M.S. Researcher · KAIST CVLAB

Seonghu Jeon.

I'm interested in how machines come to understand and represent the physical world, and how they can build on that to generate and act in it. I'm a first-year M.S. researcher at KAIST CVLAB. My research so far has centered on multi-view diffusion and 4D generation, and I'm now starting to explore 3D foundation models for robotics. Reach me at seonghu.jeon@kaist.ac.kr.

Curriculum Vitae Google Scholar GitHub
Seonghu Jeon
— 01

News & notes

most recent first
2026.03 Joined KAIST CVLAB as an M.S. student under Prof. Seungryong Kim.
2026.02 CAMEO accepted to CVPR 2026 — correspondence-attention alignment for multi-view diffusion.
2025.07 ReMoTE accepted to ITC-CSCC as oral presentation.
2025.02 Graduated from Korea University, B.S. in Computer Science & Engineering, with Great Honors.
— 02

Selected publications

04 entries
— 03

Focus

three open threads
— 01 3D / 4D vision

Reconstructing static and dynamic scenes from sparse views — how foundation models trained on geometry transfer to view-synthesis without optimization.

— 02 Generative models

Diffusion and flow matching with structured conditioning — correspondence, geometry, motion. Architecture work and better source distributions.

— 03 Robotics

The destination. If a robot can imagine a scene's geometry forward in time, it can plan in it — and that loop closes through generative models.

— 04

Experience

KAIST CVLAB
M.S. Student
Advised by Prof. Seungryong Kim. Multi-view diffusion, geometric foundation models, 4D scene generation.
2026 — now
KAIST CVLAB
Research Intern
Pre-graduate research on motion transfer and correspondence-attention. Multiple co-authored papers from this period.
2023 — 2026
Korea University
B.S., Computer Science & Engineering
Graduated with Great Honors (4.46 / 4.50). Coursework in vision, graphics, and deep learning.
2022 — 2026