LimX Dynamics · Shenzhen
Oct. 2025 – Sept. 2026Reinforcement Learning Intern
Real-world reinforcement learning for humanoid robots. Developed RAPID for efficient policy adaptation through distillation and online reinforcement learning.
Contact:
The University of Hong Kong
Pokfulam Road, Hong Kong
kunsonghku@connect.hku.hk
I am a Ph.D. student in Computer Science at The University of Hong Kong (HKU), advised by Jia Pan. Before that, I obtained my master's degree in RCMVL (Robot Control and Machine Vision Lab) of Shanghai Jiao Tong University (SJTU) advised by Prof. Zhenhua Xiong in 2025. I received my bachelor's degree in Mechanical Engineering with honors from SJTU in 2022.
From May 2024 to January 2025, I was a research intern in MSC-Lab at UC Berkeley, advised by Prof. Masayoshi Tomizuka and Prof. Mingyu Ding.
I am interested in enabling robots to learn, adapt, and interact with the physical world intelligently and safely. My recent research focuses on humanoid robot learning and tactile perception and manipulation, particularly efficient policy adaptation in real-world environments.
I am open to collaboration. Feel free to contact me if there is anything I can help with.
Reinforcement Learning Intern
Real-world reinforcement learning for humanoid robots. Developed RAPID for efficient policy adaptation through distillation and online reinforcement learning.
Project Lead, Tactile Real-World Reinforcement Learning
Developed PEARS for contact-rich tactile manipulation, combining physics-guided force reasoning, vision-language failure diagnosis, and tactile-conditioned diffusion steering.
* indicates equal contribution.