I am a Ph.D. Student in Computer Science at the University of Maryland advised by Prof. Heng Huang, where I am currently conducting research on Trustworthy Machine Learning. My work revolves around exploring the application of this field in various areas, such as computer vision, graph neural networks, and foundation models. I am fortunate to have the chance to collaborate with Prof. Hongyang Zhang and Prof. Aleksandar Bojchevski.

Publications

A Law of Robustness beyond Isoperimetry
Yihan Wu, Heng Huang, Hongyang Zhang.
In International Conference on Machine Learning, ICML 2023.

Adversarial Weight Perturbation Improves Generalization in Graph Neural Network
Yihan Wu, Aleksandar Bojchevski, Heng Huang.
In Conference on Artificial Intelligence, AAAI 2023 (oral).

Cooperation or Competition: Avoiding Player Domination for Multi-target Robustness by Adaptive Budgets
Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang, Hongyang Zhang
In IEEE / CVF Computer Vision and Pattern Recognition Conference, CVPR 2023.

RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval
Yihan Wu, Hongyang Zhang, Heng Huang.
In International Conference on Machine Learning, ICML 2022.

Completing the picture: Randomized smoothing suffers from the curse of dimensionality for a large family of distributions
Yihan Wu, Aleksandar Bojchevski, Aleksei Kuvshinov, Stephan Günnemann.
In International Conference on Artificial Intelligence and Statistics, AISTATS 2021.

Predicting antigen specificity of single T cells based on TCR CDR 3 regions
David S Fischer, Yihan Wu, Benjamin Schubert, Fabian J Theis.
Molecular systems biology 16 (8), e9416.