About
I am a Ph.D. candidate in Electrical and Computer Engineering at Seoul National University, advised by Prof. Bohyung Han ↗. My research focuses on generative modeling for financial markets, including limit-order-book simulation and path signatures, in collaboration with Prof. Kiseop Lee ↗. Previously, I worked on efficient sampling for diffusion models. I was a research intern at Adobe Research ↗ in 2024. I received my B.S. in Statistics and Mathematics from Seoul National University, summa cum laude.
Research Interests
-
Generative modeling for financial markets
- Under review — an LOB message generator whose messages are replayable by construction
- NeurIPS 2026 — a probabilistic reframing of truncated signature inversion that quantifies its inherent ambiguity
-
Efficient sampling for diffusion models
News
- Sep 2026 One paper on replayable limit-order-book message generation is available on arXiv.
- Sep 2026 One paper on probabilistic signature inversion has been accepted to NeurIPS 2026!
- Jun 2026 One paper on probabilistic signature inversion is available on arXiv.
Show older news (5)
- Nov 2025 One paper on real-world image super-resolution is available on arXiv.
- Jul 2025 One paper on training-free video editing is available on arXiv.
- May 2025 A project page for STR-Match, our training-free video editing method, is released.
- Jan 2025 Awarded the Gold Medal at the 30th Samsung Humantech Paper Award for our work on infinite video generation.
- Jan 2025 One paper on diffusion sampling has been accepted to ICLR 2025.
Education
-
Seoul National University Mar 2022 – Exp. Feb 2028
Ph.D. program in Electrical and Computer Engineering
Advisor: Prof. Bohyung Han
-
Seoul National University Mar 2015 – Aug 2021
B.S. in Statistics and Mathematics
Summa Cum Laude, GPA 4.0/4.3
-
Seoul Science High School (SSHS) Mar 2012 – Feb 2015
Experience
-
Adobe Research Research Intern Jun 2024 – Sep 2024
Seattle, USA
-
SNU Computer Vision Lab Research Intern Jun 2021 – Sep 2021
Seoul, Korea
Selected Publications
* equal contribution-
ReLOBGen: Replayable Limit Order Book Message Generation
-
Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures
-
Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions
-
FIFO-Diffusion: Generating Infinite Videos from Text without Training
-
Observation-Guided Diffusion Probabilistic Models
Honors
-
Dean's List 2016, 2020
-
Presidential Science Scholarship 2015 – 2020
-
Bronze medal on high school Korean Mathematical Olympiad 2013
Academic Services
Reviewer
Conference: NeurIPS, AAAI, WACV, CVPR