Research Areas
Our team at the Department of Data and Systems Engineering, The University of Hong Kong, specializes in Agentic Intelligence.
Our lab aims to solve long-term, challenging, and meaningful real-world research problems.
We are interested in advancing the following research areas:
- Development of Robotic Foundation Models.
- Agentic Systems built upon Large Language Models.
- Reinforcement Learning Theory and Algorithm Design.
- Data-driven Control for Nuclear Fusion.
Embodied AI expands the data and learning sources of multimodal LLMs through real-world interaction โ so we pursue both, under the banner of Agentic Intelligence.
Current Openings
(If interested, please contact Dr. Jiayu Chen directly. The Ph.D. application system accepts submissions year-round.)
- โโโ We are actively recruiting Postdocs, Ph.D., MPhil, and research assistants on LLM Agents.
For more information, please refer to the respective categories in openings.
News
- 2026-06-18: One paper accepted at ECCV (Ziyi) ๐๐๐
- 2026-06-17: One paper accepted at IEEE IROS (Xiaoquan) ๐๐๐
- 2026-06-13: One paper accepted at IEEE RAL (Wenqi) ๐๐๐
- 2026-06-02: One paper accepted at UAI 2026 (Xudong) ๐๐๐
- 2026-05-01: One paper accepted at ICML 2026 (XU Le) ๐๐๐
- 2026-02-10: Mithun Vanniasinghe received HKU Presidential PhD Scholarship ๐ฅ๐ฅ๐ฅ
- 2026-01-26: Two papers accepted at ICLR 2026 (Aravind) ๐๐๐
- 2026-01-23: One paper on RL for Fusion accepted at L4DC (Rohit) ๐๐๐
- 2025-12-21: One paper accepted at IEEE TPAMI (Mingqi) ๐๐๐
- 2025-12-19: One paper accepted at AAMAS 2026 and will be presented orally (Wentse) ๐๐๐
- 2025-12-08: Check the PIโs research story at MIT_Technology_Review ๐๐๐
- 2025-11-10: I have joined INFIFORCE as the Chief 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 (Yiming) ๐๐๐
- 2025-10-21: One paper accepted for the AAAI Student Abstract and Poster Program 2026, featuring an oral presentation (XU Le) ๐๐๐
- 2025-10-09: Our RL-LLM framework Verlog is featured by JIQIZHIXIN ๐๐๐
- 2025-09-19: Two papers accepted at NeurIPS 2025 (Wentse, Sizhe) ๐๐๐
- 2025-07-22: Our survey on Behavior Foundation Models is featured by JIQIZHIXIN ๐๐๐
Fundings
| Funding Scheme | Research Topic | Duration | Role |
|---|---|---|---|
| Early Career Scheme, HK UGC | Skill-Based Continual Reinforcement Learning for Vision-Language-Action Models Empowering Generalist Robotic Agents | 2027/01โ2029/12 | PI |
| ๅฝๅฎถ่ช็ถ็งๅญฆๅบ้้ๅนด็งๅญฆๅบ้้กน็ฎ๏ผC็ฑป๏ผ | ่ชไธป่ฟๅ็ๅ ท่บซๆบ่ฝไฝ๏ผ่ง่ง-่ฏญ่จ-ๅจไฝๆจกๅ็ๆ็ปญๅญฆไน ๆบ็็ ็ฉถ | 2026/09-2029/08 | PI |