Yiqun T. Chen

AI for Statistics and Statistics for AI.

prof_pic.jpg

I am Yiqun Chen (pronunciation here), a data science researcher at the interface of modern AI, statistical insights, and scientific modeling. I worked on selective inference and evaluation frameworks and creative ways of leveraging large language models for scientific data analysis and discovery. I am an Assistant Professor of Biostatistics and Computer Science (by courtesy) at Johns Hopkins University, with affiliations at the Data Science & AI Institute and the Malone Center for Engineering in Healthcare.

I was a Data Science Postdoctoral Fellow at Stanford University with Professor James Zou, where I led projects on generative AI for single-cell genomics and responsible AI benchmarks. I completed my PhD in Biostatistics under the guidance of Professor Daniela Witten at the University of Washington, developing selective inference tools for data-driven discovery. My collaborations span dermatology, social networks and epidemiology, human-computer interaction, and microbiome science. Before graduate school, I earned undergraduate degrees with high distinction from the University of California, Berkeley.

Over the years, I have worked with teams at Amazon Search, Waymo LLC, Meta, and a stealth startup on AI agents for ads optimization.

I am always excited to explore collaboration opportunities; the best way to reach me is yiqun.t.chen@gmail.com.

recent news

  • We found that LLMs are human-level at summarizing methods from full texts, but their errors correlated strongly with human errors; joint work with Cathy Zhang (student collaborator), Trang Nguyen, and Liz Stuart: Large Language Models for Full-Text Methods Assessment: A Case Study on Mediation Analysis (arXiv:2510.10762).
  • We are hiring Research Assistants for AI in forensics! See the position details. This is supported by our new NIST grant (MPI with Michael Rosenblum) on AI for forensics.
  • Consider applying to Biostatistics’ departmental postdoctoral fellowship on DS/AI: https://apply.interfolio.com/174430!
  • New preprint: LAVA introduces language model assisted verbal autopsy pipelines for global health partners.
  • New preprint: With my student collaborator Can Wang, we presented new work on evaluating LLMs for evidence-based clinical Q&A (arXiv:2509.10843)!
  • GenePT, our study on using ChatGPT-derived embeddings for single-cell analysis, appeared in Nature Biomedical Engineering.

🎉

I have been fortunate to have received several awards and honors, including research supports from Google (PI), NIST (MPI), and NIH (co-I), a Cornell Young Researchers Workshop in 2023, the Rising Stars in Data Science in 2022, the Best Paper Honorable Mention at CHI 2023, the Thomas R. Fleming Excellence in Biostatistics Award, the Student Research Paper Award at NESS 2022, the Best Award at WNAR 2021, the Young Investigator Award at CROI 2020, and the Outstanding Teaching Assistant Award from the School of Public Health at the University of Washington.