Jaewon Min

I am a Ph.D. student at KAIST AI, advised by Prof. Seungryong Kim. My research interests lie in generative models for vision, with a focus on image/video generation, 3D/4D generation, and geometry-aware visual foundation models. I am also interested in world modeling and real-world applications of generative visual models, particularly in robot perception and manipulation.

CV Scholar GitHub Email LinkedIn

News

Jun 2026

I have started as a visiting scholar at New York University, advised by Prof. Chen Feng.

Jun 2026

Our work, Analysis on UMM transferability, has been accepted to ECCV 2026.

Jan 2026

Our works, TAIR and NoiseRefine, have been accepted to ICLR 2026.

Sep 2025

Our work, HeadHunter, has been accepted to NeurIPS 2025.

Jul 2024

Our work, PAG, has been accepted to ECCV 2024.

Experience

New York University New York, USA

Visiting Scholar

Advisor: Prof. Chen Feng

Jun. 2026 – Present

Publications

* denotes equal contribution. · † denotes corresponding author.

2026

Transferability Between Understanding and Generation in Unified Multimodal Models

Jiwon Kang*, Heeji Yoon*, Jaewoo Jung, Jaewon Min, Minkyeong Jeon, Biyeon Hwang, Sangwon Jung, Seungryong Kim†

ECCV 2026

Project Page arXiv Code

GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion

Yeji Choi, Jinhyeok Choi, Jaewon Min, Minkyung Kwon, Jin Hyeon Kim, Seungryong Kim†

arXiv

Project Page arXiv Code

GARD: Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Jin Hyeon Kim*, Jaeeun Lee*, Clare Kim, Kyoungjin Oh, Paul Hyunbin Cho, Jaewon Min, Yeji Choi, Jihye Park, Hyunhee Park, Minkyu Park, Seungryong Kim†

arXiv

Project Page arXiv Code

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Jaewon Min, Jaeeun Lee, Yeji Choi, Paul Hyunbin Cho, Jin Hyeon Kim, Tae-Young Lee, Jongsik Ahn, Hwayeong Lee, Seonghyun Park, Seungryong Kim†

arXiv

Project Page arXiv Code

Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration

Jin Hyeon Kim, Paul Hyunbin Cho, Claire Kim, Jaewon Min, Jaeeun Lee, Yeji Choi, Seungryong Kim†

arXiv

Project Page arXiv Code

Text-Aware Image Restoration with Diffusion Models

Jaewon Min*, Jin Hyeon Kim*, Paul Hyunbin Cho, Jaeeun Lee, Jihye Park, Minkyu Park, Sangpil Kim†, Hyunhee Park†, Seungryong Kim†

ICLR 2026200+ GitHub stars

Project Page arXiv Code

A Noise is Worth Diffusion Guidance

Donghoon Ahn*, Jiwon Kang*, Sanghyun Lee, Jaewon Min, Wooseok Jang, Minjae Kim, Hyungwon Cho, Sayak Paul, SeonHwa Kim, Eunju Cha†, Kyong Hwan Jin†, Seungryong Kim†

ICLR 2026

Project Page arXiv Code

2025

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models via Attention Head Selection

Donghoon Ahn*, Jiwon Kang*, Sanghyun Lee, Minjae Kim, Jaewon Min, Wooseok Jang, Sangwu Lee, Sayak Paul, Susung Hong, Seungryong Kim†

NeurIPS 2025

Project Page arXiv Code

2024

Self-rectifying diffusion sampling with perturbed-attention guidance

Donghoon Ahn*, Hyoungwon Cho*, Jaewon Min, Wooseok Jang, Jungwoo Kim, SeonHwa Kim, Hyun Hee Park, Kyong Hwan Jin†, Seungryong Kim†

ECCV 2024300+ GitHub stars

Project Page arXiv Code