Ph.D. Student @ Seoul National University

Jeongwoo Shin

Hi! I'm a 3rd year Ph.D. student at the Graduate School of Data Science, Seoul National University, where I work in the VIP Lab advised by Prof. Joonseok Lee. I also completed my M.S. in Data Science in the same lab.

My research focuses on generative modeling, particularly diffusion-, flow-, and control-based image and video generation. Recently, I have been working on long video generation and one-step distillation.

I am actively seeking internship opportunities.

Jeongwoo Shin
Contact: swswss [at] snu.ac.kr
Follow: Google Scholar | GitHub

Updates

04/2026
2 papers are accepted to ICML 2026.
  • ASBM: Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching.
  • Residual Latent Flow: Equivariant Latent Alignment via Flow Matching under Group Symmetries.
06/2025
1 paper is accepted to ICCV 2025.
  • LDMAE: Latent Diffusion Models with Masked AutoEncoders.
09/2024
1 paper is accepted to NeurIPS 2024.
  • Self-MAE: Self-Guided Masked Autoencoder.
03/2024
Started my Ph.D. at VIP Lab, SNU.

Selected Publications

(∗ Equal contribution, † Equal advising)

Efficient Adjoint Matching for Fine-tuning Diffusion Models
Jeongwoo Shin∗, Dongsoo Shin∗, Yuchen Zhu, Wei Guo, Yongxin Chen, Joonseok Lee†, Jaewoong Choi†, Jaemoo Choi†
Preprint
arxiv
Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
Jeongwoo Shin, Jinhwan Sul, Joonseok Lee†, Jaewoong Choi†, Jaemoo Choi†
ICML 2026
arxiv
Equivariant Latent Alignment via Flow Matching under Group Symmetries
Sunghyun Kim∗, Jaehoon Hahm∗, Jeongwoo Shin, Joonseok Lee†
ICML 2026
arxiv
Latent Diffusion Models with Masked AutoEncoders
Junho Lee∗, Jeongwoo Shin∗, Hyungwook Choi, Joonseok Lee†
ICCV 2025
arxiv
Self-Guided Masked Autoencoder
Jeongwoo Shin, Inseo Lee, Junho Lee, Joonseok Lee†
NeurIPS 2024
arxiv
Diverse Motion Customization via Control-based Dynamic Optimization
Youngyoon Choi∗, Kihyun Kim∗, Jeongwoo Shin† (co-advising), Joonseok Lee†
Preprint
No More Hit-and-Hope: Optimal Initial Noise Forging via Noise Shuffling
Suho Ryu, Jeongwoo Shin, Joonseok Lee†
Preprint
Optimal Crystal Flow for Fast and Reliable Crystal Generation
Seunghoon Yi, Youngwoo Cho, Jaehoon Hahm, Jeongwoo Shin, Soo Kyung Kim†, Jaegul Choo†, Joonseok Lee†, Hongkee Yoon†
Preprint