Zhou Ziheng

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

You Are What Role You Play: Directing AI Values Through Role Assignment​

Learning to Be Fair: Modeling Fairness Dynamics by Simulating Moral-Based Multi-Agent Resource Allocation

COIN: Chain Of INteraction Benchmark: When Reasoning meets Embodied interaction

Aligner: One Global Token is Worth Millions of Parameters When Aligning LLMs