Hi there!
I am a second-year Ph.D. student at MMLab@CUHK, advised by Prof. Dahua Lin. My research focuses on Robotic Manipulation, particularly World Action Model and Dexterous Manipulation.
Before joining CUHK, I received my bachelor's degree in Automation from the College of Control Science and Engineering at Zhejiang University, where I was also a member of ACEE (Advanced Honor Class of Engineering Education) at Chu Kochen Honors College. During my undergraduate studies, I worked as a research intern at InternRobotics, working closely with Dr. Jiangmiao Pang, Dr. Jia Zeng, and Dr. Linning Xu.
in submission
We introduce a hand-skeleton-conditioned world action model that transfers manipulation skills from human demonstrations to robots through a shared hand-skeleton interface.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
We introduce InternData-A1, a high-fidelity synthetic dataset with over 630k trajectories and 7,433 hours. It provides the first evidence that synthetic data alone can match the strongest π-dataset for VLA pre-training.
Robotics: Science and Systems (RSS), 2025
We introduce gripper keypose and object pointflow as compact, generalizable interfaces for learning coordinated bimanual manipulation.
* Equal contribution. † Corresponding author.
Outside the lab, I enjoy strength training and cooking, especially experimenting with new recipes and sharing good food with friends.