chufan2 [at] illinois.edu
University of Illinois Urbana-Champaign
Thomas M. Siebel Center for Computer Science
201 North Goodwin Avenue
Urbana, IL 61801, USA
Hello! I am a Research Scientist Google Health AI. My focus area is primarily LLMs for Healthcare.
I am also broadly interested in LLM training, domain adapation, and synthetic data generation.
My PhD is/was at University of Illinois Urbana-Champaign advised by
Professor Jimeng Sun.
I did my Masters advised by
Professor Artur Dubrawski
at Carnegie Mellon University as a part of
AutonLab (Masters thesis: Addressing Time-series Signal Quality in Healthcare Data).
Internship Experiences
-
Research Intern @ Google Health
Mountain View, CA, Summer 2025
-
NLP Research Intern @ Optum (UnitedHealth Group)
Remote, Summer 2024
Clinical Note Entity Recognition
Advised by Sanjit Batra and Robert Tillman
-
Research Intern @ Medidata Solutions (Dassault Systèmes)
New York, NY, Summer 2023
Synthetic clinical trial data generation
Advised by Mandis Beigi and Afrah Shafquat
Selected Work
* indicates equal contributionPeer-reviewed
- A. Sellergren*, C. Gao*, ... D. Golden "Medgemma 1.5 technical report," 2026
- C. Gao*, J. Pradeepkumar*, T. Das*, S. Thati, J. Sun "A large-scale database for clinical trial outcomes and features," in Nature Health, 2026
- C. Gao, X. Wang*, J. Sun* "TTM-RE: Memory-Augmented Document-Level Relation Extraction," in ACL, 2024
- Z. Wang*, C. Gao*, C. Xiao, J. Sun, "MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement," in IJCAI, 2024
- Hanyin, W., C. Gao, C. Dantona, B. Hull, J. Sun, "DRG-LLaMA: tuning LLaMA model to predict diagnosis related group for hospitalized patient," in Nature Digitial Medicine, 2024
- C. Gao, N. Gisolfi, and A. Dubrawski, "Signal quality auditing for time-series data" in AAAI Fall Symposium: Artificial Intelligence for Predictive Maintenance, 2022
- C. Gao, "Addressing time-series signal quality in healthcare data," Master's thesis, Carnegie Mellon University, 2022
- C. Gao*, M. Goswami*, J. Chen, and A. Dubrawski, "Classifying unstructured clinical notes via automatic weak supervision," in Machine Learning for Healthcare, 2022
- C. Gao, S. Clark, J. Furst, and D. Raicu, "Augmenting LIDC dataset using 3D generative adversarial networks to improve lung nodule detection." In Medical Imaging 2019: Computer-Aided Diagnosis, vol. 10950, pp. 398-407. SPIE, 2019.
Miscellaneous
- Google Research blog post on MedGemma 1.5!
- "Alumni Spotlight: Chufan Gao," The Journal of Purdue Undergraduate Research: Vol. 13, Article 52.
- Fractal tree generation: I limited it to 50 trees for crashing reasons. Much thanks to Eura Shin (PhD Student @ Harvard!) for the base tree generation code!