Yuhang Chen 陈宇航

I'm currently a third-year undergraduate student (Sep. 2021 - Jun. 2025) at the School of Computer Science at Wuhan University, fortunately supervised by Prof. Mang Ye. I am currently a research intern at University of North Carolina at Chapel Hill, supervised by Prof. Tianlong Chen.

My research interests lie in Trustworthy AI, including Foundation Models (e.g., Multimodal LLMs) and Federated Learning. I am dedicated to building trustworthy Human-AI collaboration systems. Specifically, I aim to develop simple yet elegant, practical, and generalizable algorithms to ensure AI systems' privacy, safety, fairness, and robustness in diverse environments, enabling them to act as expected by humans.

I'm actively seeking PhD positions (enrolling in Fall 2025), research assistant roles, or internship opportunities related to Trustworthy AI. If you're interested in working together, please feel free to email me or contact me via WeChat.

Email  /  CV  /  Google Scholar  /  Github  /  WeChat

Publications

We discovered Parameter Update Consistency in FL under domain skew, addressing parameter update conflict and model aggregation bias to boost performance fairness.

Last Update at June, 27, 2024.
Gratefully attributed to the source code by Dr. Jon Barron.