Research Areas

Our team at the Department of Data and Systems Engineering, The University of Hong Kong, specializes in Learning for Sequential Decision-Making and Robotic Control.

We are interested in advancing the following research areas:

• Reinforcement Learning Theory and Algorithm Design.
• Development of Robotic Foundation Models, including VLA for Humanoid Robots and Generalist Household Robots.
• Post-training for Large Language Model Agents.
• Data-driven Control for Nuclear Fusion.
• Unified Theoretical Framework for Reinforcement Learning, Optimal Control, and Stochastic Optimization.

Currently, we have three active research directions: Offline Reinforcement Learning for Controllable Nuclear Fusion, VLAs for Humanoid Robots, and Continual Reinforcement Learning. We aim at the Next-Generation Physical AI. Here is an interesting reading list.

News

• 2025-12-08: Check the PI’s research story at MIT_Technology_Review 🌐🌐🌐
• 2025-11-10: I have joined INFIFORCE as a Principal Research Scientist to lead the research on RoboBrain.
• 2025-11-08: Two papers accepted at AAAI 2026, and one of them will be presented orally 🎉🎉🎉
• 2025-10-21: One paper accepted for the AAAI Student Abstract and Poster Program 2026, featuring an oral presentation 🎉🎉🎉
• 2025-10-09: Our RL-LLM framework Verlog is featured by JIQIZHIXIN 🌐🌐🌐
• 2025-09-19: Two papers accepted at NeurIPS 2025 🎉🎉🎉
• 2025-07-22: Our survey on Behavior Foundation Models is featured by JIQIZHIXIN 🌐🌐🌐

How to join us

Current Openings
(If interested, please contact Dr. Jiayu Chen directly. The Ph.D. application system accepts submissions year-round.)

• Openings for self-financed Ph.D. students and research assistants are available year-round.
• ❗❗❗ We have available positions for (funded) research assistants on World Models and Robotic Foundation Models.
• ❗❗❗ We need several remote research interns to work on skill adaptation, real-to-sim, generative-model-based RL, or auto-deployment of embodiment intelligence. Please reach out to Dr. Jiayu Chen if interested. Our Ph.D. or MPhil candidates are usually selected among research interns.

Qualifications for Ph.D. and Postdoctoral Researchers:
Candidates should possess strong proficiency in mathematics or programming, as well as demonstrate self-motivation and resilience. Applicants with backgrounds in the following areas are highly preferred: Humanoid Robots, Large Language/Reasoning Models, Statistical Machine Learning.

For more information, please refer to the respective categories in openings.