About me
I am currently an Applied Scientist at Amazon Web Services, where I work with customers to build AI agents that carry out real business tasks and bring them into production.
My research aims to advance trustworthy and efficient machine learning. I develop methods to protect privacy and make learning more efficient. I also study how models fail under attack. My current research focuses on language models and AI agents.
I received my Ph.D. in Computer Science from Old Dominion University in 2022, advised by Cong Wang, and my B.E. in Computer Science from Central South University in 2017.
Publications
-
Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training
European Conference on Computer Vision (2026)
-
Human Perception of AI Capabilities at Classifying Perturbed Roadway Signs
IEEE Transactions on Human-Machine Systems (2025)
-
Unsupervised Multi-Criteria Adversarial Detection in Deep Image Retrieval
International Conference on Security and Privacy in Communication Networks (2023)
-
A Framework for Behavioral Biometric Authentication Using Deep Metric Learning on Mobile Devices
IEEE Transactions on Mobile Computing (2023)
-
You See What I Want You to See: Exploring Targeted Black-Box Transferability Attack for Hash-Based Image Retrieval Systems
IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021)
-
Evade Deep Image Retrieval by Stashing Private Images in the Hash Space
IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020)
-
Close the Gap Between Deep Learning and Mobile Intelligence by Incorporating Training in the Loop
ACM International Conference on Multimedia (2019)
Academic service
Reviewer for the following conferences and journals.
- Conferences
- CVPR · ICCV · ECCV · BMVC · ACCV · INFOCOM · ICDCS · ICPADS · MASS
- Journals
- TIFS · TNNLS · TCSVT · TVCJ · Journal of Electronic Imaging · IEEE Access