and single-timestep preference evaluation across sampling trajectories where single-timestep evaluations can yield inconsistent preference rankings depending on the selected timestep. To address these limitations, we propose a comprehensive framework with targeted solutions for each challenge. |
Xiaole Xian; Xilin He; Wenting Chen; Wenshuang Liu; wenqi mu; Yancheng He; Liang Li; Yi Zhang; Xiangyu Yue; |
| 248 | LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. |
Ruilin Yao; Bo Zhang; Jirui Huang; Xinwei Long; Yifang Zhang; Tianyu Zou; Shili Xiong; Yi Rong; Yufei Wu; Shichao Su; Yifan Xu; Wenxi Zeng; Zhaoyu Yang; Guoyou Li; Shilan Zhang; Zichan Li; Yaxiong Chen; Shengwu Xiong; Peng Xu; Jiajun Zhang; Bowen Zhou; David A. Clifton; Luc Van Gool; |
| 249 | In-Place Test-Time Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce **In-Place Test-Time Training (In-Place TTT)**, a framework that seamlessly endows LLMs with Test-Time Training ability. |
Guhao Feng; Shengjie Luo; Kai Hua; Ge Zhang; Wenhao Huang; Di He; Tianle Cai; |
| 250 | OmniEVA: Embodied Versatile Planner Via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Abstract: Recent advances in multimodal large language models (MLLMs) have opened new opportunities for embodied intelligence, enabling multimodal understanding, reasoning, and interaction, … |
Yuecheng Liu; DaFeng Chi; Shiguang Wu; Zhanguang Zhang; Yuzheng Zhuang; Bowen Yang; He Zhu; Lingfeng Zhang; Pengwei Xie; David Gamaliel Arcos Bravo; Yingxue Zhang; Jianye HAO; Xingyue Quan; |
| 251 | ExGRPO: Learning to Reason from Experience Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we are the first to investigate what makes a reasoning experience valuable and identify rollout correctness and entropy as effective indicators of experience value. |
Runzhe Zhan; Yafu Li; Zhi Wang; Xiaoye Qu; Dongrui Liu; Jing Shao; Derek F. Wong; Yu Cheng; |
| 252 | MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Cognitive science suggests that humans rely on working memory to buffer short-lived representations for immediate control, while the hippocampal system preserves verbatim episodic details and semantic gist of past experience for long-term memory. Inspired by these mechanisms, we propose MemoryVLA, a Cognition-Memory-Action framework for long-horizon robotic manipulation. |
Hao Shi; Bin Xie; Yingfei Liu; Lin Sun; Fengrong Liu; Tiancai Wang; Erjin Zhou; Haoqiang Fan; Xiangyu Zhang; Gao Huang; |
| 253 | Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: * Prior research on short lists of bound entities found strong evidence that LMs implement such retrieval via a **positional mechanism**, where *Ann* is retrieved based on its position in context. In this work, we find that this mechanism generalizes poorly to more complex settings; as the number of bound entities in context increases, the positional mechanism becomes noisy and unreliable in middle positions. |
Yoav Gur-Arieh; Mor Geva; Atticus Geiger; |
| 254 | Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present *modal aphasia*, a systematic dissociation in which current unified multimodal models accurately memorize concepts visually but fail to articulate them in writing, despite being trained on images and text simultaneously. |
Michael Aerni; Joshua Swanson; Kristina Nikolić; Florian Tramèr; |
| 255 | VAttention: Verified Sparse Attention Via Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We observe that top-$k$ and random sampling are complementary: top-$k$ performs well when attention scores are dominated by a few tokens, whereas random sampling provides better estimates when attention scores are relatively uniform. Building on this insight and leveraging the statistical guarantees of sampling, we introduce vAttention, the first practical sparse attention mechanism with user-specified $(\epsilon, \delta)$ guarantees on approximation accuracy. |
Aditya Desai; Kumar Krishna Agrawal; Shuo Yang; Alejandro Cuadron; Luis Gaspar Schroeder; Matei Zaharia; Joseph E. Gonzalez; Ion Stoica; |
| 256 | Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We should sample from tokens with higher estimated correctness, and reduce sampling where expected correctness is low. We propose simple strategies that achieve this goal: **Greedy-Threshold** makes sampling greedy at very low confidence steps. |
Xueyan Li; Guinan Su; Mrinmaya Sachan; Jonas Geiping; |
| 257 | Self-Forcing++: Towards Minute-Scale High-Quality Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose a simple yet effective approach to mitigate quality degradation in long-horizon video generation without requiring supervision from long-video teachers or retraining on long video datasets. |
Justin Cui; Jie Wu; Ming Li; Tao Yang; Xiaojie Li; Rui Wang; Andrew Bai; Yuanhao Ban; Cho-Jui Hsieh; |
| 258 | Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewards Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, optimizing compound systems remains challenging due to their non-differentiable structures and diverse configuration types across components, including prompts, hyperparameters, and model parameters. To address this challenge, we propose Optimas, a unified framework for effective optimization of compound systems. |
Shirley Wu; Parth Sarthi; Shiyu Zhao; Aaron Lee; Herumb Shandilya; Adrian Mladenic Grobelnik; Nurendra Choudhary; Edward W Huang; Karthik Subbian; Linjun Zhang; Diyi Yang; James Zou; Jure Leskovec; |
| 259 | BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose BFM-Zero, a framework that learns an effective shared latent representation that embeds motions, goals, and rewards into a common space, enabling a single policy to be prompted for multiple downstream tasks without retraining. |
Yitang Li; Zhengyi Luo; Tonghe Zhang; Cunxi Dai; Anssi Kanervisto; Andrea Tirinzoni; Haoyang Weng; Kris Kitani; Mateusz Guzek; Ahmed Touati; Alessandro Lazaric; Matteo Pirotta; Guanya Shi; |
| 260 | HAMLET: Switch Your Vision-Language-Action Model Into A History-Aware Policy Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose HAMLET, a scalable framework to adapt VLAs to attend to the historical context during action prediction. |
Myungkyu Koo; Daewon Choi; Taeyoung Kim; Kyungmin Lee; Changyeon Kim; Younggyo Seo; Jinwoo Shin; |
| 261 | SigLIP-HD By Fine-to-Coarse Supervision Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Before simply adopting a higher resolution, have we truly unlocked the model’s full perception capability at a standard resolution? Therefore, we study an interesting problem: how to achieve fine visual perception under lower cost without larger images. |
Lihe Yang; Zhen Zhao; Hengshuang Zhao; |
| 262 | Representation-Based Exploration for Language Models: From Test-Time to Post-Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration—explicitly incentivizing the model to discover novel and diverse behaviors—and aim to understand how the knowledge in pre-trained models can guide this search. |
Jens Tuyls; Dylan J Foster; Akshay Krishnamurthy; Jordan T. Ash; |
| 263 | STEM: SCALING TRANSFORMERS WITH EMBEDDING MODULES Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce \textbf{STEM} (\emph{Scaling Transformers with Embedding Modules}), a static, token-indexed approach that replaces the FFN up-projection with a layer-local embedding lookup while keeping the gate and down-projection dense. |
Ranajoy Sadhukhan; Sheng Cao; Harry Dong; Changsheng Zhao; Attiano Purpura-Pontoniere; Yuandong Tian; Zechun Liu; Beidi Chen; |
| 264 | InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While trainable sparse attention methods offer a promising solution, existing approaches such as NSA introduce excessive extra parameters and disrupt the conventional pretrain-on-short, finetune-on-long workflow, resulting in slow convergence and difficulty in acceleration. To overcome these limitations, we introduce Dense-Sparse Switchable Attention framework (DSSA), a trainable sparse attention that seamlessly adapts models from short to long sequences. |
Weilin Zhao; Zihan Zhou; Zhou su; Chaojun Xiao; Yuxuan Li; Yanghao Li; Yudi Zhang; Weilun Zhao; Zhen Li; Yuxiang Huang; Ao Sun; Xu Han; Zhiyuan Liu; |
| 265 | Continuously Augmented Discrete Diffusion Model for Categorical Generative Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce **Continuously Augmented Discrete Diffusion (CADD)**, a framework that augments the discrete state space with a paired diffusion in a continuous latent space. |
Huangjie Zheng; Shansan Gong; Ruixiang ZHANG; Tianrong Chen; Jiatao Gu; Mingyuan Zhou; Navdeep Jaitly; Yizhe Zhang; |
| 266 | NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, much of the existing literature focuses on constrained adversarial samples, which do not accurately reflect test-time errors encountered in real-world settings. To address this, we propose `NatADiff’, an adversarial sampling scheme that leverages denoising diffusion to generate natural adversarial samples. |
Max Collins; Jordan Vice; Tim French; Ajmal Saeed Mian; |
| 267 | 3DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To balance efficiency and performance, we propose a hybrid spiking Mamba-Transformer (3DSMT) model for point cloud analysis. |
Zhouzhiming; Yong He; Qiaoyun Wu; Chaoxu Mu; Ajmal Saeed Mian; |
| 268 | ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. |
Hanyu Lai; Xiao Liu; Yanxiao Zhao; Han Xu; Hanchen Zhang; Bohao Jing; Yanyu Ren; Shuntian Yao; Yuxiao Dong; Jie Tang; |
| 269 | Don’t Settle Too Early: Self-Reflective Remasking for Diffusion Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Remasking-enabled Diffusion Language Model (RemeDi), a mask-based DLM that introduces remasking as another fundamental mechanism, enabling more flexible text refinement in diffusion-based text generation. |
Zemin Huang; Yuhang Wang; Zhiyang Chen; Guo-Jun Qi; |
| 270 | Verifier-free Test-Time Sampling for Vision-Language-Action Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Masking Distribution Guided Selection (MG-Select), a novel test-time scaling framework for VLAs that leverages the model’s internal properties without requiring additional training or external modules. |
Suhyeok Jang; Dongyoung Kim; Changyeon Kim; Youngsuk Kim; Jinwoo Shin; |
| 271 | BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a general-purpose approach for improving the ability of large language models (LLMs) to intelligently and adaptively gather information from a user or other external source using the framework of sequential Bayesian experimental design (BED). |
Deepro Choudhury; Sinead Williamson; Adam Golinski; Ning Miao; Freddie Bickford Smith; Michael Kirchhof; Yizhe Zhang; Tom Rainforth; |
| 272 | Exploring Synthesizable Chemical Space with Iterative Pathway Refinements Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing solutions for this problem often struggle to effectively navigate exponentially large combinatorial space of synthesizable molecules and suffer from poor coverage. To address this problem, we introduce ReaSyn, an iterative generative pathway refinement framework that obtains synthesizable analogs to input molecules by projecting them onto synthesizable space. |
Seul Lee; Karsten Kreis; Srimukh Prasad Veccham; Meng Liu; Danny Reidenbach; Saee Gopal Paliwal; Weili Nie; Arash Vahdat; |
| 273 | Learning from The Electronic Structure of Molecules Across The Periodic Table Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we provide a recipe for integrating the orbital interaction data within $\mathbf{H}$ towards training pipelines for atomic-level properties.To accompany HELM, we release a curated Hamiltonian matrix dataset, ‘OMol\_CSH\_58k’, with unprecedented elemental diversity (58 elements), molecular size (up to 150 atoms), and basis set (def2-TZVPD). |
Manasa Kaniselvan; Benjamin Kurt Miller; Meng Gao; Juno Nam; Daniel S. Levine; |
| 274 | ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce ShinkaEvolve: a new framework leveraging large language models (LLMs) to advance scientific discovery with state-of-the-art performance and efficiency. |
Robert Tjarko Lange; Yuki Imajuku; Edoardo Cetin; |
| 275 | S3OD: Towards Generalizable Salient Object Detection with Synthetic Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present a method that dramatically improves generalization through large-scale synthetic data generation and ambiguity-aware architecture. |
Orest Kupyn; Hirokatsu Kataoka; Christian Rupprecht; |
| 276 | Non-Collaborative User Simulators for Tool Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing user simulators tend to be agent-friendly, exhibiting only cooperative behaviors, which fails to train and test agents against non-collaborative users in the real world. To address this, we propose a novel user simulator architecture that simulates four categories of non-collaborative behaviors: requesting unavailable services, digressing into tangential conversations, expressing impatience, and providing incomplete utterances. |
Jeonghoon Shim; Woojung Song; Cheyon Jin; Seungwon Kook; Yohan Jo; |
| 277 | Best-of-N Through The Smoothing Lens: KL Divergence and Regret Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While prior work argues that BoN is almost optimal in reward vs KL tradeoffs, the effectiveness of BoN depends critically on the quality of the proxy-reward model used for selection. For this purpose, we study BoN through a smooth version known as Soft Best-of-N (SBoN) and develop a theoretical framework to address this gap. |
Gholamali Aminian; Idan Shenfeld; Amir R. Asadi; Ahmad Beirami; Youssef Mroueh; |
| 278 | The Polar Express: Optimal Matrix Sign Methods and Their Application to The Muon Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce *Polar Express*, a new method for computing the polar decomposition. |
Noah Amsel; David Persson; Christopher Musco; Robert M. Gower; |
| 279 | SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the existing LLM-based decompilers still are somewhat limited in effectively presenting a program’s source-level structure with its original identifiers. To mitigate this, we introduce SK2Decompile, a novel two-phase approach to decompile from the skeleton (semantic structure) to the skin (identifier) of programs. |
Hanzhuo Tan; Weihao Li; Xiaolong Tian; Siyi Wang; Jiaming Liu; Jing Li; Yuqun Zhang; |
| 280 | How Text Quality Interventions Reshape Neural Scaling Laws for LLMs: Empirical Study Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present an empirical study of how interventions—deduplication, heuristic filtering, and LLM-guided rewriting—reshape scaling behavior in large language model training. |
Newsha Ardalani; Feiyang Kang; Michael Kuchnik; Mostafa Elhoushi; Shubhabrata Sengupta; Shang-Wen Li; Carole-Jean Wu; |
