Scholar
Jiequan Cui
Google Scholar ID: KbXLN2AAAAAJ
Professor, Hefei University of Technology
Citations & Impact
Citations
1,763
H-index
11
i10-index
11
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including:
- - Decoupled Kullback-Leibler Divergence Loss (NeurIPS, 2024)
- - Classes Are Not Equal: An Empirical Study on Image Recognition Fairness (CVPR, 2024)
- - Generalized Parametric Contrastive Learning (TPAMI, 2023)
- - ResLT: Residual Learning for Long-tailed Recognition (TPAMI, 2022)
- - Parametric Contrastive Learning (ICCV, 2021)
- - Learnable Boundary Guided Adversarial Training (ICCV, 2021)
Research Experience
- Currently a Full Professor at Hefei University of Technology. Research focuses on developing novel algorithms and theoretical foundations, such as contrastive learning and generative learning, to more effectively leverage data for enhancing model generalization and robustness. Also, the team actively explores multi-modal alignment and robustness in large models.
Education
- Received B.E. degree in Computer Science from Shandong University in 2018; obtained Ph.D. from The Chinese University of Hong Kong (CUHK) in 2022, supervised by Prof. Jiaya Jia and Prof. Bei Yu. Spent two years at Nanyang Technological University (NTU), Singapore.
Background
- Currently a Full Professor at Hefei University of Technology. Research interests include data-centric AI, particularly contrastive learning and generative learning, aimed at enhancing model generalization and robustness. The team also actively explores multi-modal alignment and robustness in large models (such as LLMs and VLMs), addressing critical challenges like jailbreak attacks, adversarial robustness, and hallucination mitigation. Additionally, interested in emerging machine learning topics such as AI for science and 3D modeling.
