Human perception interprets video dynamics by constructing structured mental representations of entities, actions, and temporal boundaries before engaging in high-level reasoning. In contrast, current Video-LLMs typically rely on unstructured Chain-of-Thought (CoT), where crucial visual cues are obscured by verbose narration. While recent efforts ground reasoning in intermediate visual evidence, they rely on task-specific schemas that fail to generalize across diverse video understanding tasks. To address this, we introduce Structured Event Evidence, a unified, temporally ordered schema designed for general video reasoning. However, post-training a model to extract structured evidence while reasoning introduces a severe multi-objective optimization bottleneck, as candidate rollouts must simultaneously satisfy schema compliance, task accuracy, and reasoning budget. Standard reinforcement learning (RL) algorithms attempt to balance these objectives via static scalarization, enforcing a rigid accuracy-length trade-off across training and obscuring fine-grained reward signals. We resolve this by proposing Group-Relative Advantage Balancing (GRAB), which dynamically computes Pareto-optimal objective weights within each rollout group via a minimum-norm criterion over centered rewards. Operating strictly in reward space, GRAB incurs virtually zero computational overhead (<0.002% relative runtime to GRPO) and eliminates brittle weight tuning. Supported by our new PARSE-60K dataset (60K annotations across 35K videos) and a three-stage progressive curriculum, we train PARSE-4B. Across temporal grounding and video question-answering benchmarks, GRAB generates 13% to 39% fewer tokens while maintaining competitive accuracy with exhaustively hand-tuned static weights -- without requiring hyperparameter weight sweeps.
Diverging Preferences: When do Annotators Disagree and do Models Know?
New York University（纽约大学）；Allen Institute for Artificial Intelligence（人工智能研究院）；NVIDIA（NVIDIA公司）；University of Washington（华盛顿大学）；University of Southern California（南加州大学）
Optimal Transport-Based Token Weighting scheme for Enhanced Preference Optimization
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院）；LLM Team, Shopee Pte. Ltd.（Shopee Pte. Ltd. 语言模型团队）；Beijing Key Laboratory of Research on Large Models and Intelligent Governance and Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE（北京大型模型与智能治理研究重点实验室）
Evaluating Reward Model Generalization via Pairwise Maximum Discrepancy Competitions
ZJU-UIUC Institute, Zhejiang University（浙江大学ZJU-UIUC研究院）；School of Artificial Intelligence, Nanjing University of Information Science and Technology（南京信息工程大学人工智能学院）；ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University（浙江大学Hangzhou全球科技创新中心）；City University of Hong Kong（香港城市大学）
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
University of Science and Technology of China（中国科学技术大学）；Meituan LongCat Interaction Team（美团 LongCat 交互团队）；Nanjing University（南京大学）；Fudan University（复旦大学）；Huazhong University of Science and Technology（华中科技大学）
