Yifan Zhong

In-Context Editing: Learning Knowledge from Self-Induced Distributions

Falcon: Fast Visuomotor Policies via Partial Denoising

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents

Panacea: Pareto Alignment via Preference Adaptation for LLMs