Bio
I am a quantitative researcher. I completed my Ph.D. in the Department of Automation at Tsinghua University in October 2025. Prior to this, I earned my Bachelor of Science degree in Mathematics and Physics from the Department of Physics at Tsinghua University in 2020.
My research primarily focuses on machine learning under mismatched distribution, including areas such as long-tailed learning and test-time adaptation.
News
- [10/2025] Graduated from Tsinghua University with a Ph.D. degree.
- [06/2025] Two papers are accepted by ICML 2025 PUT Workshop.
- [05/2024] One paper is accepted by ICML 2024.
- [02/2024] One paper is accepted by TPAMI.
Selected Publications
Preprints
Journal Papers
Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
Chaoqun Du, Yulin Wang, Shiji Song, Gao Huang
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF=20.8), 2024
The High Separation Probability Assumption for Semi-Supervised Learning
Gao Huang, Chaoqun Du (Student First Author)
IEEE Transactions on Systems, Man, and Cybernetics: Systems (TSMC-S, IF=8.6), 2022
Conference Papers
SwiTTA: Switching Domain Experts and Aggregating Contextual Features Towards Realistic Test-Time Adaptation
Chaoqun Du, Jiayi Guo, Yulin Wang, Gao Huang
International Conference on Machine Learning (ICML) 2025 PUT Workshop, 2025
UniTTA: Unified Benchmark and Versatile Framework Towards Realistic Test-Time Adaptation
Chaoqun Du, Jiayi Guo, Yulin Wang, Gao Huang
International Conference on Machine Learning (ICML) 2025 PUT Workshop, 2025
SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
Chaoqun Du*, Yizeng Han*, Gao Huang
International Conference on Machine Learning (ICML), 2024
Assessing a Single Image in Reference-Guided Image Synthesis
Jiayi Guo, Chaoqun Du, Jiangshan Wang, Huijuan Huang, Pengfei Wan, Gao Huang
AAAI Conference on Artificial Intelligence (AAAI) (oral), 2022