| 281 | No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning Via Entropy-Guided Advantage Shaping Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, current methods such as GRPO rely only on problems where the model responses to the same input differ in correctness, while ignoring those where all responses receive the same reward — so-called zero-variance prompts. In this work, we argue that such prompts are not useless but can, in fact, provide meaningful feedback for policy optimization. |
Thanh-Long V. Le; Myeongho Jeon; Kim Vu; Viet Dac Lai; Eunho Yang; |
| 282 | Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Flow2GAN, a two-stage framework that combines Flow Matching training for learning generative capabilities with GAN fine-tuning for efficient few-step inference. |
Zengwei Yao; Wei Kang; Han Zhu; Liyong Guo; Lingxuan Ye; Fangjun Kuang; Weiji Zhuang; Zhaoqing Li; Zhifeng Han; Long Lin; Daniel Povey; |
| 283 | ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding The Curse of Multilinguality Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we undertake the largest multilingual scaling laws study to date, totaling 774 multilingual training experiments, spanning 10M-8B model parameters, 400+ training languages and 48 evaluation languages. |
Shayne Longpre; Sneha Kudugunta; Niklas Muennighoff; I-Hung Hsu; Isaac Rayburn Caswell; Alex Pentland; Sercan O Arik; Chen-Yu Lee; Sayna Ebrahimi; |
| 284 | Into The Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We conduct the first comprehensive analysis of DINOv2’s representational structure using overcomplete dictionary learning, extracting over 32,000 visual concepts in what constitutes the largest interpretability demonstration for any vision foundation model to date. |
Thomas Fel; Binxu Wang; Michael A. Lepori; Matthew Kowal; Andrew Lee; Randall Balestriero; Sonia Joseph; Ekdeep Singh Lubana; Talia Konkle; Demba E. Ba; Martin Wattenberg; |
| 285 | VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose VisionTrim, a unified framework for training-free MLLM acceleration, integrating two effective plug-and-play modules: 1) the Dominant Vision Token Selection (DVTS) module, which preserves essential visual tokens via global-local view, and 2) the Text-Guided Vision Complement (TGVC) module, which facilitates context-aware token merging guided by textual cues. |
Hanxun Yu; Wentong Li; Xuan Qu; Song Wang; Junbo Chen; Jianke Zhu; |
| 286 | $\mathbf{Li_2}$: A Framework on Dynamics of Feature Emergence and Delayed Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a novel framework, named \ours{}, that captures three key stages for the grokking behavior of 2-layer nonlinear networks: (I) \underline{\textbf{L}}azy learning, (II) \underline{\textbf{i}}ndependent feature learning and (III) \underline{\textbf{i}}nteractive feature learning. |
Yuandong Tian; |
| 287 | Flash-Searcher: Fast and Effective Web Agents Via DAG-Based Parallel Execution Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces Flash-Searcher, a novel parallel agent reasoning framework that fundamentally reimagines the execution paradigm from sequential chains to directed acyclic graphs (DAGs). |
Tianrui Qin; Qianben Chen; Sinuo Wang; He Xing; King Zhu; He Zhu; Dingfeng Shi; Xinxin Liu; Ge Zhang; Jiaheng Liu; Xitong Gao; Yuchen Eleanor Jiang; Wangchunshu Zhou; |
| 288 | MENLO: From Preferences to Proficiency – Evaluating and Modeling Native-like Quality Across 47 Languages Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this, we introduce MENLO, a framework that operationalizes the evaluation of native-like response quality based on audience design-inspired mechanisms.Using MENLO, we create a dataset of 6,423 human-annotated prompt–response preference pairs covering four quality dimensions with high inter-annotator agreement in 47 language varieties.We release our dataset and evaluation framework to support further research in multilingual LLM evaluation. |
Chenxi Whitehouse; Sebastian Ruder; Tony Zhiyang Lin; Oksana Kurylo; Haruka Takagi; Janice Lam; Nicolò Busetto; Denise Diaz; |
| 289 | Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Repetitive lexical patterns in LLM output, termed slop, degrade writing quality through over-use and make AI-generated text immediately recognizable. We present Antislop, a comprehensive framework providing tools to both detect and eliminate these overused patterns. |
Samuel J Paech; Allen G Roush; Judah Goldfeder; Ravid Shwartz-Ziv; |
| 290 | From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Analyzing embeddings from 40+ LLMs against classic human categorization benchmarks, we uncover three key findings. First, LLMs broadly align with human categories but miss fine-grained semantic distinctions crucial for human understanding. Second, LLMs demonstrate aggressive statistical compression, achieving “optimal” information-theoretic efficiency, while humans prioritize contextual richness and adaptive flexibility. Third, encoder models surprisingly outperform decoder models in human alignment, suggesting that generation and understanding rely on distinct mechanisms in current architectures. |
Chen Shani; Liron Soffer; Dan Jurafsky; Yann LeCun; Ravid Shwartz-Ziv; |
| 291 | GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we develop a novel strategy to compress models by strategically combining or merging layers from finetuned model variants, which preserves the original model’s abilities by aggregating capabilities accentuated in different finetunes. |
Guinan Su; Li Shen; Lu Yin; Shiwei Liu; Yanwu Yang; Jonas Geiping; |
| 292 | Estimating Worst-Case Frontier Risks of Open-Weight LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we study the worst-case frontier risks of the OpenAI gpt-oss model. |
Eric Wallace; Olivia Watkins; Miles Wang; Kai Chen; Chris Koch; |
| 293 | DiffusionBlocks: Block-wise Neural Network Training Via Diffusion Interpretation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose $\textit{DiffusionBlocks}$, a principled framework for transforming transformer-based networks into genuinely independent trainable blocks that maintain competitive performance with end-to-end training. |
Makoto Shing; Masanori Koyama; Takuya Akiba; |
| 294 | STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. |
Yushi LAN; Yihang Luo; Fangzhou Hong; Shangchen Zhou; Honghua Chen; Zhaoyang Lyu; Bo Dai; Shuai Yang; Chen Change Loy; Xingang Pan; |
| 295 | Theoretical Guarantees for Causal Discovery on Large Random Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We investigate theoretical guarantees for the \emph{false-negative rate} (FNR)—the fraction of true causal edges whose orientation is not recovered, under single-variable random interventions and an $\epsilon$-interventional faithfulness assumption that accommodates latent confounding. |
Mathieu Chevalley; Arash Mehrjou; Patrick Schwab; |
| 296 | Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Second, multi-agent pipelines often dilute strong solutions by averaging across all candidates. We address these challenges with a unified framework that combines implicit retrieval and structured collaboration. |
Xiangru Tang; Wanghan Xu; Yujie Wang; Zijie Guo; Daniel Shao; Cixuan Zhang; Ziyi Wang; Lixin Zhang; Guancheng Wan; Zhenfei Yin; Wenlong Zhang; LEI BAI; Philip Torr; Hanrui Wang; Di Jin; |
| 297 | AstaBench: Rigorous Benchmarking of AI Agents with A Scientific Research Suite Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Using these, we present AstaBench, a suite that provides a holistic measure of agentic ability to perform scientific research, comprising 2400+ problems spanning the entire scientific discovery process and multiple scientific domains, and including many problems inspired by actual user requests to deployed Asta agents. |
Jonathan Bragg; Mike D’Arcy; Nishant Balepur; Dan Bareket; Bhavana Dalvi Mishra; Sergey Feldman; Dany Haddad; Jena D. Hwang; Peter Jansen; Varsha Kishore; Bodhisattwa Prasad Majumder; Aakanksha Naik; Sigal Rahamimov; Kyle Richardson; Amanpreet Singh; Harshit Surana; Aryeh Tiktinsky; Rosni Vasu; Guy Wiener; Chloe Anastasiades; Stefanus Candra; Jason Dunkelberger; Daniel Emery; Rob Evans; Malachi Hamada; Regan Huff; Rodney Kinney; Matt Latzke; Jaron Lochner; Ruben Lozano-Aguilera; Ngoc-Uyen Nguyen; Smita Rao; Amber Tanaka; Brooke Vlahos; Peter Clark; Doug Downey; Yoav Goldberg; Ashish Sabharwal; Daniel S Weld; |
| 298 | Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We aim to improve the reasoning capabilities of language models via reinforcement learning with verifiable rewards (RLVR). |
Shubham Parashar; Shurui Gui; Xiner Li; Hongyi Ling; Sushil Vemuri; Blake Olson; Eric Li; Yu Zhang; James Caverlee; Dileep Kalathil; Shuiwang Ji; |
| 299 | Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we address this limitation by scaling up tool-based interactions and introduce Mini-o3, a system that executes deep, multi-turn reasoning—spanning tens of steps—and achieves state-of-the-art performance on challenging visual search tasks.First, we construct the Visual Probe Dataset, a collection of thousands of challenging visual search problems designed for exploratory reasoning. |
Xin Lai; Junyi Li; Wei Li; Tao Liu; Tianjian Li; Hengshuang Zhao; |
| 300 | Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we focus on data scaling, curating a set of 2.5M samples spanning five unique evaluation tasks (pairwise, step-level, reference-free and reference-based verification, and single rating) and multiple domains focused on reasoning evaluation. |
Austin Xu; Xuan-Phi Nguyen; Yilun Zhou; Chien-Sheng Wu; Caiming Xiong; Shafiq Joty; |
| 301 | Boosting Multi-Domain Reasoning of LLMs Via Curvature-Guided Policy Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, approaches to mitigate such conflicts and enhance multi-domain reasoning remain largely underexplored. To address this challenge, we propose **C**urvature-**G**uided **P**olicy **O**ptimization (**CGPO**), a principled and scalable training framework to advance the multi-domain reasoning of LLMs. |
Xize Liang; Lin Yang; Jie Wang; Rui Liu; Yang Lu; Jinliang Zeng; Hanzhu Chen; Dong Li; Jianye HAO; |
| 302 | H$^3$DP: Triply‑Hierarchical Diffusion Policy for Visuomotor Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Triply-Hierarchical Diffusion Policy (H$^3$DP), a novel visuomotor learning framework that explicitly incorporates hierarchical structures to strengthen the integration between visual features and action generation. |
Yiyang Lu; Yufeng Tian; Zhecheng Yuan; Xianbang Wang; Pu Hua; Zhengrong Xue; Huazhe Xu; |
| 303 | Learning-Time Encoding Shapes Unlearning in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we empirically investigate how learning-time encoding in knowledge encoding impact the effectiveness of unlearning factual knowledge. |
Ruihan Wu; Konstantin Garov; Kamalika Chaudhuri; |
| 304 | Verifying Chain-of-Thought Reasoning Via Its Computational Graph Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce a white-box method: \textbf{Circuit-based Reasoning Verification (CRV)}. |
Zheng Zhao; Yeskendir Koishekenov; Xianjun Yang; Naila Murray; Nicola Cancedda; |
| 305 | ELEPHANT: Measuring and Understanding Social Sycophancy in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this gap, we introduce **social sycophancy**, characterizing sycophancy as excessive preservation of a user’s _face_ (their desired self-image), and present **ELEPHANT**, a benchmark for measuring social sycophancy in an LLM.Our work provides theoretical grounding and an empirical benchmark for understanding and addressing sycophancy in the open-ended contexts that characterize the vast majority of LLM use cases. |
Myra Cheng; Sunny Yu; Cinoo Lee; Pranav Khadpe; Lujain Ibrahim; Dan Jurafsky; |
| 306 | Anime-Ready: Controllable 3D Anime Character Generation with Body-Aligned Component-Wise Garment Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Previous approaches for 3D anime character generation often suffer from low mesh quality and blurry textures, and they typically do not provide corresponding skeletons, limiting their usability in animation. In this work, we present a novel framework for high-quality 3D anime character generation that overcomes these limitations by combining the expressive power of the Skinned Multi-Person Linear (SMPL) model with precise garment generation. |
Jiachen Qian; Hongye Yang; Youtian Lin; tianhao zhao; Feihu Zhang; Yao Yao; Hengshuang Zhao; |
| 307 | MemGen: Weaving Generative Latent Memory for Self-Evolving Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing paradigms remain constrained: parametric memory forcibly adjusts model parameters, and retrieval-based memory externalizes experience into structured databases, yet neither captures the fluid interweaving of reasoning and memory that underlies human cognition. To address this gap, we propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty. |
Guibin Zhang; Muxin Fu; Shuicheng YAN; |
| 308 | AgenTracer: Who Is Inducing Failure in The LLM Agentic Systems? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current state-of-the-art reasoning LLMs, however, remain strikingly inadequate for this challenge, with accuracy generally below $10\\%$. To address this gap, we propose AgenTracer, the first automated framework for annotating failed multi-agent trajectories via counterfactual replay and programmed fault injection, producing the curated dataset TracerTraj. |
Guibin Zhang; Junhao Wang; Junjie Chen; Wangchunshu Zhou; Kun Wang; Shuicheng YAN; |
| 309 | Soft Tokens, Hard Truths Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, practical use of continuous tokens has been limited by strong training difficulties: previous works either just use continuous tokens at inference time on a pre-trained discrete-token model, or must distill the continuous CoT from ground-truth discrete CoTs and face computational costs that limit the CoT to very few tokens. This is the first work introducing a scalable method to learn continuous CoTs via reinforcement learning (RL), without distilling from reference discrete CoTs. |
Natasha Butt; Ariel Kwiatkowski; Ismail Labiad; Julia Kempe; Yann Ollivier; |
| 310 | Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: But the fact that this also occurs under hard distillation—where the student only sees sampled tokens—raises a deeper question: *when and how does subliminal learning actually occur? * We answer this question through controlled experiments and mechanistic analysis. |
Simon Schrodi; Elias Kempf; Fazl Barez; Thomas Brox; |
| 311 | Relational Graph Transformer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Here we introduce the Relational Graph Transformer (RelGT), the first graph transformer architecture designed specifically for relational tables. |
