Xiang Li
Assistant Professor, Department of Radiology, Massachusetts General Hospital and Harvard Medical School. Affiliated Faculty, Harvard Kempner Institute.
399 Revolution Dr., 11th Floor
Somerville, MA 02145
I am an Assistant Professor in the Department of Radiology at Massachusetts General Hospital and Harvard Medical School, and affiliated faculty at the Harvard Kempner Institute. My lab works on medical foundation models, generative AI, expert-machine alignment, medical informatics, and counterfactual causal inference — building models that clinicians can actually reason with, not just query.
I received my Ph.D. in Computer Science from the University of Georgia under Distinguished Professor Tianming Liu (AIMBE Fellow), and completed postdoctoral training at MGH/HMS with Associate Prof. Quanzheng Li and Distinguished Professor James H. Thrall.
I have published over 250 papers with more than 17,000 citations and an h-index of 60. I serve as Associate Editor for IEEE Transactions on Medical Imaging and Data Intelligence, as founding chair of MICCAI and NeurIPS workshops on medical foundation models, and as Area Chair for NeurIPS, KDD, AAAI, ACM MM, and MICCAI.
news
| Sep 21, 2026 | Happy to know that we’ll start our Automated PET Report Generation with Visual Grounding project under the support from NIH (1R01EB038426-01). |
|---|---|
| Sep 12, 2026 | OpenSkill: Open-World Self-Evolution for LLM Agents is accepted by EMNLP 2026. This work asks whether an agent can evolve given nothing but a task prompt, building both its skills and its own verification from documentation and repositories. |
| Sep 12, 2026 | Happy to know that we’ll start our UniBrain: An End-to-End Unified Toolkit for Comprehensive Neuroimaging Analysis project under the support from NIH (1R01EB038264-01A1). |
| Aug 09, 2026 | LiveMedBench: A Contamination-Limited Medical Benchmark for LLMs is accepted by KDD 2026. |
| Jul 26, 2026 | Honored to serve as the Associate Editor of IEEE Transactions on Medical Imaging. |
selected publications
- Interpretable agentic AI system with localized reasoning for radiologynpj Digital Medicine, 2026
- Towards a general-purpose foundation model for functional MRI analysisNature Biomedical Engineering, 2026
- ECHOPulse: ECG Controlled Echocardio-gram Video GenerationIn International Conference on Learning Representations, 2025
-
- A generalist vision–language foundation model for diverse biomedical tasksNature Medicine, 2024
- Eye-gaze guided multi-modal alignment for medical representation learningAdvances in Neural Information Processing Systems, 2024