Home
Experience
Education
Research
Publications
Activities
Miscellaneous
Deadlines

About Me

Jian Liang

梁坚 (Jian Liang, Tim)
Associate Professor
Center for Research on Intelligent Perception and Computing
Institute of Automation, Chinese Academy of Sciences

Room 1505, Intelligent Building, 95 Zhongguancun East Road
100190, Haidian District, Beijing, China

👻Resume
♟Github
🎖Google Scholar
📄Arxiv
 ⇰ liangjian92🌀gmail.com or jian.liang🌀nlpr.ia.ac.cn


Before joining CASIA in June 2021, I was a research fellow at the Vision and Learning Group, National University of Singapore, working with Dr. Jiashi Feng from June 2019 to April 2021. I obtained Ph.D. in Pattern Recognition and Intelligent Systems from CASIA in Jan 2019, under the supervision of Prof. Tieniu Tan and co-supervision of Prof. Ran He and Prof. Zhenan Sun, and received my bachelor degree in Automation from Xi'an Jiaotong University in June 2013.

My current research interests mainly focus on representation learning, knowledge transfer, trustworthy AI (including security, privacy, or robustness in AI), and their applications in various computer vision problems.

I am open to discussion or collaboration. Feel free to drop me an email if you're interested.

News (the past year)

  • [2025/06] One paper has been accepted to ICCV 2025.

  • [2025/06] I am invited as an Area Chair of WACV 2026.

  • [2025/02] Two papers have been accepted to CVPR 2025.

  • [2025/01] Our paper on LoRA has been accepted to ICLR 2025.

  • [2024/12] I am invited as an Area Chair of ICCV 2025.

  • [2024/12] I am invited as an Associate Editor of Pattern Recognition.

  • [2024/12] Two papers have been accepted to AAAI 2025.

  • [2024/12] I am invited as an Area Chair of IJCAI 2025.

  • [2024/11] I am invited as an Area Chair of ICML 2025.

  • [2024/10] Our extension on model fingerprinting has been accepted to IJCV.

  • [2024/09] Our paper on validation of unsupervised domain adaptation methods has finally been accepted to NeurIPS Datasets and Benchmarks Track 2024.

  • [2024/08] I am invited as an Area Chair of ICLR 2025.

  • [2024/07] Our paper on source-free semantic segmentation has finally been accepted to TPAMI.

  • [2024/07] Our survey on test-time adaptation has been accepted to IJCV.

  • [2024/07] Our paper on open-set test-time adaptation has been accepted to ECCV 2024.


Recent Work

Protecting Model Adaptation from Trojans in the Unlabeled Data.

Abstract:

Lijun Sheng, Jian Liang, Ran He, Zilei Wang, Tieniu Tan.
AAAI Conference on Artificial Intelligence (AAAI), 2025
[Paper] [Link]

Exploring Vacant Classes in Label-Skewed Federated Learning.

Abstract:

Kuangpu Guo, Yuhe Ding, Jian Liang, Ran He, Zilei Wang, Tieniu Tan.
AAAI Conference on Artificial Intelligence (AAAI), 2025
[Paper] [Link]

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?

Abstract:

Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu Tan.
Arxiv technical report, 2024.
[Paper] [Link] [Code]

A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts.
Jian Liang, Ran He, Tieniu Tan.
International Journal of Computer Vision (IJCV), 2024.
[Paper] [Code]

Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection.

Abstract:

Yuting Xu, Jian Liang, Lijun Sheng, Xiao-Yu Zhang.
International Journal of Computer Vision (IJCV), 2024.
[Paper] [Link]

Sample Correlation for Fingerprinting Deep Face Recognition.

Abstract:

Jiyang Guan, Jian Liang, Yanbo Wang, Ran He.
International Journal of Computer Vision (IJCV), 2024.
[Paper] [Link] [Code]

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization.
Abstract:
Jian Liang, Lijun Sheng, Zhengbo Wang, Ran He, Tieniu Tan.
International Conference on Machine Learning (ICML), 2024.
[Paper] [Code]

Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models.

Abstract:

Zhengbo Wang, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
International Conference on Machine Learning (ICML), 2024.
[Paper] [Link] [Code]

Trustworthy and Intelligent Machines (TIM) Group

Current Students

Alumni (Since 2019)