Vijay Prakash Dwivedi; Sri Jaladi; Yangyi Shen; Federico Lopez; Charilaos I. Kanatsoulis; Rishi Puri; Matthias Fey; Jure Leskovec; |
| 312 | DiffusionNFT: Online Diffusion Reinforcement with Forward Process Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Diffusion Negative-aware FineTuning (DiffusionNFT), a new online RL paradigm that optimizes diffusion models directly on the forward process via flow matching. |
Kaiwen Zheng; Huayu Chen; Haotian Ye; Haoxiang Wang; Qinsheng Zhang; Kai Jiang; Hang Su; Stefano Ermon; Jun Zhu; Ming-Yu Liu; |
| 313 | InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we discard the single-entity assumption and introduce a novel framework that enforces strong, region‑specific binding of conditions from modalities to each identity’s spatiotemporal footprint. |
Zhenzhi Wang; Jiaqi Yang; Jianwen Jiang; Chao Liang; Gaojie Lin; Zerong Zheng; Ceyuan Yang; Yuan Zhang; Mingyuan Gao; Dahua Lin; |
| 314 | CapRL: Stimulating Dense Image Caption Capabilities Via Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To overcome the limitation of SFT, we propose applying the Reinforcement Learning with Verifiable Rewards (RLVR) paradigm to the open-ended task of image captioning. |
Long Xing; Xiaoyi Dong; Yuhang Zang; Yuhang Cao; Jianze Liang; Qidong Huang; Jiaqi Wang; Feng Wu; Dahua Lin; |
| 315 | ScaleCap: Scalable Image Captioning Via Dual-Modality Debiasing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper presents ScaleCap, a scalable image captioning strategy that generates comprehensive and detailed image captions. |
Long Xing; Qidong Huang; Xiaoyi Dong; Pan Zhang; Yuhang Zang; Yuhang Cao; Jinsong Li; Shuangrui Ding; Weiming Zhang; Nenghai Yu; Jiaqi Wang; Feng Wu; Dahua Lin; |
| 316 | AceReason-Nemotron 1.1: Advancing Math and Code Reasoning Through SFT and RL Synergy Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we investigate the synergy between supervised fine-tuning (SFT) and reinforcement learning (RL) in developing strong reasoning models. |
Zihan Liu; Zhuolin Yang; Yang Chen; Chankyu Lee; Mohammad Shoeybi; Bryan Catanzaro; Wei Ping; |
| 317 | LLM Pretraining with Continuous Concepts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Continuous Concept Mixing (CoCoMix), a novel pretraining framework that combines discrete next token prediction with continuous concepts. |
Jihoon Tack; Jack Lanchantin; Jane Yu; Andrew Cohen; Ilia Kulikov; Janice Lan; Shibo Hao; Yuandong Tian; Jason E Weston; Xian Li; |
| 318 | BiasFreeBench: A Benchmark for Mitigating Bias in Large Language Model Responses Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To enable consistent evaluation across debiasing methods and bridge this gap, we introduce **BiasFreeBench**, an empirical benchmark that comprehensively compares eight mainstream bias mitigation techniques (covering four prompting-based and four training-based methods) on two test scenarios (multi-choice QA and open-ended multi-turn QA) by reorganizing existing datasets into a unified query-response setting.We release our benchmark, aiming to establish a unified testbed for bias mitigation research [https://github.com/xxupiano/BiasFreeBench](https://github.com/xxupiano/BiasFreeBench). |
Xin Xu; Xunzhi He; Churan Zhi; Ruizhe Chen; Julian McAuley; Zexue He; |
| 319 | Visual Autoregressive Modeling for Instruction-Guided Image Editing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present VAREdit, a visual autoregressive (VAR) framework that reframes image editing as a next-scale prediction problem. |
Qingyang Mao; Qi Cai; Yehao Li; Yingwei Pan; Mingyue Cheng; Ting Yao; Qi Liu; Tao Mei; |
| 320 | Vid2World: Crafting Video Diffusion Models to Interactive World Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present _Vid2World_, a general approach for leveraging and transferring pre-trained video diffusion models into interactive world models. |
Siqiao Huang; Jialong Wu; Qixing Zhou; Shangchen Miao; Mingsheng Long; |
| 321 | ManagerBench: Evaluating The Safety-Pragmatism Trade-off in Autonomous LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, they overlook the challenge of agents taking harmful actions when the most effective path to an operational goal conflicts with human safety. To address this gap, we introduce ManagerBench, a benchmark that evaluates LLM decision-making in realistic, human-validated managerial scenarios. |
Adi Simhi; Jonathan Herzig; Martin Tutek; Itay Itzhak; Idan Szpektor; Yonatan Belinkov; |
| 322 | Composition-Grounded Data Synthesis for Visual Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce COGS (COmposition-Grounded instruction Synthesis), a data-efficient framework for equipping MLLMs with advanced reasoning abilities from a small set of seed questions.We release the code and data at https://cogsynthesis.github.io. |
Xinyi Gu; Jiayuan Mao; Zhang-Wei Hong; Zhuoran Yu; Pengyuan Li; Dhiraj Joshi; Rogerio Feris; Zexue He; |
| 323 | It’s All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building upon these insights, we present Miras, a general framework to design deep learning architectures based on the choice of attentional bias objective, retention gate, associative memory architecture, and memory learning algorithm.Going beyond $L_2$ loss function, we present a set of alternative attentional bias configurations along with their effective approximations. |
Ali Behrouz; Meisam Razaviyayn; Peilin Zhong; Vahab Mirrokni; |
| 324 | Reusing Pre-Training Data at Test Time Is A Compute Multiplier Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Large language models learn from their vast pre-training corpora, gaining the ability to solve an ever increasing variety of tasks; yet although researchers work to improve these datasets, there is little effort to understand how efficient the pre-training apparatus is at extracting ideas and knowledge from the data. In this work, we use retrieval augmented generation along with test-time compute as a way to quantify how much dataset value was left behind by the process of pre-training, and how this changes across scale. |
Alex Fang; Thomas Voice; Ruoming Pang; Ludwig Schmidt; Tom Gunter; |
| 325 | Planner Aware Path Learning in Diffusion Language Models Training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we systematically investigate the mismatch of discrete diffusion training and inference under planning and theoretically prove that the standard discrete diffusion training evidence lower bound (ELBO) does not accurately describe a denoiser that uses a non-uniform planner. |
Fred Zhangzhi Peng; Zachary Bezemek; Jarrid Rector-Brooks; Shuibai Zhang; Michael M. Bronstein; Anru Zhang; Joey Bose; Alexander Tong; |
| 326 | Addressing Divergent Representations from Causal Interventions on Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: First, we demonstrate theoretically and empirically that common causal intervention techniques often do shift internal representations away from the natural distribution of the target model. Then, we provide a theoretical analysis of two cases of such divergences: harmless divergences that occur in the behavioral null-space of the layer(s) of interest, and pernicious divergences that activate hidden network pathways and cause dormant behavioral changes. |
Satchel Grant; Simon Jerome Han; Alexa R. Tartaglini; Christopher Potts; |
| 327 | LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present LLM-guided Evolution for Materials design (**LLEMA**), a unified framework that couples the scientific knowledge embedded in large language models with chemistry-informed evolutionary rules and memory-based refinement. |
Nikhil Abhyankar; Sanchit Kabra; Saaketh Desai; Chandan K. Reddy; |
| 328 | CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with A Single Model Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce CUPID (Comprehensive Uncertainty Plug-in estImation moDel), a general-purpose module that jointly estimates aleatoric and epistemic uncertainty without modifying or retraining the base model. |
Xinran Xu; Xiuyi Fan; |
| 329 | Multiplayer Nash Preference Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Multiplayer Nash Preference Optimization (MNPO), a novel framework that generalizes NLHF to the multiplayer regime. |
Fang Wu; Xu Huang; Weihao Xuan; Zhiwei Zhang; Yijia Xiao; Guancheng Wan; Xiaomin Li; Bing Hu; Peng Xia; Jure Leskovec; Yejin Choi; |
| 330 | DeepSearch: Overcome The Bottleneck of Reinforcement Learning with Verifiable Rewards Via Tree-based Search Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present DeepSearch, a framework that integrates Monte Carlo Tree Search (MCTS) directly into RLVR training. |
Fang Wu; Weihao Xuan; Heli Qi; Aaron Tu; Ximing Lu; Li Erran Li; Yejin Choi; |
| 331 | Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce LGTM (Less Gaussians, Texture More), a feed-forward and pose-free framework that predicts both compact geometric primitives and associated per-primitive texture maps in a single forward pass without per-scene optimization. |
Yixing Lao; Xuyang BAI; Xiaoyang Wu; Nuoyuan Yan; Zixin Luo; Tian Fang; Jean-Daniel Nahmias; Yanghai Tsin; Shiwei Li; Hengshuang Zhao; |
| 332 | Unleashing Guidance Without Classifiers for Human-Object Interaction Animation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a data-driven alternative in which guidance emerges from the denoising pace itself, reducing dependence on manually designed priors. |
Ziyin Wang; Sirui Xu; chuan guo; Bing Zhou; Jiangshan Gong; Jian Wang; Yu-Xiong Wang; Liangyan Gui; |
| 333 | Tracing The Traces: Latent Temporal Signals for Efficient and Accurate Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Latent-Trajectory signals that characterize the temporal evolution of a model’s internal representations during the generation of intermediate reasoning tokens. |
Martina G. Vilas; Safoora Yousefi; Besmira Nushi; Eric Horvitz; Vidhisha Balachandran; |
| 334 | DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce DeepTRACE, a novel sociotechnically grounded audit framework that turns prior community-identified failure cases into eight measurable dimensions spanning answer text, sources, and citations. |
Pranav Narayanan Venkit; Philippe Laban; Yilun Zhou; Kung-Hsiang Huang; Yixin Mao; Chien-Sheng Wu; |
| 335 | Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce DeceptionDecoded, a large-scale benchmark of 12,000 image–caption pairs grounded in trustworthy reference articles, created using an intent-guided simulation framework that models both the desired influence and the execution plan of news creators. |
Jiaying Wu; Fanxiao Li; Zihang Fu; Min-Yen Kan; Bryan Hooi; |
| 336 | Sparse Attention Adaptation for Long Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SeerAttention-R, a sparse attention framework specifically tailored for the long decoding of reasoning models. |
Yizhao Gao; Shuming Guo; Shijie Cao; Yuqing Xia; Yu Cheng; Lei Wang; Lingxiao Ma; Yutao Sun; Tianzhu Ye; Li Dong; Hayden Kwok-Hay So; Yu Hua; Ting Cao; Fan Yang; Mao Yang; |
| 337 | Adapting Self-Supervised Representations As A Latent Space for Efficient Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision transformers. |
Ming Gui; Johannes Schusterbauer; Timy Phan; Felix Krause; Joshua M. Susskind; Miguel Ángel Bautista; Björn Ommer; |
| 338 | CyberGym: Evaluating AI Agents’ Real-World Cybersecurity Capabilities at Scale Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static outcomes, failing to capture the full, dynamic range of real-world security challenges. To address these limitations, we introduce CyberGym, a large-scale benchmark featuring 1,507 real-world vulnerabilities across 188 software projects. |
Zhun Wang; Tianneng Shi; Jingxuan He; Matthew Cai; Jialin Zhang; Dawn Song; |
| 339 | Jackpot: Align Actor-Policy Distribution for Scalable and Stable RL for LLM Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing importance sampling–based corrections for distribution mismatch suffer from an inherent trade-off between stability and training performance. To tackle this problem, we propose Jackpot, which leverages Optimal Budget Rejection Sampling to directly reduce the gap between actor and policy distributions. |
Zhuoming Chen; Hongyi Liu; Yang Zhou; Haizhong Zheng; Beidi Chen; |
| 340 | Video-As-Prompt: Unified Semantic Control for Video Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods either introduce artifacts by enforcing inappropriate pixel-wise priors from structure-based controls, or rely on non-generalizable, condition-specific finetuning or task-specific architectures. We introduce Video-As-Prompt (VAP), a new paradigm that reframes this problem as in-context generation. |
Yuxuan Bian; Xin Chen; Zenan Li; Tiancheng Zhi; Shen Sang; Linjie Luo; Qiang Xu; |
| 341 | VLMgineer: Vision-Language Models As Robotic Toolsmiths Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present VLMgineer, the first fully automatic framework designs tools and actions from scratch by harnessing the creativity of Vision–Language Models (VLMs) together with evolutionary search.To facilitate future research on automated tool invention, we will release our benchmark and code. |
George Jiayuan Gao; Tianyu Li; Junyao Shi; Yihan Li; Zizhe Zhang; Nadia Figueroa; Dinesh Jayaraman; |
| 342 | DuPO: Enabling Reliable Self-Verification Via Dual Preference Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present DuPO, a dual learning-based preference optimization framework that generates annotation-free feedback via the generalized duality. |
Shuaijie She; Yu Bao; Yu Lu; Lu Xu; Tao Li; Wenhao Zhu; Jianbing Zhang; Shujian Huang; Shanbo Cheng; Lu Lu; Yuxuan Wang; |
| 343 | DParallel: Learnable Parallel Decoding for DLLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Yet, their parallel decoding potential remains largely underexplored, as existing open-source models still require nearly token-length decoding steps to ensure performance. To address this, we introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling. |
Zigeng Chen; Gongfan Fang; Xinyin Ma; Ruonan Yu; Xinchao Wang; |
| 344 | Sparse Autoencoders Trained on The Same Data Learn Different Features Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: For example, in an SAE with 131K latents trained on a feedforward network in Llama 3 8B, only 30% of the features were shared across different seeds. We observed this phenomenon across multiple layers of three different LLMs, two datasets, and several SAE architectures. |
Gonçalo Paulo; Nora Belrose; |
