5 papers
EGSD: Event-Grounded Self-Distillation for Streaming Video Understanding
Yuwei Miao, Xuesheng Zhang, Wenhao Zou +5
Real-time video understanding requires incrementally maintaining a memory of streaming content, and optimizing this requires dense process signals. On-Policy Self-Distillation (OPS…
G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation
Shiao Xie, Siyu Chen, Jianwei Lv +3
Personalized interpretation of medical reports has emerged as an increasingly important need among patients. Addressing this need requires both evidence-grounded medical factuality…
PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus
Gen Li, Yuanze Hu, Zhichao Yang +10
Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information. Existing LLM-based medical agents show strong medical reasoning abili…
EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA
Yunsheng Zeng, Gen Li, Yuwei Miao +8
Large Reasoning Models are typically trained via reinforcement learning from verifiable rewards (RLVR). However, existing approaches adopt fixed weights for positive and negative s…
C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning
Yuwei Miao, Gen Li, Yunsheng Zeng +8
Retrieval-augmented generation (RAG) trained with reinforcement learning (RL) is a promising way to ground large language models in medical evidence for clinical diagnosis. However…