About Me
Hi! I’m Sicong Li (李斯骢, E-mail: lisicong@iie.ac.cn). Now I am a PhD. student at Institute of Information Engineering, Chinese Academy of Sciences (IIE, CAS), supervised by Prof. Qingming Huang (黄庆明) (Professor at UCAS, IEEE Fellow) and Qianqian Xu (许倩倩) (Professor at ICT, CAS). I have received the B.E. degree in computer science and technology from Beihang University in 2024. My research interests include machine learning and computer vision. I have authored or co-authored several academic papers in top-tier international conferences and journals, including NeurIPS, ICML, CVPR, TPAMI, etc. If you are interested in my research, please email me at lisicong@iie.ac.cn.
📝 Publications
ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning
Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Longtao Huang, Xiaochun Cao, and Qingming Huang. ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning. Advances in Neural Information Processing Systems (NeurIPS), 2026. | [Code]
Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification
Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Linchao Zhang, Xiaochun Cao, and Qingming Huang. Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification. International Conference on Machine Learning (ICML), 2025. | [Code]
Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
Zhikang Xu, Qianqian Xu, Zitai Wang, Cong Hua, Sicong Li, Zhiyong Yang, and Qingming Huang. Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026. (Accepted)
DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations
Zhiyong Yang, Qianqian Xu, Sicong Li, Zitai Wang, Xiaochun Cao, and Qingming Huang. DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. (Accepted, DOI: 10.1109/TPAMI.2025.3647124)
Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
Zhiyong Yang, Qianqian Xu, Zitai Wang, Sicong Li, Boyu Han, Shilong Bao, Xiaochun Cao, and Qingming Huang. Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition. International Conference on Machine Learning (ICML), 2024. | [Code] | [Video]
🥇 Competitions
VizWiz Grand Challenge (Grounding All Valid Answers track) @ CVPR 2026, 1st Place
Team: Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Qingming Huang
3DCoMPaT Grounded CoMPaT Recognition Challenge (Fine track) @ CVPR 2025, 1st Place
Team: Sicong Li, Qianqian Xu, Cong Hua, Yangbangyan Jiang, Qingming Huang
EgoVis HoloAssist Challenges @ CVPR 2025, 1st Place
Team: Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Sicong Li, Qingming Huang
📖 Academic Services
Conference
- ICML: Reviewer (2025, 2026)
- NeurIPS: Reviewer (2024, 2025, 2026)
- ICLR: Reviewer (2025, 2026, 2027)
- CVPR: Reviewer (2026)
- AAAI: Reviewer (2027)
🎓 Educations
2024.09 - now, Ph.D. Student.
Institute of Information Engineering, Chinese Academy of Sciences (中国科学院信息工程研究所, IIE, CAS).
University of Chinese Academy of Sciences, Beijing.
2020.09 - 2024.06, Undergraduate.
Shenyuan Honors College.
Beihang University (北京航空航天大学, BUAA), Beijing.