| 345 | Evaluating SAE Interpretability Without Generating Explanations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This method makes it difficult to disentangle the explanation generation and evaluation process from the actual interpretability of the features in the sparse coder. In this work, we adapt existing methods to assess the interpretability of sparse coders, with the advantage that they do not require generating natural language explanations as an intermediate step. |
Gonçalo Paulo; Nora Belrose; |
| 346 | No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose an annotation-free training framework that improves both reasoning and grounding. |
Damiano Marsili; Georgia Gkioxari; |
| 347 | Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present MedVLSynther, a rubric-guided generator-verifier framework that synthesizes high-quality multiple-choice VQA items directly from open biomedical literature by conditioning on figures, captions, and in-text references. |
Xiaoke Huang; Ningsen Wang; Hui Liu; Xianfeng Tang; Yuyin Zhou; |
| 348 | Conformalized Hierarchical Calibration for Uncertainty-Aware Adaptive Hashing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing methods face two critical limitations: target domain noise severely misleads model training, and indiscriminate domain alignment strategies treat all target samples equally, potentially distorting essential feature structures. We propose an uncertainty-aware adaptive hashing approach that addresses these challenges through a hierarchical conformal calibration framework. |
Junyu Luo; Jinsheng Huang; Yang Xu; Lutong Zou; Xiao Luo; Bohan Wu; Yifan Wang; Wei Ju; Ming Zhang; |
| 349 | Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this issue, we first empirically demonstrate that the model’s suboptimal predictions can be effectively refined using sub-networks of the model itself, without requiring additional training or the integration of external modules. Building on this insight, we propose **$S^2$-Guidance ($S$tochastic $S$elf-Guidance)**, a novel method that leverages stochastic block-dropping during the denoising process to construct sub-networks. |
Chubin Chen; Jiashu Zhu; Xiaokun Feng; Nisha Huang; Chen Zhu; Meiqi Wu; Fangyuan Mao; Jiahong Wu; Xiangxiang Chu; Xiu Li; |
| 350 | UALM: Unified Audio Language Model for Understanding, Generation and Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces Unified Audio Language Model (UALM), which aims to unify audio understanding, text-to-audio generation, and multimodal reasoning in a single model. |
Jinchuan Tian; Sang-gil Lee; Zhifeng Kong; Sreyan Ghosh; Arushi Goel; Chao-Han Huck Yang; Wenliang Dai; Zihan Liu; Hanrong Ye; Shinji Watanabe; Mohammad Shoeybi; Bryan Catanzaro; Rafael Valle; Wei Ping; |
| 351 | Continual Low-Rank Adapters for LLM-based Generative Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing LoRA-based continual methods primarily focus on preserving performance on previous tasks, but this overlooks the unique nature of recommendation: the goal is not to predict past preferences, and outdated preferences can even harm performance when current interests shift significantly. To address this, we propose PESO (Proximally rEgularized Single evolving lOra, a continual adaptation method for LoRA in recommendation. |
Hyunsik Yoo; Ting-Wei Li; SeongKu Kang; Zhining Liu; Charlie Xu; Qilin Qi; Hanghang Tong; |
| 352 | Neural Synchrony Between Socially Interacting Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Although large language models (LLMs) are widely accepted as powerful approximations of human behavior, with multi-LLM system being extensively explored to enhance their capabilities, it remains controversial whether they can be meaningfully compared to human social minds. In this work, we explore neural synchrony between socially interacting LLMs as an empirical evidence for this debate. |
Zhining Zhang; Wentao Zhu; Chi Han; Yizhou Wang; Heng Ji; |
| 353 | ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose ReST-KV, a robust KV eviction method that combines layer-wise output **Re**construction and **S**patial-**T**emporal smoothing to provide a more comprehensive perspective for the KV cache eviction task. |
Yongqi An; Chang Lu; Kuan Zhu; Tao Yu; Chaoyang Zhao; Hong Wu; Ming Tang; Jinqiao Wang; |
| 354 | VeriTrail: Closed-Domain Hallucination Detection with Traceability Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this need, we present VeriTrail, the first closed-domain hallucination detection method designed to provide traceability for both MGS and SGS processes.We also introduce the first datasets to include all intermediate outputs as well as human annotations of final outputs’ faithfulness for their respective MGS processes. |
Dasha Metropolitansky; Jonathan Larson; |
| 355 | Output Supervision Can Obfuscate The Chain of Thought Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Second, since later tokens are conditioned on earlier ones, safe‑looking CoTs may increase the likelihood of safe outputs, causing safe-looking CoTs to be reinforced. We introduce two mitigations to address these two issues, which achieve a Pareto improvement in terms of monitorability and task performance compared to regular training. |
jacob drori; Luke Marks; Bryce Woodworth; Alex Cloud; Alexander Matt Turner; |
| 356 | Code World Models for General Game Playing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here we introduce an alternative approach: We use the LLM to translate natural language rules and game trajectories into a formal, executable world model represented as Python code. |
Wolfgang Lehrach; Daniel Hennes; Miguel Lazaro-Gredilla; Xinghua Lou; Carter Wendelken; Zun Li; Antoine Dedieu; Marc Lanctot; Atil Iscen; John Schultz; Marcus Chiam; Ian Gemp; Piotr Zielinski; Satinder Singh; Kevin Patrick Murphy; |
| 357 | ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the asynchronous sampling and irregular intervals inherent to IMTS pose two core challenges for existing methods: (1) how to accurately represent the raw information of irregular time series without introducing data distortion, and (2) how to effectively capture the complex dynamic dependencies between observation points. To address these challenges, we propose the Adaptive Spatio-Temporal Graph Interaction (ASTGI) framework. |
Xvyuan Liu; Xiangfei Qiu; Hanyin Cheng; Xingjian Wu; Chenjuan Guo; Bin Yang; Jilin Hu; |
| 358 | Learning to Orchestrate Agents in Natural Language with The Conductor Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce a new kind of Conductor model trained with reinforcement learning to automatically discover powerful coordination strategies among LLMs. |
Stefan Nielsen; Edoardo Cetin; Peter Schwendeman; Qi Sun; Jinglue Xu; Yujin Tang; |
| 359 | EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the challenges posed by our benchmark, we present EvoTest, an evolutionary test-time learning framework that improves an agent without any fine-tuning or gradients—by evolving the entire agentic system after every episode. |
Yufei He; Juncheng Liu; Yue Liu; Yibo Li; Tri Cao; Zhiyuan Hu; Xinxing Xu; Bryan Hooi; |
| 360 | Control Tax: The Price of Keeping AI in Check Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To study this problem better, we introduce the notion of Control tax—the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. |
Mikhail Terekhov; Zhen Ning David Liu; Caglar Gulcehre; Samuel Albanie; |
| 361 | Doxing Via The Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we identify a novel category of privacy leakage in MLRMs: Adversaries can infer sensitive geolocation information, such as users’ home addresses or neighborhoods, from user-generated images, including selfies captured in private settings. |
Weidi Luo; Tianyu Lu; Qiming Zhang; Xiaogeng Liu; Bin Hu; Yue Zhao; Jieyu Zhao; Song Gao; Patrick McDaniel; Zhen Xiang; Chaowei Xiao; |
| 362 | TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Through detailed empirical analyses, we identify that existing PRMs, though widely adopted for supervising text-only reasoning steps, struggle with table-specific operations such as sub-table retrieval and schema interaction, leading to critical performance bottlenecks. To address this limitation, we propose TaTToo, a novel table-grounded PRM framework that (i) reasons explicitly over tabular reasoning steps and (ii) integrates tool-based verification to provide precise reward supervision. |
Jiaru Zou; Soumya Roy; Vinay Kumar Verma; Ziyi Wang; David Wipf; Pan Lu; Sumit Negi; James Zou; Jingrui He; |
| 363 | What’s In My Human Feedback? Learning Interpretable Descriptions of Preference Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce *What’s In My Human Feedback* (WIMHF), a method that produces human-interpretable, natural language features from preference data using sparse autoencoders. |
Rajiv Movva; Smitha Milli; Sewon Min; Emma Pierson; |
| 364 | GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: This paper empirically investigates the limitations of VLMs in 3D spatial knowledge, revealing that their primary shortcoming lies in the lack of global-local correspondence between the scene and individual frames. To address this, we introduce GPT4Scene, a novel visual prompting paradigm in VLM training and inference that helps build the global-local relationship, significantly improving the 3D spatial understanding of indoor scenes. |
Zhangyang Qi; Zhixiong Zhang; Ye Fang; Jiaqi Wang; Hengshuang Zhao; |
| 365 | Front-Loading Reasoning: The Synergy Between Pretraining and Post-Training Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Could earlier inclusion risk overfitting and harm generalization, or instead establish durable foundations that later fine-tuning cannot recover? To address these questions, we conduct the first systematic study of how reasoning data—varying in scale, diversity, and quality—affects LLM performance when introduced at different stages of training. |
Syeda Nahida Akter; Shrimai Prabhumoye; Eric Nyberg; Mostofa Patwary; Mohammad Shoeybi; Yejin Choi; Bryan Catanzaro; |
| 366 | Reevaluating Policy Gradient Methods for Imperfect-Information Games Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To facilitate the resolution of this hypothesis, we implement and release the first broadly accessible exact exploitability computations for five large games. Using these games, we conduct the largest-ever exploitability comparison of DRL algorithms for imperfect-information games. |
Max Rudolph; Nathan Lichtlé; Sobhan Mohammadpour; Alexandre M Bayen; J Zico Kolter; Amy Zhang; Gabriele Farina; Eugene Vinitsky; Samuel Sokota; |
| 367 | Generative Universal Verifier As Multimodal Meta-Reasoner Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce *Generative Universal Verifier*, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. |
Xinchen Zhang; Xiaoying Zhang; Youbin Wu; Yanbin Cao; Renrui Zhang; Ruihang Chu; Ling Yang; Yujiu Yang; Guang Shi; |
| 368 | ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Pairwise Rotation Quantization (ParoQuant), a PTQ method that combines hardware-efficient and optimizable independent Givens rotations with channel-wise scaling to even out the magnitudes across channels and narrow the dynamic range within each quantization group, effectively addressing the outlier issue. |
Yesheng Liang; Haisheng Chen; Song Han; Zhijian Liu; |
| 369 | Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In parallel, text describing the visual world proves crucial, though its performance impact saturates rapidly. Leveraging these insights, we propose a data-centric recipe for pre-training vision-aware LLMs and verify it in 1T token scale pre-training. |
Junlin Han; Shengbang Tong; David Fan; Yufan Ren; Koustuv Sinha; Philip Torr; Filippos Kokkinos; |
| 370 | Understanding Vs. Generation: Navigating Optimization Dilemma in Multimodal Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We analyzed this trade-off and identify the primary cause might be the potential conflict between generation and understanding, which creates a competitive dynamic within the model. To address this, we propose the Reason-Reflect-Refine (R3) framework. |
Sen Ye; Mengde Xu; Shuyang Gu; Di He; Liwei Wang; Winston Hu; |
| 371 | KL-Regularized Reinforcement Learning for Generative Modelling Is Designed to Mode Collapse Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Building on this perspective, we introduce a simple and scalable modification that rescales rewards to induce target distributions assigning substantial probability across _all_ high-reward regions. |
Anthony GX-Chen; Jatin Prakash; Jeff Guo; Rob Fergus; Rajesh Ranganath; |
| 372 | VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce \textbf{VLM4VLA}, a minimal adaptation pipeline that converts general-purpose VLMs into VLA policies using only a small set of new learnable parameters for fair and efficient comparison. |
Jianke Zhang; Xiaoyu Chen; Yanjiang Guo; Yucheng Hu; Jianyu Chen; |
| 373 | Tree Search for LLM Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. |
Yuxiang Ji; Ziyu Ma; Yong Wang; Guanhua Chen; Xiangxiang Chu; Liaoni Wu; |
| 374 | To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In fact, we show that given the right choice of tool access and problem-dependent training data, SSMs can learn to solve any tractable problem and generalize to arbitrary problem length/complexity (i.e., achieve length generalization). |
Eran Malach; Omid Saremi; Sinead Williamson; Arwen Bradley; Aryo Lotfi; Emmanuel Abbe; Joshua M. Susskind; Etai Littwin; |
| 375 | AnyUp: Universal Feature Upsampling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. |
Thomas Wimmer; Prune Truong; Marie-Julie Rakotosaona; Michael Oechsle; Federico Tombari; Bernt Schiele; Jan Eric Lenssen; |
| 376 | SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we revisit stochastic gradient descent (SGD) with AdaGrad-type preconditioning. |
Dmitry Kovalev; |
| 377 | Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we challenge whether high SFT scores translate to improved performance after RL. |
Feiyang Kang; Michael Kuchnik; Karthik Padthe; Marin Vlastelica; Ruoxi Jia; Carole-Jean Wu; Newsha Ardalani; |
| 378 | Language Models Use Lookbacks to Track Beliefs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our investigation uncovered a pervasive algorithmic pattern that we call a lookback mechanism, which enables the LM to recall important information when it becomes necessary. |
Nikhil Prakash; Natalie Shapira; Arnab Sen Sharma; Christoph Riedl; Yonatan Belinkov; Tamar Rott Shaham; David Bau; Atticus Geiger; |
| 379 | Stable Video Infinity: Infinite-Length Video Generation with Error Recycling Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose **Stable Video Infinity (SVI)** that can generate non-looping, ultra-long videos with stable visual quality, while supporting per-clip prompt control and multi-modal conditioning. |
