Advisor: Tian Li
I’m currently a first year PhD student at University of Chicago. Before that, I worked as a machine learning engineer at EV.com and CarAI.com. Previouly, I co-founded a startup company: Hemlig AI. Hemlig aims to study the cutting edge topics in trustworthy machine learning and implement these techniques into our products. I received my Master’s degree from the Department of Electrical and Computer Engineering in the University of Toronto and received my bachelor degree from Department of CSE in Shanghai Jiao Tong University. During my undergraduate studies, I was a research intern at John Hopcroft Center for Computer Science, advised by Liyao Xiang and Xinbing Wang. Previously, I took a research fellowship at Max Planck Society, advised by Yiting Xia and Binghang Yuan. I speak Mandarin, English, and French.
My research focuses on privacy-preserving machine learning in distributed systems. My research interest includes data privacy, system security, Trustworthy ML, and decentralized trust technologies. I’m interested in solving problems with real-world use cases, facilitating full-stack solutions for data privacy and system security in modern decentralized and AI oriented ecosystem. Here are some examples: How can we realize privacy-preserving split learning and have as much as possible tradeoff for privacy, accuracy and efficiency? How can we address the data and device heterogeneity towards robust Federated Learning, without compromising the privacy requirements? How can we theoretically explain privacy concerns in foundation models?
