Zhihe Yang

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

SortedRL: Accelerating RL Training for LLMs through Online Length-aware Scheduling

Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

Policy Consistency in Multi-Agent Reinforcement Learning with Mixed Reward

Q-Supervised Contrastive Representation: A State Decoupling Framework for Safe Offline Reinforcement Learning