Wuyang Li; Wentao Pan; Po-Chien Luan; Yang Gao; Alexandre Alahi; |
| 380 | Emergent Hierarchical Reasoning in LLMs Through Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This insight exposes a core inefficiency in prevailing RL algorithms like GRPO, which apply optimization pressure agnostically and dilute the learning signal across all tokens. To address this, we propose Hierarchy-Aware Credit Assignment (HICRA), an algorithm that concentrates optimization efforts on high-impact planning tokens. |
Haozhe Wang; Qixin Xu; Che Liu; Junhong Wu; Fangzhen Lin; Wenhu Chen; |
| 381 | SWERank: Software Issue Localization with Code Ranking Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Alternatively, traditional code ranking models, typically optimized for query-to-code or code-to-code retrieval, struggle with the verbose and failure-descriptive nature of issue localization queries. To bridge this gap, we introduce SWERank, an efficient and effective retrieve-and-rerank framework for software issue localization. |
Revanth Gangi Reddy; Tarun Suresh; JaeHyeok Doo; Ye Liu; Xuan-Phi Nguyen; Yingbo Zhou; Semih Yavuz; Caiming Xiong; Heng Ji; Shafiq Joty; |
| 382 | MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce MetaEmbed, a new framework for multimodal retrieval that rethinks how multimodal embeddings are constructed and interacted with at scale. |
Zilin Xiao; Qi Ma; Mengting Gu; Chun-cheng Jason Chen; Xintao Chen; Vicente Ordonez; Vijai Mohan; |
| 383 | Learning Robust Intervention Representations with Delta Embeddings Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we show that an effective strategy for improving out of distribution (OOD) robustness is to focus on the representation of actionable counterfactuals in the latent space. |
Panagiotis Alimisis; Christos Diou; |
| 384 | Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Even with this engineering, these approaches still struggle to reliably solve long-horizon, dexterous manipulation tasks. To provide a seamless tool for robotic data generation in simulation, we introduce a simple framework that enables on-policy reinforcement learning to reliably solve an array of such tasks with a single reward function, set of algorithm hyper-parameters, no auto-curricula, and no human demonstrations. |
Patrick Yin; Tyler Westenbroek; Zhengyu Zhang; Ignacio Dagnino; Eeshani Shilamkar; Numfor Mbiziwo-Tiapo; Simran Bagaria; Xinlei Liu; Galen Mullins; Andrey Kolobov; Abhishek Gupta; |
| 385 | FlowRL: Matching Reward Distributions for LLM Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose FlowRL: matching the full reward distribution via flow balancing instead of solely maximizing rewards in large language model (LLM) reinforcement learning (RL). |
Xuekai Zhu; Daixuan Cheng; Dinghuai Zhang; Hengli Li; Kaiyan Zhang; Che Jiang; Youbang Sun; Ermo Hua; Yuxin Zuo; Xingtai Lv; Qizheng Zhang; Lin Chen; Fanghao Shao; Bo Xue; Yunchong Song; Zhenjie Yang; Ganqu Cui; Ning Ding; Jianfeng Gao; Xiaodong Liu; Bowen Zhou; Hongyuan Mei; Zhouhan Lin; |
| 386 | From Data Statistics to Feature Geometry: How Correlations Shape Superposition Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we introduce Bag-of-Words Superposition (BOWS), a framework in which autoencoders (AEs) with a non-linearity are trained to compress sparse, binary bag-of-words vectors drawn from Internet-scale text. |
Lucas Prieto; Edward Stevinson; Melih Barsbey; Tolga Birdal; Pedro A. M. Mediano; |
| 387 | Harder Is Better: Boosting Mathematical Reasoning Via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Data-wise, augmentation approaches primarily rephrase questions to enhance diversity without systematically increasing intrinsic difficulty. To address these issues, we propose a two-dual MathForge framework to improve mathematical reasoning by targeting harder questions from both perspectives, which comprises a Difficulty-Aware Group Policy Optimization (DGPO) algorithm and a Multi-Aspect Question Reformulation (MQR) strategy. |
Yanqi Dai; Yuxiang Ji; Xiao Zhang; Yong Wang; Xiangxiang Chu; Zhiwu Lu; |
| 388 | Scaling Synthetic Task Generation for Agents Via Exploration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing approaches for task generation rely heavily on human annotation or prompting MLLM with limited downstream environment information, which is either costly or poorly scalable as it yield tasks with limited coverage. To remedy this, we present AutoPlay, a scalable pipeline for task generation that explicitly explores interactive environments to discover possible interactions and current state information to synthesize environment-grounded tasks. |
Ram Ramrakhya; Andrew Szot; Omar Attia; Bogdan Mazoure; Anh Tuan Nguyen; Yuhao Yang; Zhe Gan; Harsh Agrawal; Alexander T Toshev; |
| 389 | SR-Scientist: Scientific Equation Discovery With Agentic AI Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as code, submits it for evaluation, and optimizes the equation based on experimental feedback. |
Shijie Xia; Yuhan Sun; Pengfei Liu; |
| 390 | SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we revisit the safety alignment objective itself and demonstrate that it admits a closed-form solution, yielding a theoretically grounded and provably equivalent reformulation that enables a direct and tractable optimization procedure. |
Geon-Hyeong Kim; Yu Jin Kim; Byoungjip Kim; Honglak Lee; Kyunghoon Bae; Youngsoo Jang; Moontae Lee; |
| 391 | A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To jointly enhance accuracy and efficiency, we propose Adaptive Policy Optimization (APO), which enforces adaptive sampling across modes and applies a cost-regularized reward. |
Qianben Chen; Jingyi Cao; Jiayu Zhang; Tianrui Qin; LiXiaowan; King Zhu; Dingfeng Shi; He Zhu; Minghao Liu; Xiaobo Liang; Ge Zhang; Jian Yang; Yuchen Eleanor Jiang; Wangchunshu Zhou; |
| 392 | DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: To this end, we introduce DeepMath-103K, a large-scale mathematical dataset designed with high difficulty (primarily levels 5-9), rigorous decontamination against numerous benchmarks, and verifiable answers for rule-based RL reward. |
Zhiwei He; Tian Liang; Jiahao Xu; Qiuzhi Liu; Xingyu Chen; Yue Wang; Linfeng Song; Dian Yu; Zhenwen Liang; Wenxuan Wang; Zhuosheng Zhang; Rui Wang; Zhaopeng Tu; Haitao Mi; Dong Yu; |
| 393 | Captain Cinema: Towards Short Movie Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present **Captain Cinema**, a generation framework for short movie generation. |
Junfei Xiao; Ceyuan Yang; Lvmin Zhang; Shengqu Cai; Yang Zhao; Yuwei Guo; Gordon Wetzstein; Maneesh Agrawala; Alan Yuille; Lu Jiang; |
| 394 | ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios Via Guidance Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, enhancing the reasoning ability of OLLMs through additional training presents significant challenges, including the need for high-quality data, task-specific adaptation, and substantial computational costs. To address these limitations, we propose ThinkOmni, a training-free and data-free framework that lifts textual reasoning to omni-modal scenarios. |
Yiran Guan; Sifan Tu; Dingkang Liang; Linghao Zhu; Jianzhong Ju; Zhenbo Luo; Jian Luan; Yuliang Liu; Xiang Bai; |
| 395 | SimpleToM: Exposing The Gap Between Explicit ToM Inference and Implicit ToM Application in LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce SimpleToM, a benchmark that advances ToM evaluation along two novel axes. |
Yuling Gu; Oyvind Tafjord; Hyunwoo Kim; Jared Moore; Ronan Le Bras; Peter Clark; Yejin Choi; |
| 396 | RLBFF: Binary Flexible Feedback to Bridge Between Human Feedback & Verifiable Rewards Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose Reinforcement Learning with Binary Flexible Feedback (RLBFF), which combines the versatility of human-driven preferences with the precision of rule-based verification, enabling reward models to capture nuanced aspects of response quality beyond mere correctness. |
Zhilin Wang; Jiaqi Zeng; Olivier Delalleau; Ellie Evans; Daniel Egert; Hoo-Chang Shin; Felipe Soares; Yi Dong; Oleksii Kuchaiev; |
| 397 | Mixture of Mini Experts: Overcoming The Linear Layer Bottleneck in Multiple Instance Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we introduce MAMMOTH, a parameter-efficient, multi-head mixture of experts module designed to improve the performance of any MIL model with minimal alterations to the total number of parameters. |
Daniel Shao; Joel Runevic; Richard J. Chen; Drew FK Williamson; Ahrong Kim; Andrew H. Song; Faisal Mahmood; |
| 398 | Shoot First, Ask Questions Later? Building Rational Agents That Explore and Act Like People Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We develop methods to benchmark and enhance agentic information-seeking, drawing on insights from human behavior. |
Gabriel Grand; Valerio Pepe; Joshua B. Tenenbaum; Jacob Andreas; |
| 399 | TRIBE: TRImodal Brain Encoder for Whole-brain FMRI Response Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Here, we introduce TRIBE, the first deep neural network trained to predict brain responses to stimuli across multiple modalities, cortical areas and individuals. |
Stéphane d’Ascoli; Jérémy Rapin; Yohann Benchetrit; Hubert Banville; Jean-Remi King; |
| 400 | Learning An Image Editing Model Without Image Editing Pairs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present a new training paradigm that eliminates the need for paired data entirely. |
Nupur Kumari; Sheng-Yu Wang; Nanxuan Zhao; Yotam Nitzan; Yuheng Li; Krishna Kumar Singh; Richard Zhang; Eli Shechtman; Jun-Yan Zhu; Xun Huang; |
| 401 | Towards Personalized Deep Research: Benchmarks and Evaluations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To assess system performance, we propose the PQR Evaluation Framework, which jointly measures (P) Personalization Alignment, (Q) Content Quality, and (R) Factual Reliability. |
Yuan Liang; Jiaxian Li; Yuqing Wang; WANG PIAOHONG; Motong Tian; Pai Liu; Shuofei Qiao; Runnan Fang; He Zhu; Ge Zhang; Minghao Liu; Yuchen Eleanor Jiang; Ningyu Zhang; Wangchunshu Zhou; |
| 402 | LEXam: Benchmarking Legal Reasoning on 340 Law Exams Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Long-form legal reasoning remains a key challenge for large language models (LLMs) in spite of recent advances in test-time scaling. To address this, we introduce ***LEXam***, a novel benchmark derived from 340 law exams spanning 116 law school courses across a range of subjects and degree levels. |
Yu Fan; Jingwei Ni; Jakob Merane; Yang Tian; Yoan Hermstrüwer; Yinya Huang; Mubashara Akhtar; Etienne Salimbeni; Florian Geering; Oliver Dreyer; Daniel Brunner; Markus Leippold; Mrinmaya Sachan; Alexander Stremitzer; Christoph Engel; Elliott Ash; Joel Niklaus; |
| 403 | QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present QuoKA: Query-oriented KV selection for efficient attention, a training-free and hardware agnostic sparse attention algorithm for accelerating transformer inference under chunked prefill. |
Dalton Jones; Junyoung Park; Matthew J Morse; Mingu Lee; Matthew Harper Langston; Christopher Lott; |
| 404 | Toward Efficient Exploration By Large Language Model Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, rather than relying on finetuning or in-context learning to coax LLMs into implicitly imitating a RL algorithm, we illustrate how LLMs can be used to explicitly implement an existing RL algorithm (Posterior Sampling for Reinforcement Learning) whose capacity for statistically-efficient exploration is already well-studied. |
Dilip Arumugam; Thomas L. Griffiths; |
| 405 | SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Current sports benchmarks either cover single sports or lack the detailed reasoning chains and precise visual grounding needed to robustly evaluate these core capabilities in a multi-sport context. To address this gap, we introduce SportR, the first multi-sports large-scale benchmark designed to train and evaluate MLLMs on the fundamental reasoning required for sports intelligence. |
Haotian Xia; Haonan Ge; Junbo Zou; Hyun Woo Choi; Xuebin Zhang; Danny Suradja; Botao Rui; Ethan Tran; Wendy Jin; Zhen Ye; Xiyang Lin; Christopher Lai; Shengjie Zhang; Junwen Miao; Shichao Chen; Rhys Tracy; Vicente Ordonez; Weining Shen; Hanjie Chen; |
| 406 | Dyna-Mind: Learning to Simulate from Experience for Better AI Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by literature on human cognition, we argue that current AI agents need “vicarious trial and error” – the capacity to mentally simulate alternative futures before acting – in order to enhance their understanding and performance in complex interactive environments. We introduce Dyna-Mind, a two-stage training framework that explicitly teaches (V)LM agents to integrate such simulation into their reasoning. |
Xiao Yu; Baolin Peng; Michel Galley; Hao Cheng; Qianhui Wu; Janardhan Kulkarni; Suman Nath; Zhou Yu; Jianfeng Gao; |
| 407 | Searching for Privacy Risks in LLM Agents Via Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the evolving nature of such dynamic dialogues makes it challenging to anticipate emerging vulnerabilities and design effective defenses. To tackle this problem, we present a search-based framework that alternates between improving attack and defense strategies through the simulation of privacy-critical agent interactions. |
Yanzhe Zhang; Diyi Yang; |
| 408 | ACADREASON: Exploring The Limits of Reasoning Models with Academic Research Problems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, existing evaluations focus mainly on math/code contests or general tasks, while existing multi-domain academic benchmarks lack sufficient reasoning depth, leaving the field without a rigorous benchmark for high-level reasoning. To fill this gap, we introduce the ACADREASON benchmark, designed to evaluate the ability of LLMs and agents to acquire and reason over academic knowledge. |
Xin Gui; King Zhu; JinCheng Ren; Qianben Chen; Zekun Moore Wang; Yizhi LI; Xinpeng Liu; REN WENLI; Linyu Miao; Tianrui Qin; Ziqi Shu; He Zhu; Dingfeng Shi; Jiaheng Liu; Yuchen Eleanor Jiang; Minghao Liu; Ge Zhang; Wangchunshu Zhou; |
| 409 | Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These implementations can unintentionally cause imbalanced transitions, such as unmasking too rapidly during the early stages of generation, which degrades the quality of the resulting samples. To address this, we draw insight from the analysis and propose a novel classifier-free guidance mechanism. |
Kevin Rojas; Ye He; Chieh-Hsin Lai; Yuhta Takida; Yuki Mitsufuji; Molei Tao; |
