About me
I am a Ph.D. candidate in Computer Science and Engineering at The Hong Kong University of Science and Technology (HKUST), advised by Prof. Hao Chen. My research focuses on medical multimodal foundation models, explainable medical AI, and agentic clinical systems.
I am particularly interested in combining generalist models, specialist models, tools, and structured evidence to build reliable systems for multimodal medical-image understanding and long-horizon clinical workflows.
Since April 2026, I have also been a research intern with the TGT Project at JD Health, working on medical multimodal large language models and agent Harness systems.
Research Highlights
Generalist–Specialist Collaboration
Co-first author of GSCo and MedDr, a framework that combines a medical generalist foundation model with lightweight specialist models for diagnosis and report generation.
Explainable Biomedical Foundation Model
Co-first author of ConceptCLIP, built with 23 million image–text–concept triplets and evaluated across 78 datasets and 10 imaging modalities.
News
Our work on ConceptCLIP was published in Nature Biomedical Engineering.
Our survey on agentic AI in biomedicine was published online in IEEE Reviews in Biomedical Engineering.
HKUST featured our Generalist–Specialist Collaboration framework for medical AI.
UniBiomed was published in Nature Communications.
Our work on GSCo and MedDr was published in Nature Biomedical Engineering.
Joined the TGT Project at JD Health as a research intern.
Our surgical video foundation model SurgVISTA was published in npj Digital Medicine.
FreeTumor was published in Nature Communications.
MedDr was featured among four HKUST medical AI foundation models.
Education
- Ph.D. in Computer Science and Engineering, HKUST, 2023–Present
- M.E. in Artificial Intelligence, Tsinghua University, 2020–2023
- B.S. in Automation, Hefei University of Technology, 2016–2020
Experience
- Research Intern, TGT Project, JD Health, Apr 2026–Present
Medical multimodal large language models and agent Harness systems. - FA Talent, AI4Science, Microsoft Research Asia, Jan–Jul 2023
Multimodal understanding with large language models. - Researcher, YouTu Lab, Tencent, Jul 2021–Jan 2023
Vision–language pretraining and multi-label classification.
Professional Service
Conference Reviewer
- CVPR2026 (Outstanding Reviewer)
- ECCV2026
- NeurIPS2026
- AAAI2026, 2027
- ACM Multimedia2024
Journal Reviewer
- IEEE Transactions on Medical Imaging (TMI)
- Neural Networks (NN)
- IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- Pattern Recognition
Selected Honors
- RedBird PhD Award, HKUST, 2023, 2025, and 2026
- Stars of Tomorrow Internship Program, Microsoft Research Asia, 2023
- National Scholarship, Ministry of Education, China, 2017–2019