Daniel P. Jeong

danielje [at] cs.cmu.edu

---

I'm a final-year Ph.D. student in the Machine Learning Department at Carnegie Mellon University, where I am advised by Profs. Zachary C. Lipton and Pradeep Ravikumar. I also work closely with Prof. Michael Oberst at Johns Hopkins University. Before CMU, I earned a B.S. in Computer Science from Columbia University, where I was advised by Profs. Itsik Pe'er, David A. Knowles, David M. Blei, and Kriste Krstovski.

My research focuses on making foundation models reliable for healthcare. I develop methods for applying and adapting these models, and study how evaluation choices shape our conclusions about them. These choices include whether model comparisons account for prompt sensitivity and statistical uncertainty, how results are aggregated across benchmark tasks, and which reference outputs are treated as ground truth. My work spans medically specialized large language and vision-language models, tabular foundation models, and learning from implicit clinician feedback (e.g., edits to LLM outputs) in real-world deployments.

Outside of CMU, I am a part-time Member of Technical Staff (Intern) at Abridge AI and serve as a Managing Editor for the Journal of Machine Learning Research (JMLR). I also spent wonderful summers interning with the Real-World Evidence Group at Microsoft Research (Health Futures) and the Machine Learning Groups (398J, 393K) at NASA Jet Propulsion Laboratory (JPL).