About
Lihao Liu is an Applied Scientist at Amazon Web Services (AWS) AI Lab, USA. He received his Ph.D. from the Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge, under the supervision of Prof. Carola-Bibiane Schoenlieb, Dr. Angelica I. Aviles-Rivero, and Prof. Pietro Lio. Prior to that, he obtained his M.Phil. from the Chinese University of Hong Kong (CUHK) (supervised by Prof. Pheng-Ann Heng) and his B.Eng. from Chongqing University.
During 2024.11 – 2025.05, he was a visiting researcher at the GMAI Lab, collaborating on LLM-based agents and AI for healthcare.
Research Interests
- LLM-based Autonomous Agents for Medicine: multi-agent systems for clinical and biomedical tasks
- Medical Image Analysis: segmentation, registration, detection — including brain structure segmentation and lung nodule analysis
- AI for Healthcare and Clinical Decision Support: applied large language models to clinical workflows
- Computer Vision: video shadow detection (SCOTCH and SODA, CVPR 2023), mirror detection, object detection
Selected Publications
- MedGround-R1 (MICCAI 2025) — Co-author. Advancing medical image grounding via spatial-semantic rewarded group relative policy optimization. MICCAI Best Paper and Young Scientist Award Shortlist.
- Detect Any Mirrors (CVPR 2025) — Co-first Author. Boosting learning reliability on large-scale unlabeled data with an iterative data engine.
- Mamba4D (CVPR 2025) — Co-author. Efficient 4D point cloud video understanding with disentangled spatial-temporal state space models.
- SCOTCH and SODA (CVPR 2023) — First Author. A Transformer video shadow detection framework.
- Contrastive Registration for Unsupervised Medical Image Segmentation (IEEE TNNLS 2022) — First Author.
- Psi-Net (IEEE TMI 2020) — First Author. Stacking densely convolutional LSTMs for sub-cortical brain structure segmentation.
- Multi-Task Deep Model with Margin Ranking Loss for Lung Nodule Analysis (IEEE TMI 2019) — First Author.
Career Trajectory
Chongqing University (B.Eng.) -> CUHK (M.Phil., Prof. Pheng-Ann Heng) -> University of Cambridge (Ph.D., DAMTP) -> UCLA (Visiting Scholar, Prof. Stanley Osher) -> Amazon AWS AI Lab (Applied Scientist) – with research visits at Microsoft Research Cambridge and GMAI Lab