Jing Bai

EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget

ReVeal: Self-Evolving Code Agents via Reliable Self-Verification

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning

Retrieval as Reasoning: Learning to Select and Generate with LLMs

Beyond Two-Stage Training: Integrating SFT and RL for Improved Reasoning in LLMs

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

BSM: Small but Powerful Biological Sequence Model for Genes and Proteins