Zechao Li
Professor
Intelligent Media Analysis Group (IMAG)
School of Computer Science and Engineering
Nanjing University of Science and Technology
Email: zechao[dot]li[AT]njust[dot]edu[dot]cn
Positions for Interns / Master's / PhD Programme
We are looking for self-motivated students who aim to produce impactful research or engineering contributions and publish in top-tier venues. Ideal candidates are well-rounded and demonstrate a strong and responsible attitude, solid mathematical foundations, strong programming skills, and excellent English proficiency. If you are interested, please feel free to drop me an email with your CV and a brief description of your research interests.
Biography
Zechao Li is currently a Professor and dean of the School of Computer Science and Engeering, the School of Artificial Intelligence, and the School of Software Engeering at the Nanjing University of Science and Technology. He received the Bachelor's degree from University of Science and Technology of China (USTC) in 2008 and the Doctor degree from National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences in 2013. He has authored over 90 papers in top-tier journals and conferences. His research interests include Multimedia analysis, Embodied Intelligence, MLLM for Science, Detection & Segmentation, few-shot learning, etc. He was a recipient of the Best Paper Award in ACM Multimedia Asia 2020 and 2024. He has served as an Associate Editor for IEEE TPAMI, TNNLS, etc.
Research Interests
My research focuses on intelligent multimedia analysis and computer vision, with emphasis on developing efficient and robust algorithms for real-world applications:
- Cross-Media Intelligent Analysis
- Embodied Intelligence
- MLLM for Science
- Detection & Segmentation
- Hashing and Retrieval
News
- [2025-10] One paper about "T2I Generation" accepted to TPAMI.
- [2025-09] Four paper accepted to NeurIPS 2025.
- [2025-07] Two paper accepted to ICCV 2025.
- [2025-07] One paper "Inv Adapter" accepted to TPAMI.
- [2025-07] One paper accepted to ACM MM 2025.
- [2024-12] One paper "ConTriNet" accepted to TPAMI.
- [2024-10] Received Best Paper Award at ACM Multimedia Asia 2024.
- [2024-06] Two papers on visual grounding and visual prompting accepted to CVPR 2024.
- [2024-03] One paper on robust visual grounding accepted to TPAMI.
Major Honors & Awards
- 2020-2024: Elsevier Highly Cited Chinese Researchers
- 2024: Best Paper Award of ACM Multimedia Asia
- 2020-2023: Elsevier Highly Cited Chinese Researchers
- 2022: The First Prize of Natural Sciences Award of The Chinese Institute of Electronics
- 2020: The First Prize of Science and Technology Award of Jiangsu Province
- 2020: Best Paper Award of ACM Multimedia Asia
- 2018: The WU WEN JUN Artificial Intelligence Excellent Youth Award
- 2018: Best Student Paper Award of International Conference on Internet Multimedia Computing and Service
- 2017: The First Prize of Science and Technology Award of Jiangsu Province
- 2017: Young Talent Program of China Association for Science and Technology
- 2016: Top 10% Paper Award of IEEE MMSP
- 2015: Excellent Doctoral Dissertation of Chinese Academy of Sciences
- 2015: Excellent Doctoral Dissertation of China Computer Federation
- 2013: President Scholarship of the Chinese Academy of Sciences
Courses Taught
- 2020-2024: Media Computing Foundations (媒体计算基础) - Courses (课件) google_drive Courses (课件) baidu_drive
Selected Publications
Peng Xing, Ning Wang, Yanpeng Sun, Jinhui Tang, Zechao Li*, "Refine, Control and Distill: A Text-to-Image Framework for Faithful Image Generation", T-PAMI, 2025.
Paper
Weihao Bo, Yanpeng Sun, Yu Wang, Xinyu Zhang, Zechao Li, "FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts", NeurIPS 2025.
Paper
Pytorch Code
Peng Xing, Haofan Wang, Yanpeng Sun, Qixun Wang, Xu Bai, Hao Ai, Jen-Yuan Huang, Zechao Li*, "CSGO: Content-Style Composition in Text-to-Image Generation", NeurIPS 2025.
Paper
Pytorch Code
Jiawei Gu, Ziyue Qiao, Xinming Li, Zechao Li*, "Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening", NeurIPS 2025.
Paper
Jiawei Gu, Ziyue Qiao, Zechao Li*, "Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks", NeurIPS 2025.
Paper
Xu Cheng, Xin Jiang, Zechao Li*, "A Unified Interpretation of Training-Time Out-of-Distribution Detection", Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2025.
Paper
Jiawei Gu, Ziyue Qiao, Zechao Li*, "Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention", Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2025.
Paper
Peng Xing, Ning Wang, Jianbo Ouyang, Zechao Li*, "Inv-Adapter: ID Customization Generation via Image Inversion and Lightweight Parameter Adapter", IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2025.
Paper
Hao Tang, Zechao Li*, Dong Zhang, Shengfeng He, Jinhui Tang, "Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.
Paper
Pytorch Code
Yanpeng Sun, Jiahui Chen, ...,Jingdong Wang, Zechao Li*, "VRP-SAM: SAM with Visual Reference Prompt", IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024.
Paper
Pytorch Code
Wei Tang, Liang Li, Xuejing Liu, Lu Jin, Jinhui Tang, Zechao Li*, "Context Disentangling and Prototype Inheriting for Robust Visual Grounding", IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.
Paper
Pytorch Code
Yanpeng Sun, Qiang Chen, ..., Zechao Li*, Jingdong Wang, "Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning", Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), 2022.
Paper
Paddle Code
Pytorch Code
Academic Services
- IEEE TPAMI 编委
- IEEE TNNLS 编委
- IEEE TMM 编委
- IEEE TCSVT 编委
- Information Sciences 编委
- IEEE/CAA Journal of Automatica Sinica(自动化学报英文版)青年编委(2021.10-)
- JCST 编委(2019.01-)
- CSIG 机器视觉专委会常务委员
- CSIG 多媒体专委会常务委员
- CCF 多媒体专委会副秘书长




























