About Me
I am a M.S. student in the Graduate School of Data Science at Seoul National University (SNU), advised by Prof. Joonseok Lee at the Visual Information Processing (VIP) Lab.
My research focuses on generative modeling, particularly video diffusion and flow models. Recently, I have worked on long video generation, identifying why autoregressive video models drift beyond their training horizon and proposing a training-free method that extends short-horizon models to minute-scale generation. My long-term goal is to leverage the rich representations learned by generative models to build persistent world models that enable interactive, world-consistent, and long-horizon generation.
Research
* indicates equal contribution
-
Jeongwoo Shin*, Youngyoon Choi*, Sangwoo Jo, Hyunmog Kim, Sungjoon Choi, Joonseok Lee, Jaewoong Choi, Jaemoo Choi
arxiv, 2026
-
Youngyoon Choi*, Kihyun Kim*, Jeongwoo Shin, Joonseok Lee
arxiv, 2026
-
MIUA 2026
Wonyoung Jang*, Junho Lee*, Youngyoon Choi, Seunggeun Lee, Joonseok Lee
Medical Image Understanding and Analysis (MIUA), 2026
-
CVPR Workshop 2025
Inseo Lee, Youngyoon Choi, Joonseok Lee
CVPR Workshop on Perception Beyond the Visible Spectrum (CVPRW), 2025
Background
Education
- M.S. in Data Science @ SNU [Mar 2024 – Present] * Expected Feb 2027
- B.A. in Psychology @ SNU [Mar 2019 – Feb 2024] * Graduated Summa Cum Laude
Interdisciplinary Program in Brain, Mind, and Behavior
- Exchange Student @ University of Missouri-Columbia [Sep 2022 – Dec 2022]
Research Experience
Honors & Awards
- 4th stage BK21 Scholarship [Sep 2024 – Dec 2025]
- 3rd Place, Brain-Mind-Behavior Interdisciplinary Research Presentation [Dec 2023]
- Undergraduate Research Funding Program [Jul 2022 – Dec 2022]
- Dean’s List, Academic Scholarship [Dec 2020]