Xiangyu Qi
Graduate Student
Xiangyu Qi is a Ph.D. candidate at Princeton University. His work focuses on examining safety and security vulnerabilities in AI systems and developing approaches to mitigate the risks these vulnerabilities may pose in practical applications. His work has been selected for oral presentations at multiple prestigious conferences such as CVPR, AAAI, and ICLR, and has also been featured by mainstream media outlets, including The New York Times. His research is supported by the Princeton Gordon Y.S. Wu Fellowship and an OpenAI Superalignment Grant.