Yihao Sun

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

Hierarchical Value-Decomposed Offline Reinforcement Learning for Whole-Body Control

The Three Regimes of Offline-to-Online Reinforcement Learning

On the Representation Degradation in Vision-Language-Action Models

Planning with Unified Multimodal Models

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

Improving Reward Model Generalization from Adversarial Process Enhanced Preferences

Whale-X: Learning Scalable Embodied World Models with Enhanced Generalizability