I am an Assistant Professor of Computer Science and Public Affairs at Princeton University. I'm also excited to be part of Princeton's Center for Information Technology Policy.
I study societal impacts of algorithms, machine learning and AI, and develop and deploy algorithms and technologies that enable data-driven innovations while preserving privacy, fairness and robustness. I also design and perform AI audits.
Reach out by email if you would like to collaborate.
Prospective Ph.D. students should apply to the Ph.D. program in the Department of Computer Science or in the School of Public and International Affairs and indicate an interest in working with me in your statement.
Prospective postdocs should apply to CITP's Fellows Program and reach out to me directly.
Honored to be selected to serve on the United Nations Independent Scientific Panel on AI. I look forward to working with the other panelists for the benefit of all nations.
Looking forward to attending IASEAI 2026, and discussing my group's forthcoming paper, "Measuring Validity and Fairness in LLM-based Resume Screening".
Excited to welcome Blossom Metevier, Max Springer, Hayoung Jung, Bohdan Turbal, and Anderson Lee to my research group!
Congratulations to Zeyu on two papers at NeurIPS 2025: ReliabilityRAG and LiveCodeBench Pro (one of a few benchmarks cited by Gemini 3 Pro in its eval).
Congratulations to Jane on being named a 2026 Siebel Scholar!
Privacy, algorithmic fairness, accountability and transparency are currently at the center of key debates across academia, industry and policy. My research sits at the intersection of these topics and aims to leverage algorithmic thinking in order to provide new solution spaces that allow for a better balance between individual interests, societal goals, and technical innovation.
I develop algorithmic and systems advances that can enable data-driven innovations while preserving individual privacy, defined in the paradigm of differential privacy.
I work to understand how opaque AI systems (including generative AI) may be affecting individuals and society, and to develop algorithmic techniques for mitigating their negative consequences.
Proceedings of 2nd International Association for Safe & Ethical AI (IASEAI 2026)
