Chengxing Jia

ADM-v2: Pursuing Full-Horizon Roll-out in Dynamics Models for Offline Policy Learning and Evaluation

Off-Policy Token Clipped Supervised Fine-Tuning Yields a Robust Cold-Start

Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning

Controlling Large Language Model with Latent Action