| 410 | AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing memory benchmarks rely on static, off-policy data as context, limiting evaluation reliability and scalability. To address these gaps, we introduce AMemGym, an interactive environment enabling on-policy evaluation and optimization for memory-driven personalization. |
Cheng Jiayang; Dongyu Ru; Lin Qiu; Yiyang Li; Xuezhi Cao; Yangqiu Song; Xunliang Cai; |
| 411 | Temporal Sparse Autoencoders: Leveraging The Sequential Nature of Language for Interpretability Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We argue that this limitation stems from neglecting the temporal structure of language, where semantic content typically evolves smoothly over sequences. Building on this insight, we introduce Temporal Sparse Autoencoders (T-SAEs), which incorporate a novel contrastive loss encouraging consistent activations of high-level features over adjacent tokens. |
Usha Bhalla; Alex Oesterling; Claudio Mayrink Verdun; Himabindu Lakkaraju; Flavio Calmon; |
| 412 | Pinet: Optimizing Hard-constrained Neural Networks with Orthogonal Projection Layers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce an output layer for neural networks that ensures satisfaction of convex constraints. |
Panagiotis D. Grontas; Antonio Terpin; Efe C. Balta; Raffaello D’Andrea; John Lygeros; |
| 413 | InnovatorBench: Evaluating Agents’ Ability to Conduct Innovative AI Research Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: AI agents could accelerate scientific discovery by automating hypothesis formation, experiment design, coding, execution, and analysis, yet existing benchmarks probe narrow skills in simplified settings. To address this gap, we introduce InnovatorBench, a benchmark-platform pair for realistic, end-to-end assessment of agents performing Large Language Model (LLM) research. |
Yunze Wu; Dayuan Fu; Weiye Si; Zhen Huang; Mohan Jiang; Keyu Li; Shijie Xia; Jie Sun; Tianze Xu; Yang Xiao; Pengrui Lu; Xiaojie Cai; Lyumanshan Ye; Wenhong Zhu; Xiangkun Hu; Pengfei Liu; |
| 414 | EgoTwin: Dreaming Body and View in First Person Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To bridge this gap, we introduce a novel task of joint egocentric video and human motion generation, characterized by two key challenges: 1) Viewpoint Alignment: the camera trajectory in the generated video must accurately align with the head trajectory derived from human motion; 2) Causal Interplay: the synthesized human motion must causally align with the observed visual dynamics across adjacent video frames. To address these challenges, we propose EgoTwin, a joint video-motion generation framework built on the diffusion transformer architecture. |
Jingqiao Xiu; Fangzhou Hong; Yicong Li; Mengze Li; Wentao Wang; Sirui Han; Liang Pan; Ziwei Liu; |
| 415 | Training Large Reasoning Models Efficiently Via Progressive Thought Encoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Progressive Thought Encoding, a parameter-efficient fine-tuning method that enables LRMs to reason effectively under fixed-size caches. |
Zeliang Zhang; Xiaodong Liu; Hao Cheng; Hao Sun; Chenliang Xu; Jianfeng Gao; |
| 416 | Go-Browse: Training Web Agents with Structured Exploration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To address this, we propose Go-Browse, a method for automatically collecting diverse and realistic web agent data at scale through structured exploration of web environments. |
Apurva Gandhi; Graham Neubig; |
| 417 | Disentangled Robot Learning Via Separate Forward and Inverse Dynamics Pretraining Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Besides, such a vision-action entangled training manner limits model learning from large-scale, action-free web video data. To address these issues, we propose DeFI, a novel framework that Decouples visual Forward and Inverse dynamics pretraining to exploit respective data sources, wherein video generation and action prediction are disentangled. |
Wenyao Zhang; Bozhou Zhang; Zekun Qi; Wenjun Zeng; Xin Jin; Li Zhang; |
| 418 | FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: While the lack of exact latent inversion is a core advantage of these methods, it often results in unstable editing trajectories and poor source consistency. To address this limitation, we propose {\em FlowAlign}, a novel inversion-free flow-based framework for consistent image editing with principled trajectory control. |
Jeongsol Kim; Yeobin Hong; Jonghyun Park; Jong Chul Ye; |
| 419 | FastVGGT: Fast Visual Geometry Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Our analysis reveals a “token collapse” phenomenon, where many tokens attend to nearly identical regions, resulting in redundant computation and inefficiency. Motivated by this finding, we propose FastVGGT, a training-free framework that strategically prunes these redundant tokens. |
You Shen; Zhipeng Zhang; Yansong Qu; Xiawu Zheng; Jiayi Ji; Shengchuan Zhang; Liujuan Cao; |
| 420 | AutoBio: A Simulation and Benchmark for Robotic Automation in Digital Biology Laboratory Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce AutoBio, a simulation framework and benchmark designed to evaluate robotic automation in biology laboratory environments—an application domain that combines structured protocols with demanding precision and multimodal interaction. |
Zhiqian Lan; Yuxuan Jiang; Ruiqi Wang; Xuanbing Xie; Rongkui Zhang; Yicheng Zhu; LI PEIHANG; Tianshuo Yang; Tianxing Chen; Haoyu Gao; Xiaokang Yang; Xuelong Li; Hongyuan Zhang; Yao Mu; Ping Luo; |
| 421 | On The Reasoning Abilities of Masked Diffusion Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we characterize what types of reasoning problems MDMs can provably solve and how efficiently. |
Anej Svete; Ashish Sabharwal; |
| 422 | RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing works largely adopt one-shot settings, ignoring the iterative and feedback-driven nature of realistic workflows of scientific research development. To address this gap, we present RECODE, a benchmark of 102 tasks from research papers and repositories that evaluates LLMs through multi-turn interactions with human feedback. |
Chunyu Miao; Henry Peng Zou; Yangning Li; Yankai Chen; Yibo Wang; Fangxin Wang; Yifan Li; Wooseong Yang; Bowei He; Xinni Zhang; Dianzhi Yu; Hanchen Yang; Hoang H Nguyen; Yue Zhou; Jie Yang; Jizhou Guo; Wenzhe Fan; Chin-Yuan Yeh; Panpan Meng; Liancheng Fang; Jinhu Qi; Wei-Chieh Huang; Zhengyao Gu; Yuwei Han; Langzhou He; Yuyao Yang; Xue Liu; Irwin King; Philip S. Yu; |
| 423 | AutoLibra: Agent Metric Induction from Open-Ended Human Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Agents are predominantly evaluated and optimized via task success metrics, which are coarse, rely on manual design from experts, and fail to reward intermediate emergent behaviors. We propose AutoLibra, a framework for agent evaluation, that transforms open-ended human feedback e.g. “If you find that the button is disabled, don’t click it again”, or “This agent has too much autonomy to decide what to do on its own” into metrics for evaluating fine-grained behaviors in agent trajectories. |
Hao Zhu; Phil Cuvin; Xinkai Yu; Charlotte Ka Yee Yan; Jason Zhang; Diyi Yang; |
| 424 | EXP-Bench: Can AI Conduct AI Research Experiments? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce EXP-Bench, a novel benchmark designed to systematically evaluate AI agents on complete research experiments sourced from influential AI publications. |
Patrick Tser Jern Kon; Qiuyi Ding; Jiachen Liu; Xinyi Zhu; Jingjia Peng; Jiarong Xing; Yibo Huang; Yiming Qiu; Jayanth Srinivasa; Myungjin Lee; Mosharaf Chowdhury; Matei Zaharia; Ang Chen; |
| 425 | Reliable Weak-to-Strong Monitoring of LLM Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a monitor red teaming (MRT) workflow that varies agent and monitor awareness, adversarial evasion strategies, and evaluation across tool-calling (SHADE-Arena) and computer-use (CUA-SHADE-Arena) environments.We release code, data, and logs to support further research. |
Neil Kale; Chen Bo Calvin Zhang; Kevin Zhu; Ankit Aich; Paula Rodriguez; Christina Q Knight; Zifan Wang; |
| 426 | AlphaSAGE: Structure-Aware Alpha Mining Via GFlowNets for Robust Exploration Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Third, the standard RL objective of maximizing expected returns inherently drives policies towards a single optimal mode, directly contradicting the practical need for a diverse portfolio of non-correlated alphas. To overcome these challenges, we introduce **AlphaSAGE** (**S**tructure-**A**ware Alpha Mining via **G**enerative Flow Networks for Robust **E**xploration), a novel framework is built upon three cornerstone innovations: (1) a structure-aware encoder based on Relational Graph Convolutional Network (RGCN); (2) a new framework with Generative Flow Networks (GFlowNets); and (3) a dense, multi-faceted reward structure. |
Binqi Chen; Hongjun Ding; Ning Shen; Taian Guo; Jinsheng Huang; Luchen Liu; Ming Zhang; |
| 427 | NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive exploration of complex model systems. To address these critical gaps, we introduce **NewtonBench**, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains. |
Tianshi Zheng; Kelvin Kiu Wai Tam; Newt Nguyen Kim Hue Nam; Baixuan Xu; Zhaowei Wang; Cheng Jiayang; Hong Ting Tsang; Weiqi Wang; Jiaxin Bai; Tianqing Fang; Yangqiu Song; Ginny Wong; Simon See; |
| 428 | Unveiling Super Experts in Mixture-of-Experts Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this study, we report, for the first time, the discovery and systematic investigation of a distinct subset of experts that play a pivotal role in the model’s forward inference. |
Zunhai Su; Qingyuan Li; HaoZhang; Weihao Ye; Qibo Xue; Yulei Qian; Ngai Wong; Kehong Yuan; |
| 429 | Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This simplification discards the imaginary component, which contains valuable phase information, leading to a potential loss of relational details crucial for modeling long-context dependencies. In this paper, we propose an extension that re-incorporates this discarded imaginary component. |
Xiaoran Liu; Yuerong Song; Zhigeng Liu; Zengfeng Huang; Qipeng Guo; Zhaoxiang Liu; Shiguo Lian; Ziwei He; Xipeng Qiu; |
| 430 | Dynamic Classifier-Free Diffusion Guidance Via Online Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This “one-size-fits-all” approach fails to adapt to the diverse requirements of different prompts; moreover, prior solutions like gradient-based correction or fixed heuristic schedules introduce additional complexities and fail to generalize. In this work, we challenge this static paradigm by introducing a framework for dynamic CFG scheduling. |
Pinelopi Papalampidi; Olivia Wiles; Ira Ktena; Aleksandar Shtedritski; Emanuele Bugliarello; Ivana Kajic; Isabela Albuquerque; Aida Nematzadeh; |
| 431 | Should We Still Pretrain Encoders with Masked Language Modeling? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, it remains unclear whether these gains reflect an inherent advantage of the CLM approach or arise from confounding factors such as model and data scale. In this paper, we address this question through a series of large-scale, carefully controlled pretraining ablations, training a total of 38 models ranging from 210 million to 1 billion parameters, and conducting over 15,000 fine-tuning and evaluation runs. |
Hippolyte Gisserot-Boukhlef; Nicolas Boizard; Manuel Faysse; Duarte Miguel Alves; Emmanuel Malherbe; Andre Martins; CELINE HUDELOT; Pierre Colombo; |
| 432 | Zebra-CoT: A Dataset for Interleaved Vision-Language Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce **Zebra-CoT** a diverse large-scale interleaved text-image reasoning dataset with 182,384 reasoning traces across 18 domains with over 50 distinct tasks. |
Ang Li; Charles L. Wang; Deqing Fu; Kaiyu Yue; Zikui Cai; Wang Bill Zhu; Ollie Liu; Peng Guo; Willie Neiswanger; Furong Huang; Tom Goldstein; Micah Goldblum; |
| 433 | ReLi3D: Relightable Multi-view 3D Reconstruction with Disentangled Illumination Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present MIDR-3D, the first unified end-to-end pipeline that simultaneously reconstructs complete 3D geometry, spatially-varying physically-based materials, and environment illumination from sparse multi-view images in under one second. |
Jan-Niklas Dihlmann; Mark Boss; Simon Donné; Andreas Engelhardt; Hendrik Lensch; Varun Jampani; |
| 434 | ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Real-world travel planning exemplifies these challenges, evaluating agents’ abilities to handle constraints that are explicit, implicit, and even evolving based on interactions with dynamic environments and user needs. In this paper, we present ATLAS, a general multi-agent framework designed to effectively handle such complex nature of constraints awareness in real-world travel planning tasks. |
Jihye Choi; Jinsung Yoon; Jiefeng Chen; Somesh Jha; Tomas Pfister; |
| 435 | Energy-Based Transformers Are Scalable Learners and Thinkers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, most existing approaches suffer from several limitations: they are modality-specific (e.g., working only in text), problem-specific (e.g., verifiable domains like math and coding), or require additional supervision/training on top of unsupervised pretraining (e.g., verifiers or verifiable rewards). In this paper, we ask the question “Is it possible to generalize these System 2 Thinking approaches, and develop models that learn to think solely from unsupervised learning?” |
Alexi Gladstone; Ganesh Nanduru; Md Mofijul Islam; Peixuan Han; Hyeonjeong Ha; Aman Chadha; Yilun Du; Heng Ji; Jundong Li; Tariq Iqbal; |
| 436 | LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we propose a first step in that direction where we develop LLM-JEPA, a JEPA based solution for LLMs applicable both to finetuning and pretraining. |
Hai Huang; Yann LeCun; Randall Balestriero; |
| 437 | Parallel Sampling from Masked Diffusion Models Via Conditional Independence Testing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: These goals conflict because high-confidence predictions often cluster and depend on each other, opportunities for parallel updates. We present PUNT, a model-agnostic sampler that reconciles this trade-off. |
Iskander Azangulov; Teodora Pandeva; Niranjani Prasad; Javier Zazo; Sushrut Karmalkar; |
| 438 | Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We extend our analysis to video VLMs and identify an analogous linear temporal ID mechanism. |
Raphi Kang; Hongqiao Chen; Georgia Gkioxari; Pietro Perona; |
