Tao Kong

Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots

RoboOmni: Actions Are Just Another Modality for Your Vision-Language Models

Flow-Based Policy for Online Reinforcement Learning

Human-assisted Robotic Policy Refinement via Action Preference Optimization

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Mani-WM: An Interactive World Model for Real-Robot Manipulation