I am a Ph.D. student at Visual AI Lab at Yonsei University, advised by Prof. Hae-Gon Jeon. Previously, I received an M.S. in AI Convergence and a B.S. in EECS from GIST. I believe that foundation generative models encode rich priors over images and videos, and my research focuses on leveraging these priors more effectively. In particular, I aim to 1️⃣design guidance and scaling strategies to improve generation quality, and 2️⃣adapt these priors to downstream computer vision tasks.
* indicates equal contribution.
[P1] Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
Wooseok Jeon*, Seungho Park*, Seunghyun Shin, Sangeyl Lee, Hyeonho Jeong, Hae-Gon Jeon
arXiv preprint
[C2] TriMotion: Modality-Agnostic Camera Control for Video Generation
Seunghyun Shin, Jifei Song, Wooseok Jeon, Hae-Gon Jeon, Jiankang Deng
European Conference on Computer Vision (ECCV), 2026
[C1] Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening
Wooseok Jeon, Seunghyun Shin, Dongmin Shin, Hae-Gon Jeon
International Conference on Learning Representations (ICLR), 2026
[P1] Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
Wooseok Jeon*, Seungho Park*, Seunghyun Shin, Sangeyl Lee, Hyeonho Jeong, Hae-Gon Jeon
[C2] TriMotion: Modality-Agnostic Camera Control for Video Generation
Seunghyun Shin, Jifei Song, Wooseok Jeon, Hae-Gon Jeon, Jiankang Deng
[C1] Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening
Wooseok Jeon, Seunghyun Shin, Dongmin Shin, Hae-Gon Jeon
Yonsei University
Ph.D. in Artificial Intelligence Mar. 2026 - Present
Gwangju Institute of Science and Technology (GIST)
M.S. in AI Convergence Sep. 2024 - Feb. 2026
B.S. in Electrical Engineering and Computer Science Mar. 2019 - Aug. 2024