Hi. I'm Yiwei Yang.

I am a PhD candidate at the University of Washington, advised by Bill Howe. I received my undergraduate degree in Computer Science in 2019 from the University of Michigan.

My research interest lies broadly in reliability of Large Multi-modal Models (LMMs). Currently, I am working on benchmarking and mitigating spurious correlations of LMMs. Recently, I worked on improving robustness to spurious correlations using out-of-distribution examples.

News

• Y. Yang, A. Liu, R. Wolfe, A. Caliskan, B. Howe. Label-Efficient Group Robustness via Out-of-Distribution Concept Curation Accepted to CVPR 2024
• Y. Yang, A. Liu, R. Wolfe, A. Caliskan, B. Howe. Regularizing Model Gradients with Concepts to Improve Robustness to Spurious Correlations Accepted to ICML SCIS 2023
• R. Wolfe, Y. Yang, B. Howe, A. Caliskan. Contrastive Language-Vision AI Models Pretrained on Web-Scraped Multimodal Data Exhibit Sexual Objectification Bias Accepted to FAccT 2023 Preprint https://arxiv.org/abs/2212.11261