| 439 | A2ASecBench: A Protocol-Aware Security Benchmark for Agent-to-Agent Multi-Agent Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present the first comprehensive security evaluation of A2A-MAS. |
Tianhao Li; Chuangxin Chu; Yujia Zheng; Bohan Zhang; Neil Zhenqiang Gong; Chaowei Xiao; |
| 440 | Meta-RL Induces Exploration in Language Agents Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we present LaMer, a general Meta-RL framework that enables LLM agents to actively explore and learn from the environment feedback at test time. |
Yulun Jiang; Liangze Jiang; Damien Teney; Michael Moor; Maria Brbic; |
| 441 | VideoAnchor: Reinforcing Subspace-Structured Visual Cues for Coherent Visual-Spatial Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To address this challenge, we draw a novel connection between the self-expressiveness property in sparse subspace clustering and the attention mechanism in Transformers. Building on this insight, we propose VideoAnchor, a plug-and-play module that leverages subspace affinities to reinforce visual cues across frames without retraining, effectively anchoring attention to shared visual structures. |
Zhaozhi Wang; Tong Zhang; Mingyue Guo; Yaowei Wang; Qixiang Ye; |
| 442 | Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce the concept of **Knowledge Purification**, which consolidates the rationales from multiple teacher LLMs into a single rationale, thereby mitigating conflicts and enhancing efficiency. |
Ruihan Jin; Pengpeng Shao; Zhengqi Wen; Jinyang Wu; Mingkuan Feng; Shuoyang; Chu Yuan Zhang; Jianhua Tao; |
| 443 | EditBench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce EditBench, a benchmark for evaluating LLM code editing capabilities grounded in real-world usage, i.e.,~user instructions and code contexts collected in the wild. |
Wayne Chi; Valerie Chen; Ryan Shar; Aditya Mittal; Jenny Liang; Wei-Lin Chiang; Anastasios Nikolas Angelopoulos; Ion Stoica; Graham Neubig; Ameet Talwalkar; Chris Donahue; |
| 444 | Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Over a wide range of Pythia model sizes and multiple randomization schemes, we find that, in many settings, SAEs trained on randomly initialized transformers produce auto-interpretability scores and reconstruction metrics that are similar to those from trained models. |
Thomas Heap; Tim Lawson; Lucy Farnik; Laurence Aitchison; |
| 445 | RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Data Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we hope to provide insights from real-world data, advancing scientific ML toward bridging the sim-to-real gap and real-world deployment. |
Peiyan Hu; Haodong Feng; Hongyuan Liu; Tongtong Yan; Wenhao Deng; Tianrun Gao; Rong Zheng; Haoren Zheng; Chenglei Yu; Chuanrui Wang; Kaiwen Li; Zhi-Ming Ma; Dezhi Zhou; Xingcai Lu; Dixia Fan; Tailin Wu; |
| 446 | Sequential Parallel Duality in Prefix Scannable Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This generalization unifies many existing architectures, including element-wise RNNs (e.g., Mamba) and linear transformers (e.g., GLA, Mamba2, mLSTM), while also introducing new models with softmax-like operators that achieve O(1) amortized compute per token and log(N) memory for sequence length N. We empirically evaluate such models on illustrative small-scale language modeling and canonical synthetic tasks, including state tracking and associative recall. |
Morris Yau; Sharut Gupta; Valerie Engelmayer; Kazuki Irie; Stefanie Jegelka; Jacob Andreas; |
| 447 | GLSTM: Mitigating Over-Squashing By Increasing Storage Capacity Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we re-examine the over-squashing phenomenon through the lens of model storage and retrieval capacity, which we define as the amount of information that can be stored in a node’s representation for later use. |
Hugh Blayney; Alvaro Arroyo; Xiaowen Dong; Michael M. Bronstein; |
| 448 | RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: Current evaluations of this threat either lack support for adversarial testing in realistic but controlled environments or ignore hybrid web-OS attack scenarios involving both interfaces. To address this, we propose RedTeamCUA, an adversarial testing framework featuring a novel hybrid sandbox that integrates a VM-based OS environment with Docker-based web platforms. |
Zeyi Liao; Jaylen Jones; Linxi Jiang; Yuting Ning; Eric Fosler-Lussier; Yu Su; Zhiqiang Lin; Huan Sun; |
| 449 | OmniCT: Towards A Unified Slice-Volume LVLM for Comprehensive CT Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present \textbf{OmniCT}, a powerful unified slice–volume LVLM for CT scans, which makes three contributions: \textbf{(i) Spatial Consistency Enhancement (SCE):} volumetric slice composition combined with tri-axial positional encoding introduces volumetric consistency, and an MoE hybird projection enables efficient slice–volume adaptation; \textbf{(ii) Organ-level Semantic Enhancement (OSE):} segmentation and ROI localization explicitly align anatomical regions, emphasizing lesion- and organ-level semantics; \textbf{(iii) MedEval-CT:} the largest slice–volume CT dataset and hybrid benchmark integrates multi-level metrics for unified evaluation. |
Tianwei Lin; Zhongwei Qiu; Wenqiao Zhang; Jiang Liu; Yihan Xie; Mingjian Gao; Zhenxuan Fan; Zhaocheng Li; Sijing Li; Zhongle Xie; Peng LU; Yueting Zhuang; Ling Zhang; Beng Chin Ooi; Yingda Xia; |
| 450 | MotionGPT3: Human Motion As A Second Modality Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Motivated by recent multi-branch Transformer designs that separate signals from different modalities, we propose MotionGPT3, a bimodal motion–language model for both understanding and generation. |
Bingfan Zhu; Biao Jiang; Sunyi Wang; SHIXIANG TANG; Tao Chen; Linjie Luo; Youyi Zheng; Xin Chen; |
| 451 | INTIMA: A Benchmark for Human-AI Companionship Behavior Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Interactions and Machine Attachment Benchmark (INTIMA), a benchmark for evaluating companionship behaviors in language models. |
Lucie-Aimée Kaffee; Giada Pistilli; Yacine Jernite; |
| 452 | REMem: Reasoning with Episodic Memory in Language Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present REMem, a two-phase framework for constructing and reasoning with episodic memory: 1) Offline indexing, where REMem converts experiences into a hybrid memory graph that flexibly links time-aware gists and facts. |
Yiheng Shu; Saisri Padmaja Jonnalagedda; Xiang Gao; Bernal Jiménez Gutiérrez; Weijian Qi; Kamalika Das; Huan Sun; Yu Su; |
| 453 | Real-Time Motion-Controllable Autoregressive Video Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing AR video diffusion models are limited to simple control signals or text-to-video generation, and often suffer from quality degradation and motion artifacts in few-step generation. To address these challenges, we propose AR-Drag, the first RL-enhanced few-step AR video diffusion model for real-time image-to-video generation with diverse motion control. |
Kesen Zhao; Jiaxin Shi; Beier Zhu; Junbao Zhou; Xiaolong Shen; Yuan Zhou; Qianru Sun; Hanwang Zhang; |
| 454 | Weight Decay May Matter More Than ΜP for Learning Rate Transfer in Practice Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, the scaling rules of µP rely on strong assumptions, particularly about the geometric alignment of a layer’s inputs with both its weights and gradient updates. In this large-scale empirical investigation, we show that these assumptions hold only briefly at the start of training in the practical setups where learning rate transfer is most valuable, such as LLM training. |
Atli Kosson; Jeremy Welborn; Yang Liu; Martin Jaggi; Xi Chen; |
| 455 | GLASS Flows: Efficient Inference for Reward Alignment of Flow and Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To remove this bottleneck, we introduce GLASS Flows, a new sampling paradigm that simulates a ”flow matching model within a flow matching model” to sample Markov transitions. As we show in this work, this ”inner” flow matching model can be retrieved from any pre-trained model without any re-training, effectively combining the efficiency of ODEs with the stochastic evolution of SDEs. |
Peter Holderrieth; Uriel Singer; Tommi Jaakkola; Ricky T. Q. Chen; Yaron Lipman; Brian Karrer; |
| 456 | WAVE: Learning Unified & Versatile Audio-Visual Embeddings with Multimodal LLM Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce WAVE (\textbf{u}nified \& \textbf{v}ersatile \textbf{a}udio-\textbf{v}isual \textbf{e}mbeddings), the first LLM-based embedding that creates a unified representation space for text, audio, and video modalities. |
Changli Tang; Qinfan Xiao; Ke Mei; Tianyi Wang; Fengyun Rao; Chao Zhang; |
| 457 | FantasyWorld: Geometry-Consistent World Modeling Via Unified Video and 3D Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we present FantasyWorld, a geometry-enhanced framework that augments frozen video foundation models with a trainable geometric branch, enabling joint modeling of video latents and an implicit 3D field in a single forward pass. |
Yixiang Dai; Fan Jiang; Chiyu Wang; Mu Xu; Yonggang Qi; |
| 458 | Scaling Agent Learning Via Experience Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While reinforcement learning (RL) can empower large language model (LLM) agents by enabling self-improvement through interaction, its practical adoption remains challenging due to costly rollouts, limited task diversity, unreliable reward signals, and infrastructure complexity, all of which obstruct the collection of scalable experience data. To address these challenges, we introduce DreamGym, the first unified framework designed to synthesize diverse experiences with scalability in mind to enable effective online RL training for autonomous agents. |
Zhaorun Chen; Zhuokai Zhao; Kai Zhang; Bo Liu; Qi Qi; Yifan Wu; Tarun Kalluri; Xuefei Cao; Yuanhao Xiong; Haibo Tong; Huaxiu Yao; Hengduo Li; Jiacheng Zhu; Xian Li; Dawn Song; Bo Li; Jason E Weston; Dat Huynh; |
| 459 | Visual Compositional Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we explore the impact of task complexity on informative data curation and introduce COMPACT (COMPositional Atomic-to-complex Visual Capability Tuning), a VIT data recipe that scales training sample complexity by combining multiple atomic visual capabilities in a single training example. |
Xindi Wu; Hee Seung Hwang; Polina Kirichenko; Esin Tureci; Olga Russakovsky; |
| 460 | Scaling Large Vision-Language Model RL Training Via Efficient Load Balancing Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Existing systems either focus on text-only RL or employ general load-balancing techniques that are incompatible with the small-batch, iterative nature of RL training. To address these challenges, we present FlexRL, a holistic system designed to optimize the end-to-end VLM RL pipeline. |
Zerui Wang; Qinghao Hu; Chang Chen; Jiecheng Zhou; Haojie Duanmu; Xingcheng Zhang; Peng Sun; Dahua Lin; |
| 461 | Monitoring Decomposition Attacks with Lightweight Sequential Monitors Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To defend in real‐time, we propose a lightweight sequential monitoring framework that cumulatively evaluates each sub‑prompt. |
Chen Yueh-Han; Nitish Joshi; Yulin Chen; Maksym Andriushchenko; Rico Angell; He He; |
| 462 | HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We hypothesize that temporal resolution is a fundamental axis of representation learning, with different clinical and behavioral outcomes relying on features at distinct scales. To test this resolution hypothesis, we introduce HiMAE (Hierarchical Masked Autoencoder), a self-supervised framework that combines masked autoencoding with a hierarchical convolutional encoder–decoder. |
Simon A. Lee; Cyrus Tanade; Hao Zhou; Juhyeon Lee; Megha Thukral; Md Sazzad Hissain Khan; Keum San Chun; Baiying Lu; Migyeong Gwak; Mehrab Bin Morshed; Viswam Nathan; Md Mahbubur Rahman; Li Zhu; Subramaniam Venkatraman; Sharanya Arcot Desai; |
| 463 | HeurekaBench: A Benchmarking Framework for AI Co-scientist Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, evaluating these systems is challenging, as it requires realistic, end-to-end research scenarios that integrate data analysis, interpretation, and the generation of new insights from the experimental data. To address this limitation, we introduce HeurekaBench, a framework to create benchmarks with exploratory, open-ended research questions for experimental datasets. |
Siba Smarak Panigrahi; Jovana Videnović; Maria Brbic; |
| 464 | STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: While naively generating a complete chain-of-thought (CoT) reasoning before starting to talk can enable thinking for SLMs, this induces additional latency for the speech response, as the CoT reasoning can be arbitrarily long. To solve this issue, we propose STITCH, a novel generation method that alternates between the generation of unspoken reasoning chunks and spoken response chunks. |
Cheng-Han Chiang; Xiaofei Wang; Linjie Li; Chung-Ching Lin; Kevin Lin; Shujie LIU; Zhendong Wang; Zhengyuan Yang; Hung-yi Lee; Lijuan Wang; |
| 465 | CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Moreover, they tend to produce poorly calibrated policies that remain confident in their generations regardless of correctness. To address this challenge, we introduce **Curiosity-Driven Exploration (CDE)**, a framework that leverages the model’s intrinsic sense of curiosity to guide exploration. |
Runpeng Dai; Linfeng Song; Haolin Liu; Zhenwen Liang; Dian Yu; Haitao Mi; Zhaopeng Tu; Rui Liu; Tong Zheng; Hongtu Zhu; Dong Yu; |
| 466 | SEMA: Simple Yet Effective Learning for Multi-Turn Jailbreak Attacks Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose SEMA, a simple yet effective framework that trains a multi-turn attacker without relying on any existing strategies or external data. |
Mingqian Feng; Xiaodong Liu; Weiwei Yang; Jialin Song; Xuekai Zhu; Chenliang Xu; Jianfeng Gao; |
| 467 | Achieving Olympia-Level Geometry Large Language Model Agent Via Complexity Boosting Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we make the first attempt to build a medalist-level LLM agent for geometry and present InternGeometry.We will release the model, data, and symbolic engine to support future research. |
Haiteng Zhao; Junhao Shen; Yiming Zhang; Songyang Gao; Kuikun Liu; Tianyou Ma; Fan Zheng; Dahua Lin; Wenwei Zhang; Kai Chen; |
| 468 | AutoMetrics: Approximate Human Judgments with Automatically Generated Evaluators Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present **AutoMetrics**, a framework for synthesizing evaluation metrics under low-data constraints. |
Michael J Ryan; Yanzhe Zhang; Amol Salunkhe; Yi Chu; Di Xu; Diyi Yang; |
