I’m an Assistant Professor of Computer Science at Johns Hopkins, and a visiting scientist (part-time) at Abridge. Previously, I was a postdoc at Carnegie Mellon University with Zack Lipton, and obtained my PhD in Computer Science at MIT with David Sontag. You can find more information on my background in my CV.
Research Overview
My group develops methods for principled and efficient evaluation and monitoring of AI systems, with an emphasis on applications in healthcare. In the era of large language models (LLMs) and vision-language models (VLMs), it has never been easier to develop an initial prototype of an AI tool. However, turning a demo into a robust and reliable AI system still requires enormous effort, both pre- and post-deployment: From collecting expensive but essential ground-truth data (e.g., expert feedback), to rigorously evaluating the impact of these tools on downstream clinical outcomes. To develop methods that address these challenges, my group draws on a broad methodological toolkit spanning statistics, causal inference, and machine learning, and collaborates closely with clinical researchers in medicine, nursing, and public health.
Research Group
I am recruiting PhD students for Fall 2026. If you are interested in working with me as a PhD student or postdoc, please see this page for more information
Current Students
- Erik Skalnes (PhD Student)
- Jacob Chen (PhD Student, supervised by Ilya Shpitser)
- Jiashuo Zhang (MS Student)
- Jonathan Zhang (Undergraduate Researcher)
- Daniel Yao (Undergraduate Researcher)
Collaborators / Former Students
- Daniel Jeong (PhD Student at CMU)
- Yewon (Emily) Byun (PhD Student at CMU)
- Andrew Wang (Undergraduate at CMU, now PhD student at Brown)
- Helen Zhou (MEng at MIT, then PhD at CMU, now at Apple)
- Christina X. Ji (PhD Student at MIT, now at Genesis Therapeutics)
- Justin Lim (MEng Student at MIT, now at Citadel)
- Sooraj Boominathan (MEng at MIT, now at Two Sigma)
Selected publications (Full List)
No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
Pranav Mani, Peng Xu, Zachary C. Lipton, Michael Oberst
Preprint, 2025
[paper]
Just Trial Once: Ongoing Causal Validation of Machine Learning Models
Jacob M. Chen, Michael Oberst
Conference on Uncertainty in Artificial Intelligence (UAI), 2025
Oral Presentation (3% of submissions, 9% of accepted papers)
[paper], [poster]
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
Daniel P. Jeong, Saurabh Garg, Zachary C. Lipton, Michael Oberst
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
[paper], [extended version]
Auditing Fairness under Unobserved Confounding
Emily Byun, Dylan Sam, Michael Oberst, Zachary Lipton, Bryan Wilder
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
[paper]
Regularizing towards Causal Invariance: Linear Models with Proxies
Michael Oberst, Nikolaj Thams, Jonas Peters, David Sontag
International Conference on Machine Learning (ICML), 2021
[paper], [video], [slides], [poster], [code]