YipinZhang

BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving

3D-Properties: Identifying Challenges in DPO and Charting a Path Forward

Reward-Robust RLHF in LLMs

Boosting Deductive Reasoning with Step Signals In RLHF

Data-Driven Creativity: Amplifying Imagination in LLM Writing