He Zhang 张贺

Gmail: he.zhang.cs AT
Tencent Email: herbzhang AT
Previous Email:

I am a senior researcher at Tencent RoboticsX Lab (Agent Learning Center).

My current work focuses on motion control of the simulated character and dexterous manipulation with physics-based, data-driven, and learning-based techniques.

I received Ph.D from the University of Edinburgh in Computer Science in 2022, advised by Prof.Taku Komura.

Check out my Google Scholar, Linkedin, GitHub, or CV.


ManipNet: Neural Manipulation Synthesis with a Hand-Object Spatial Representation
He Zhang, Yuting Ye, Takaaki Shiratori, Taku Komura
ACM Transactions on Graphics 40(4), 2021
Proceedings of SIGGRAPH 2021
[pdf] [video] [supplementary video] [project]
Neural State Machine for Character-Scene Interactions
Sebastian Starke*, He Zhang*, Taku Komura, Jun Saito
ACM Transactions on Graphics 38 (6), 2019
Proceedings of SIGGRAPH Asia 2019
[pdf] [project] [video]
Mode-Adaptive Neural Networks for Quadruped Motion Control
He Zhang*, Sebastian Starke*, Taku Komura, Jun Saito
ACM Transactions on Graphics 37(4), 2018
Proceedings of SIGGRAPH 2018
[pdf] [project] [video]
Few-shot Learning of Homogeneous Human Locomotion Styles
Ian Mason, Sebastian Starke, He Zhang, Hakan Bilen, Taku Komura
Computer Graphics Forum, 37(7), 2018
Best Student Paper Award at Pacific Graphics 2018
[pdf] [code] [video]