Yuan Mingzhi
- IMIC Lab
- People , Engineering teacher
- July 3, 2025

Yuan Mingzhi, Ph.D., is a lecturer at the School of Artificial Intelligence (College of Future Technology), Nanjing University of Information Science & Technology, and a core member of the Jiangsu University Key Laboratory of Intelligent Medical Image Computing and the Smart Medical Research Institute. Obtained a bachelor’s degree in engineering (communication engineering) from Harbin Institute of Technology in June 2020, and a doctorate in engineering (biomedical engineering) from Fudan University in June 2025. The current main research directions are intelligent drug design, three-dimensional computer vision, etc. In the past three years, he has published 25 papers in top conferences and journals such as ICCV, ECCV, CVPR, ICRA, and BIB, including 17 first authors (including co-authors). He has long served as a reviewer for important journals in the field, TPAMI, TIP, RAL, and Automation Journal.
For more information, please visit my personal homepage: http://faculty.nuist.edu.cn/%7Ezuaeye/zh_CN/index.htm
Research direction:
Intelligent drug design: protein representation learning, virtual drug screening, small molecule representation learning, molecular docking
3D computer vision: 3D point cloud registration, point cloud perception
Machine Learning: Active Learning
Representative papers:
[1] Yuan M, Fu K, Li Z, et al. PointMBF: A multi-scale bidirectional fusion network for unsupervised RGB-D point cloud registration[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 17694-17705.
[2] Yuan M, Li Z, Jin Q, et al. Pointclm: A contrastive learning-based framework for multi-instance point cloud registration[C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2022: 595-611.
[3] Yuan M, Fu K, Li Z, et al. Robust point cloud registration via random network co-ensemble[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(7): 5742-5752.
[4] Yuan M, Shen A, Ma Y, et al. ProteinF3S: boosting enzyme function prediction by fusing protein sequence, structure, and surface[J]. Briefings in Bioinformatics, 2025, 26(1): bbae695.
[5] Yuan M, Huang X, Fu K, et al. Boosting 3D point cloud registration by transferring multi-modality knowledge[C]//2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2023: 11734-11741.
Translated from the original Chinese source.


