Now Notes

Chengjing Yuan

I am currently a Research Engineer at the National University of Singapore, where I am fortunate to work with Prof. Xingyu Liu. Before this, I spent my time at UC San Diego — earning a B.S. in Computer Engineering and an M.S. in Intelligent Systems, Robotics and Control — and got incredibly lucky to learn from Prof. Xiaolong Wang and Prof. Michael Yip along the way.

I am broadly excited about building robots that can perceive, reason, and act in the real world — spanning Robot Learning, Reinforcement Learning, Computer Vision, and Control Theory.

Chengjing Yuan

Publications

Visual Manipulation with Legs

Xialin He*, Chengjing Yuan*, Wenxuan Zhou, Ruihan Yang, David Held, Xiaolong Wang

CoRL 2024

A system enabling quadrupeds to manipulate objects with their legs using reinforcement learning trained on point cloud observations.

Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation

Jianglong Ye*, Keyi Wang*, Chengjing Yuan, Ruihan Yang, Yiquan Li, Jiyue Zhu, Yuzhe Qin, Xueyan Zou, Xiaolong Wang

RSS 2025

A large-scale dataset of one billion demonstrations for dexterous manipulation, covering grasping and articulation across thousands of diverse objects and multiple robot hands.

Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control

Chenhao Lu*, Xuxin Cheng*, Jialong Li*, Shiqi Yang, Mazeyu Ji, Chengjing Yuan, Ge Yang, Sha Yi, Xiaolong Wang

ICRA 2025

Predictive motion priors for humanoid whole-body control, enabling mobile manipulation through teleoperation with learned motion anticipation.