| 469 | The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce Delethink, a thinking algorithm that realizes the Markovian Thinking Paradigm. |
Milad Aghajohari; Kamran Chitsaz; Amirhossein Kazemnejad; Sarath Chandar; Alessandro Sordoni; Aaron Courville; Siva Reddy; |
| 470 | Let’s (not) Just Put Things in Context: Test-time Training for Long-context LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose query-only test-time training (qTTT): a cache-preserving adaptation that performs a single prefill to fix keys/values and then applies a handful of gradient updates to the query projections. |
Rachit Bansal; Aston Zhang; Rishabh Tiwari; Lovish Madaan; Sai Surya Duvvuri; Fnu Devvrit; David Brandfonbrener; David Alvarez-Melis; Prajjwal Bhargava; Mihir Kale; Samy Jelassi; |
| 471 | Scaling Knowledge Graph Construction Through Synthetic Data Generation and Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We identify that this limitation stems not from model capabilities but from the absence of high-quality training data for document-level KG construction. To address this gap, we introduce SynthKG, a multi-step data synthesis pipeline that generates high-quality document-KG pairs through systematic chunking, decontextualization, and structured extraction using LLMs. |
Prafulla Kumar Choubey; Xin Su; Man Luo; XIANGYU PENG; Caiming Xiong; Tiep Le; Shachar Rosenman; Vasudev Lal; Phil L Mui; Ricky Ho; Phillip Howard; Chien-Sheng Wu; |
| 472 | Virtual Community: An Open World for Humans, Robots, and Society Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To explore this future, we present Virtual Community—an open-world platform for humans, robots, and society—built on a universal physics engine and grounded in real-world 3D scenes.Leveraging Virtual Community, we propose two novel challenges. |
Qinhong Zhou; Hongxin Zhang; Xiangye Lin; Zheyuan Zhang; Yutian Chen; Wenjun Liu; Zunzhe Zhang; Sunli Chen; Lixing Fang; Qiushi Lyu; Xinyu Sun; Jincheng Yang; Zeyuan Wang; Bao Chi Dang; Zhehuan Chen; Daksha Ladia; Quang Vinh Dang; Jiageng Liu; Chuang Gan; |
| 473 | Learning Is Forgetting; LLM Training As Lossy Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We show pre-training results in models that are optimally compressed for next-sequence prediction, approaching the Information Bottleneck bound on compression. |
Henry Conklin; Tom Hosking; Tan Yi-Chern; Jonathan D. Cohen; Sarah-Jane Leslie; Thomas L. Griffiths; Max Bartolo; Seraphina Goldfarb-Tarrant; |
| 474 | Capacity-Aware Inference: Mitigating The Straggler Effect in Mixture of Experts Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, under expert parallelism, MoE suffers from inference inefficiencies due to imbalanced token-to-expert assignment, where underloaded experts complete computations early but must wait for overloaded experts, leading to global delays. We define this phenomenon as the \textbf{\textit{Straggler Effect}}, as the most burdened experts dictate the overall inference latency. |
Shwai He; Weilin Cai; Jiayi Huang; Ang Li; |
| 475 | Light-X: Generative 4D Video Rendering with Camera and Illumination Control Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we present Light-X, a video generation framework that enables controllable rendering from monocular videos with both viewpoint and illumination control. |
Tianqi Liu; Zhaoxi Chen; Zihao Huang; Shaocong Xu; Saining Zhang; Chongjie Ye; Bohan Li; Zhiguo Cao; Wei Li; Hao Zhao; Ziwei Liu; |
| 476 | Expanding Reasoning Potential in Foundation Model By Learning Diverse Chains of Thought Patterns Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we define the foundation model’s reasoning potential for the first time as the inverse of the number of independent attempts required to correctly answer the question, which is strongly correlated with the final model performance. |
Xuemiao Zhang; Can Ren; Chengying Tu; Rongxiang Weng; Shuo Wang; Hongfei Yan; Jingang Wang; Xunliang Cai; |
| 477 | DispViT: Direct Stereo Disparity Regression with A Single-Stream Vision Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: This paper introduces \textbf{DispViT}, a new architecture that establishes a \textbf{regression-centric paradigm}. |
Tongfan Guan; Jiaxin Guo; Tianyu Huang; Jinhu Dong; Chen Wang; Yun-Hui Liu; |
| 478 | What Happens Next? Anticipating Future Motion By Generating Point Trajectories Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We consider the problem of forecasting motion from a single image, i.e., predicting how objects in the world are likely to move, without the ability to observe other parameters such as the object velocities or the forces applied to them. |
Gabrijel Boduljak; Laurynas Karazija; Iro Laina; Christian Rupprecht; Andrea Vedaldi; |
| 479 | End-to-End Probabilistic Framework for Learning with Hard Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ProbHardE2E, a probabilistic forecasting framework that incorporates hard operational/physical constraints and provides uncertainty quantification. |
Utkarsh Utkarsh; Danielle C. Maddix; Ruijun Ma; Michael W. Mahoney; Bernie Wang; |
| 480 | We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce WE-MATH 2.0, a unified system that integrates a structured mathematical knowledge hierarchy, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to enhance the mathematical reasoning abilities of MLLMs. |
Runqi Qiao; Qiuna Tan; Peiqing Yang; Yanzi Wang; Xiaowan Wang; Enhui Wan; Guanting Dong; Shiqiang Lang; Sitong Zhou; Yida Xu; Yuchen Zeng; Jie Wang; Chong Sun; Chen Li; Honggang Zhang; |
| 481 | Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose \textbf{Geometric Action Control (GAC)}, a novel action generation paradigm that preserves the geometric benefits of spherical distributions while \textit{simplifying computation}. |
Zhihao Lin; |
| 482 | ARMOR: Aligning Secure and Safe Large Language Models Via Meticulous Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: To this end, we propose ARMOR, which introduces a structured three-step reasoning pipeline: (1) analyze jailbreak strategies from an external, updatable strategy library, (2) extract the core intent, and (3) apply policy-based safety verification. |
Zhengyue Zhao; YingziYingzi Ma; Somesh Jha; Marco Pavone; Patrick McDaniel; Chaowei Xiao; |
| 483 | Revisiting Active Sequential Prediction-Powered Mean Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we revisit the problem of active sequential prediction-powered mean estimation, where at each round one must decide the query probability of the ground-truth label upon observing the covariates of a sample. |
Maria-Eleni Sfyraki; Jun-Kun Wang; |
| 484 | JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Inspired by the implicit scene representation in human navigation, analogous to the left brain’s semantic understanding and the right brain’s spatial cognition, we propose JanusVLN, a novel VLN framework featuring a dual implicit neural memory that models spatial-geometric and visual-semantic memory as separate, compact, and fixed-size neural representations. |
Shuang Zeng; Dekang Qi; Xinyuan Chang; Feng Xiong; Xie Shichao; Xiaolong Wu; Shiyi Liang; Mu Xu; Xing Wei; |
| 485 | Speculative Speculative Decoding Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, speculative decoding itself relies on a *sequential* dependence between speculation and verification. We introduce *speculative speculative decoding* (SSD) to parallelize these operations. |
Tanishq Kumar; Tri Dao; Avner May; |
| 486 | In Agents We Trust, But Who Do Agents Trust? Latent Source Preferences Steer LLM Generations Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We hypothesize that when information is attributed to specific sources (e.g., particular publishers, journals, or platforms), LLMs will exhibit systematic latent source preferences. |
Mohammad Aflah Khan; Mahsa Amani; Soumi Das; Bishwamittra Ghosh; Qinyuan Wu; Krishna P. Gummadi; Manish Gupta; Abhilasha Ravichander; |
| 487 | Efficient Agent Training for Computer Use Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: We introduce PC Agent-E, an efficient agent training framework that significantly reduces reliance on large-scale human demonstrations. |
Yanheng He; Jiahe Jin; Pengfei Liu; |
| 488 | $\pi^3$: Permutation-Equivariant Visual Geometry Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We introduce $\pi^3$, a feed-forward neural network that offers a novel approach to visual geometry reconstruction, breaking the reliance on a conventional fixed reference view. |
Yifan Wang; Jianjun Zhou; Haoyi Zhu; Wenzheng Chang; Yang Zhou; Zizun Li; Junyi Chen; Jiangmiao Pang; Chunhua Shen; Tong He; |
| 489 | TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Save Highlight: However, the effectiveness of recent speech tokens for joint modeling remains under-explored. To address this, we introduce Text-Aligned Speech Tokenization and Embedding (TASTE), a method that directly addresses the modality gap by aligning speech token with the corresponding text transcription during the tokenization stage. |
Liang-Hsuan Tseng; Yi-Chang Chen; Kuan Yi Lee; Da-shan Shiu; Hung-yi Lee; |
| 490 | Branched Schrödinger Bridge Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: However, these methods are inherently limited to unimodal transitions and cannot capture *branched* or *divergent* evolution from a common origin to multiple distinct outcomes. To address this, we introduce **Branched Schrödinger Bridge Matching (BranchSBM)**, a novel framework that learns branched Schrödinger bridges. |
Sophia Tang; Yinuo Zhang; Alexander Tong; Pranam Chatterjee; |
| 491 | Neologism Learning for Controllability and Self-Verbalization Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We explore and validate a similar idea in our communication with LLMs: introducing new words to better understand and control the models, expanding on the recently introduced neologism learning. |
John Hewitt; Oyvind Tafjord; Robert Geirhos; Been Kim; |
| 492 | IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we propose Instance-Grounded Geometry Transformer (IGGT), an end-to-end large unified transformer to unify the knowledge for both spatial reconstruction and instance-level contextual understanding. |
Hao Li; Zhengyu Zou; Fangfu Liu; Xuanyang Zhang; Fangzhou Hong; Yukang Cao; Yushi LAN; Manyuan Zhang; Gang YU; Dingwen Zhang; Ziwei Liu; |
| 493 | SoSBench: Benchmarking Safety Alignment on Six Scientific Domains Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Consequently, they fail to adequately assess model safety when handling knowledge-intensive, hazardous scenarios. To address this critical gap, we introduce SOSBench, a regulation-grounded, hazard-focused benchmark encompassing six high-risk scientific domains: chemistry, biology, medicine, pharmacology, physics, and psychology. |
Fengqing Jiang; Fengbo Ma; Zhangchen Xu; Yuetai Li; Zixin Rao; Bhaskar Ramasubramanian; Luyao Niu; Bo Li; Xianyan Chen; Zhen Xiang; Radha Poovendran; |
| 494 | Dancing in Chains: Strategic Persuasion in Academic Rebuttal Via Theory of Mind Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this paper, we introduce RebuttalAgent, the first framework to ground academic rebuttal in Theory of Mind (ToM). |
Zhitao He; Zongwei LYU; Yi R. Fung; |
| 495 | NRGPT: An Energy-based Alternative for GPT Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We propose a minimal modification of the GPT setting to unify it with the EBM framework. |
Nima Dehmamy; Benjamin Hoover; Bishwajit Saha; Leo Kozachkov; Jean-Jacques Slotine; Dmitry Krotov; |
| 496 | Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: In this work, we take an initial step toward bridging embodied reasoning with VLA policy learning by introducing **Vlaser** – a **V**ision-**L**anguage-**A**ction Model with **s**ynergistic **e**mbodied **r**easoning capability, which is a foundational vision-language model designed to integrate high-level reasoning with low-level control for embodied agents. |
Ganlin Yang; Tianyi Zhang; Haoran Hao; Weiyun Wang; Yibin Liu; Dehui Wang; Guanzhou Chen; Zijian Cai; Junting Chen; Weijie Su; Wengang Zhou; Yu Qiao; Jifeng Dai; Jiangmiao Pang; Gen Luo; Wenhai Wang; Yao Mu; Zhi Hou; |
| 497 | EmoPrefer: Can Large Language Models Understand Human Emotion Preferences? Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: * To answer this, we propose **EmoPrefer**, a pioneering work exploring the potential of LLMs in decoding human emotion preferences.Specifically, we construct the first emotion preference dataset, **EmoPrefer-Data**, featuring high-quality preference annotations from experts. |
Zheng Lian; Licai Sun; Lan Chen; Haoyu Chen; Zebang Cheng; Fan Zhang; Ziyu Jia; Ziyang Ma; Fei Ma; Xiaojiang Peng; Jianhua Tao; |
| 498 | Latent Adaptation of Foundation Policies for Sim-to-Real Transfer Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: The conventional sim-to-real methods heavily rely on resource-intensive re-training of the policy network to adapt to new domains, which limits the flexibility of the deployment of RL policies in ever-changing environments. Inspired by human locomotion, where individuals adjust their gait to new surface conditions without relearning the skill of walking, we introduce Latent Adaptation of Foundation Policies (Found-adapt), a framework that decouples this problem into skill acquisition and environment adaptation. |
Longchao Da; T Pranav Kutralingam; Lirong Xiang; Hua Wei; |
| 499 | End-to-end Listen, Look, Speak and Act Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: We present ELLSA (End-to-end Listen, Look, Speak and Act), which, to our knowledge, is the first full-duplex, end-to-end model that simultaneously perceives and generates across vision, text, speech, and action within a single architecture, enabling interaction patterns previously out of reach, yielding more natural, human-like behaviors. |
Siyin Wang; Wenyi Yu; Xianzhao Chen; Xiaohai Tian; Jun Zhang; Lu Lu; Yuxuan Wang; Chao Zhang; |
| 500 | PEERING INTO THE UNKNOWN: ACTIVE VIEW SELECTION WITH NEURAL UNCERTAINTY MAPS FOR 3D RECONSTRUCTION Related Papers Related Patents Related Grants Related Venues Related Experts View Save Highlight: Instead of learning radiance fields, like NeRF or 3D Gaussian Splatting, from a current observation and computing uncertainty for each candidate viewpoint, we introduce a novel AVS approach guided by neural uncertainty maps predicted by a lightweight feedforward deep neural network, named UPNet.We will release all code, models, and datasets. |
Zhengquan Zhang; Feng Xu; Mengmi Zhang; |
This table only includes 500 papers selected by our daily digest algorithm. To continue with the full list (~5,300 papers), please visit Paper Digest: ICLR-2026 (Full List).