Yisheng Lv

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning

MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving

RIME: Robust Preference-based Reinforcement Learning with Noisy Human Preferences