Xianyuan Zhan

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model

Sample Efficient Offline RL via T-Symmetry Enforced Latent State-Stitching

Dichotomous Diffusion Policy Optimization

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance

Towards Robust Zero-Shot Reinforcement Learning

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

Data Center Cooling System Optimization Using Offline Reinforcement Learning

Skill Expansion and Composition in Parameter Space

Efficient Robotic Policy Learning via Latent Space Backward Planning

xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing

Pushing the Limit of Small-Efficient Offline Reinforcement Learning

Co-evolved Self-Critique: Enhancing Large Language Models with Self-Generated Data