Chao Zhang
Chao Zhang is a senior researcher at Samsung Research China, Beijing, where he has worked since 2016. His computer vision research spans optical flow, scene graph generation, semantic scene completion, and 3D perception, and he is known for Flowformer, which applies a transformer architecture to optical-flow estimation. He has also contributed to vision-language-action models for robotic manipulation, including the H-VLA and DAM-VLA frameworks.
“H-VLA splits robotic control into two stages: a Key-Action Model that predicts the next manipulation subgoal (a 6-DoF end-effector pose + gripper state), and a Motion Planning Model that generates dense frame-by-frame actions conditioned on that subgoal.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.