🏔️ Jaehoon Hahm

I’m a first-year Ph.D. student in Physics at the University of Illinois, Urbana-Champaign, advised by Bryan Clark and Ge Liu. Previously, I completed my M.S. at the Graduate School of Data Science, Seoul National University, advised by Joonseok Lee. Before that, I did my B.S. at Physics, Seoul National University.

I’m interested in ML + Quantum, Geometric Deep Learning, and Generative Modeling. I'm currently working on Shadow Tomography, Riemannian Geometry + Diffusion/Flow based models, Neural QEC, and Neural Back Flow/Quantum States.

Preprints

Shadow Flow Matching for Learning Quantum States

Jaehoon Hahm, Bryan Clark

Preprint, 2025

We introduce Shadow Flow Matching, a novel generative framework for quantum state learning that combines classical shadow representations with Riemannian flow matching.

Paper

Publications

SummDiff: Generative Modeling of Video Summarization with Diffusion

Kwanseok Kim, Jaehoon Hahm, Sumin Kim, Jinhwan Sul, Byung-Hak Kim, Joonseok Lee

20th IEEE/CVF International Conference on Computer Vision (ICCV), 2025

We approach a video summarization problem using generative modeling framework, motivated from the diverse and subjective characteristic innate to the summarization task.

Paper

Generative Modeling of Quantum Distribution with Functional Flow Matching

Jaehoon Hahm, Tak Hur, Joonseok Lee, Daniel K. Park

8th International Conference on Quantum Techniques in Machine Learning (QTML), 2024

We use Functional Flow Matching to learn the distribution of quantum states via Wigner function mapping.

Paper

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Jaehoon Hahm, Junho Lee, Sunghyun Kim, Joonseok Lee

41st International Conference on Machine Learning (ICML), 2024

We introduce a method to leverage isometric representation learning, motivated from Riemannian geometry, to obtain a smoother and disentangled latent space for diffusion mdoels.

Paper Code