About Me

I am a Ph.D. candidate at KAIST AI (Kim Jaechul Graduate School of AI), advised by Prof. Jong Chul Ye at the Bioimaging, Signal Processing and Learning Lab (BiSPL). I received my B.S. in Computer Science and Bio and Brain Engineering (double major) from KAIST, graduating Summa Cum Laude.

My research explores diffusion and flow models for controllable visual generation, with a focus on inverse problems and consistency-preserving image/video generation and editing.

• Diffusion & Flow Models
• Controllable Visual Generation
• Video Generation & Editing
• Inverse Problems

News

• Nov. 2026 "MoviEdit: Long-form Multi-Shot Video Editing Made Easy" preprint released on arXiv.
• Oct. 2026 "Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation" accepted to WACV 2027.
• Jul. 2026 "InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem" accepted to ECCV 2026.
• Apr. 2026 Started research internship at Adobe Research, London.
• Feb. 2026 "PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment" accepted to CVPR 2026.
• Aug. 2025 Started research internship at NAVER Cloud (Generation Research, AI Lab).
• Jul. 2025 "Reangle-A-Video: 4D Video Generation as Video-to-Video Translation" accepted to ICCV 2025.
• Sep. 2024 Started Ph.D. at KAIST AI.
• Jan. 2024 "LLM-CXR", "Don't Play Favorites: Minority Guidance for Diffusion Models", and "Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems" accepted to ICLR 2024.
• Jul. 2023 "Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models" accepted to ICCV 2023.
• Aug. 2022 Started M.S. at KAIST AI.

Industry Experience

Publications

P: preprint, C: conference · * denotes equal contribution

[P1] MoviEdit: Long-form Multi-Shot Video Editing Made Easy

Suhyeon Lee*, Zhengang Li, Soo Ye Kim, Peihao Zhu, Jong Chul Ye, Chun-Hao Paul Huang, Duygu Ceylan, Yan Kang, Hyeonho Jeong*

arXiv preprint (2026).

arXiv PDF Project Benchmark

[C8] Single-Step Bidirectional Unpaired Image Translation Using Implicit Bridge Consistency Distillation

Suhyeon Lee*, Kwanyoung Kim*, Jong Chul Ye

WACV 2027.

arXiv PDF

[C7] InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

Yeobin Hong*, Suhyeon Lee*, Hyungjin Chung, Jong Chul Ye

ECCV 2026.

arXiv PDF Code

[C6] Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment

Suhyeon Lee, Jong Chul Ye

CVPR 2026.

arXiv PDF Code

[C5] Reangle-A-Video: 4D Video Generation as Video-to-Video Translation

Hyeonho Jeong*, Suhyeon Lee*, Jong Chul Ye

ICCV 2025.

arXiv PDF Code

[C4] LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation

Suhyeon Lee*, Won Jun Kim*, Jinho Chang, Jong Chul Ye

ICLR 2024.

arXiv PDF Code

[C3] Don't Play Favorites: Minority Guidance for Diffusion Models

Soobin Um, Suhyeon Lee, Jong Chul Ye

ICLR 2024.

arXiv PDF Code

[C2] Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

Hyungjin Chung, Suhyeon Lee, Jong Chul Ye

ICLR 2024.

arXiv PDF Code

[C1] Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

Suhyeon Lee*, Hyungjin Chung*, Minyoung Park, Jonghyuk Park, Wi-Sun Ryu, Jong Chul Ye

ICCV 2023.

arXiv PDF Code