I am a fourth year PhD student in the Machine Learning Department at Carnegie Mellon University, very fortunate to be advised by Bryan Wilder and Zachary Lipton. I'm broadly interested in algorithmic and statistical questions that arise in complementary decision making, and more recently, in accelerating scientific discovery. Currently, I am visiting UC Berkeley, hosted by Emma Pierson. Before my PhD, I studied physics and computer science at Brown University.
Robust Human-AI Complementarity under Uncertainty
Yewon Byun, Bryan Wilder
International Conference on Machine Learning (ICML), 2026.
Valid Inference with Imperfect Synthetic Data
Yewon Byun, Shantanu Gupta, Zachary C. Lipton, Rachel Leah Childers, Bryan Wilder
Neural Information Processing Systems (NeurIPS), 2025.
Conference on Language Modeling (COLM) Social Simulations Workshop, 2025. (oral)
Expert Routing with Synthetic Data for Domain Incremental Learning
Yewon Byun, Sanket Vaibhav Mehta, Saurabh Garg, Michael Oberst, Emma Strubell, Bryan Wilder, Zachary Lipton
Transactions on Machine Learning Research (TMLR), 2025. (J2C certification, 10% of accepted papers)
Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
Santiago Cortes-Gomez, Carlos Patiño, Yewon Byun, Steven Wu, Eric Horvitz, Bryan Wilder
International Conference on Learning Representations (ICLR), 2025.
Decision-Focused Evaluation of Worst-Case Distribution Shift
Kevin Ren, Yewon Byun, Bryan Wilder
Uncertainty in Artificial Intelligence (UAI), 2024.
Auditing Fairness under Unobserved Confounding
Yewon Byun, Dylan Sam, Michael Oberst, Zachary Lipton, Bryan Wilder
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
Domain Knowledge Priors for Bayesian Neural Networks
Dylan Sam*, Rattana Pukdee*, Daniel Jeong, Yewon Byun, Zico Kolter
International Conference on Machine Learning (ICML) Knowledge and Logical Reasoning, 2023. (oral)
email: yewonb@cs.cmu.edu
twitter: @yewonbyun_
bluesky: @yewonbyun.bsky.social