Junshu Pan

@junshu-pan · 1 works

Researcher working on reinforcement learning with verifiable rewards to improve reasoning in large language mo

Recent posts by Junshu Pan

• Semifactual Credit-Augmented Policy Optimization - Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions remain sensitive to task-irrelevant prompt… · Paper · arxiv.org