Minghan Li
Postdoc Research Fellow at Harvard University
Embedded Files
I am a PostDoc Research Fellow at Harvard Medical School under the guidance of Prof. Mengyu Wang. In Harvard AI and Robotic lab, my research focuses on building world model for dynamic environments, including video understanding, generation, and editing, Embodied AI and AI for science. During this period, my PI and I co-organized the Harvard AI & Robotics Seminar Series, which brings together researchers to discuss advances in artificial intelligence and robotics.
🎓 In Aug. 2024, I received my PhD degree in the Department of Computing at the Hong Kong Polytechnic University (PolyU), advised by Prof. Lei Zhang.
🎓In 2019, I received my Master’s degree in the School of Mathematics and Statistics at Xi'an JiaoTong University under the supervision of Prof. Deyu Meng.
Research Interests
GenAI: Image/video understanding, generation, editing 💥💥💥
High-level generation: image and video editing, personalization
Mid-level recognition: video grounding, detection, segmentation
Low-level vision: video rain/snow removal, low-light enhancement
EmAI: understanding → reconstruction → interaction
AI for Science: vision language models for medical data 💥
Medical imaging: Data privacy, demography fairness, federated learning
LLMs for Genomics: Gene-Gene interaction, Gene-to-drug
Work Experience
09/2024-now, Postdoc research fellow in Harvard AI & Robotics Lab, Harvard Medical School.
08/2023-09/2024, I worked as a Research Intern in OPPO Research Institute.
05/2019-11/2019, I worked as a research assistant in the Hong Kong Polytechnic University.
05/2018-09/2018 and 03/2020-11/2021, I worked as a Research Intern in DAMO Academy, Alibaba.
Invited Presentations
3D 视觉工坊, Sep-18-2025, Video Editing Benchmark
AI Time, Sep-12-2025, Video Editing Benchmark
Twelve Labs: Unified Video Segmentation and Video Object Segmentation
VALSE 2024: Outstanding Student Forum (优秀学生论坛)
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2018-now
The IEEE/CVF International Conference on Computer Vision (ICCV) 2018-now
The European Conference on Computer Vision (ECCV) 2018-now
The International Conference on Learning Representations (ICLR) 2025
The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NIPS) 2025
The Association for the Advancement of Artificial Intelligence (AAAI) 2024
The International Joint Conference on Artificial Intelligence (IJCAI) 2025
Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
IEEE Transactions on Image Processing (TIP)
Pattern Recognition (PR)
Engineering Applications of Artificial Intelligence (EAAI)
Expert Systems with Applications (ESWA)
Image and Vision Computing
Signal Processing
Page updated
Google Sites
Report abuse