Hye Won Chung

Hye Won Chung is an Associate Professor in the School of Electrical Engineering at KAIST, jointly affiliated with the School of Computing and the Graduate School of AI. His research interests include data science, information theory, statistical inference, machine learning, and quantum information. He completed his Ph.D. in Electrical Engineering and Computer Science at MIT in 2014 and holds a B.S. (with summa cum laude) from KAIST. His work focuses on developing theoretical frameworks and efficient algorithms for data science and machine learning. He has published extensively in top conferences and journals, including ICLR, NeurIPS, ICML, and IEEE Transactions. Chung is also actively involved in academic leadership roles, such as serving as an area chair for NeurIPS 2026 and ICML 2026.

Hye Won Chung is an Associate Professor at KAIST, specializing in Information Theory, Machine Learning, Mathematical Data Science, and Statistical Inference. Her research focuses on developing robust methods for data valuation, test-time adaptation, and generative adversarial networks. She explores techniques such as self-training, dataset distillation, and convex relaxation for clustering and detection problems. Chung's work also addresses fundamental limits in data acquisition and communication systems, including optical channels and quantum channel coding. Her contributions span theoretical and applied aspects of machine learning and information theory, emphasizing efficiency and robustness in complex data environments.