Scholar
Mingi Kwon
Google Scholar ID: W8vK8BwAAAAJ
Yonsei University
Citations & Impact
Citations
574
H-index
7
i10-index
6
Publications
16
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Papers: [2025] 'Balanced Conic Rectified Flow' accepted in Neurips2025; [2025] 'TCFG: Tangential Damping Classifier-free Guidance' accepted in CVPR2025; [2024] 'Harnessing Text-to-Image Models for Video Generation' accepted in ECCV2024; [2024] 'Attribute Based Interpretable Evaluation Metrics for Generative Models' accepted in ICML2024; [2024] 'Plug-and-Play Diffusion Distillation' accepted in CVPR2024; [2024] 'Training-free Style Transfer Emerges from h-space in Diffusion models' accepted in WACV2024; [2023] 'Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry' accepted in Neurips2023; [2023] 'Diffusion Models already have a Semantic Latent Space' accepted in ICLR2023 as a notable-top-25%; [2022] 'FurryGAN: High Quality Foreground-aware Image Synthesis' accepted in ECCV2022. Awards: Gold prize in Samsung Humantech Paper Award, 2022 (1st prize in the category).
Research Experience
- March 2021 - Present, Graduate Student Researcher, ViLab; June 2025 - September 2025, Atmanity research internship, working with Yi-Hsuan Tsai, Yumin Suh, and other great team members; May 2023 - December 2023, Adobe summer internship (full-time internship extended), advised by SeoungWug Oh, JoonYoung Lee, Yang Zhou, Difan Liu, Feng Liu, and other great team members.
Education
- Ph.D. Student, Department of Artificial Intelligence, College of Computing, Yonsei University, Research Advisor: Prof. Yongjung Uh
Background
- Research interests: generative AI, especially image/video generation and editing. Developed diffusion-based image editing methods. Recent focus on extending video generation and editing, including talking head problems.
Miscellany
- As a YouTuber, running Veritasium Korean (280k+ subscribers) and 3Blue1Brown Korean (100k+ subscribers) channels, focusing on math and science stories. As Co-founder/CEO of CineLingo, providing AI services for translating videos.
