About Me

I am currently a visiting Ph.D. student at the Lee Kong Chian School of Medicine (LKCMedicine), Nanyang Technological University (NTU), Singapore, advised by Prof. Baosheng Yu. Since 2021, I have been enrolled in the Master-Ph.D. Combined Program in Control Science and Engineering at the College of Information Science and Engineering, Northeastern University, China, where I am advised by Prof. Tong Jia.

My recent work focuses on artificial intelligence for medicine, applying technologies such as AI agents, agentic AI, and reinforcement learning to multimodal medical data, including images and text. Before this, I mainly studied overlapping object perception methods for autonomous security inspection scenarios, including prohibited item detection, prohibited item segmentation, and pneumonia detection.

You can also find my articles on my Google Scholar profile.

News

Selected Publications

FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception

Mingyuan Li, Tong Jia, H. Lu, Bowen Ma, H. Wang, and D. Chen

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2025. JCR Q1, IF: 20.8; under review

arXiv

MMCL: Boosting Deformable DETR-Based Detectors with Multi-Class Min-Margin Contrastive Learning for Superior Prohibited Item Detection

Mingyuan Li, Tong Jia, H. Lu, Bowen Ma, H. Wang, and D. Chen

IEEE Transactions on Image Processing (IEEE TIP), 2025. JCR Q1, IF: 10.8; under review

arXiv

CSPCL: Category Semantic Prior Contrastive Learning for Deformable DETR-Based Prohibited Item Detectors

Mingyuan Li, Tong Jia, H. Wang, Bowen Ma, H. Lu, and D. Chen

NeurIPS 2025, 2025. CCF A

Paper arXiv

AO-DETR: Anti-Overlapping DETR for X-Ray Prohibited Items Detection

Mingyuan Li, Tong Jia, H. Wang, Bowen Ma, H. Lu, Shuyang Lin, and D. Chen

IEEE Transactions on Neural Networks and Learning Systems, 2024. JCR Q1, IF: 10.2

Paper arXiv

GADet: A Geometry-Aware X-Ray Prohibited Items Detector

Mingyuan Li, Bowen Ma, H. Wang, D. Chen, and Tong Jia

IEEE Sensors Journal, 2023. JCR Q1, IF: 4.3

Paper

Education

• 2021.09-Present: Visiting Ph.D. student, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore. Advisor: Prof. Baosheng Yu.
• 2021.09-Present: Master-Ph.D. Combined Program in Control Science and Engineering, Northeastern University, China. Advisor: Prof. Tong Jia.
• 2017.09-2021.06: B.S. in Automation, Northeastern University, China.

Selected Projects

• 2021.09-2023.09: Participated in a classified project of the National Key Research and Development Program of China, 5 million RMB.
• 2022.09-2023.03: Participated in and led the Huawei Computer Vision Premium Course project, developing YOLOv5 models with MindSpore, including model construction, training, evaluation, visualization, Jupyter Notebook cases, manuals, textbooks, and presentation materials.
• 2019.11-2021.07: Led a provincial college students’ innovative training project on perovskite-based nano-gas sensors for vehicle air quality detection.
• Joint Funds of the National Natural Science Foundation of China (U22A2063): Theory and implementation method of 3D visual perception of industrial robots for flexible and accurate assembly tasks, 2.56 million RMB, project backbone.
• National Key Research and Development Program of China (2022YFF0902401): Research on immersive content intelligent construction and multi-modal fusion technology, 679,000 RMB, project backbone.

Patent

• Tong Jia, Yixin Tian, Songsheng Wu, Bowen Ma, Shuyang Lin, Mingyuan Li. A target detection method under complex overlapping backgrounds. China Patent ZL202410572032, approval number CN118135244A.

Professional Services

Reviewer for NeurIPS, CVPR, TNNLS, PR, EAAI, TETCI, and PRCV.