Mingi Kwon
Mingi Kwon
Embedded Files
Co-founder & CTO, FamiliarLab
Ph.D. in Artificial Intelligence, Yonsei University
Running of VeritasiumKorean (300k+ subscribers), 3Blue1Brown한국어 (100k+ subscribers)
Email: mingi@thefamiliarlab.com (Bussiness) kwonmingi@yonsei.ac.kr (Research)
CV / Google Scholar / Semantic Scholar / GitHub / LinkedIn / YouTube1 / YouTube2
About
About
As a Co-founder
I am currently the Co-founder and CTO of FamiliarLab, which I started with Andrew after finishing my Ph.D.
Before FamiliarLab, I spent about a year building CineLingo with Jaeseok Jeong, while doing my Ph.D. in Korea. There, I worked on video translation research and turned it into a real business. Although research was still my main focus, we found customers, generated revenue, joined Korea’s Early-Stage Startup Package, and were featured in Korean media.
After graduating, I wanted to take what I had been building to a much larger, global market. That led me to start FamiliarLab with Andrew, backed by Y Combinator. Now, we are building FamiliarLab to break language barriers for video and communication around the world.
As a Researcher
I received my Ph.D. in Artificial Intelligence from Yonsei University in August 2026. My Ph.D. research was on multimodal generation. Research Advisor: Prof. Yongjung Uh
I have worked on image, video, and audio generation, and recently I have also become interested in LLMs and multimodal models. In general, I enjoy understanding how generative models work and finding ways to make them better.
Previously, I completed my internship at Adobe Research (2023 May-Dec), advised by SeoungWug Oh, JoonYoung Lee, Yang Zhou, Difan Liu, Feng Liu, and other great team members.
As a YouTuber
I am currently running YouTube channels called Veritasium Korean and 3Blue1Brown Korean, which focus on math and science stories. Since 2021, I have been officially collaborating with the original Veritasium channel. Currently, the channel has nearly 300k and 100k subscribers.
Papers
Papers
🧡❤️ [2026] "FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation" is arxived.
❤️ [2026] "JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching" was accepted in ECCV2026!
🧡 [2026] "Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers" was accepted in ICLR2026!
🧡 [2025] "Balanced Conic Rectified Flow" was accepted in Neurips2025!
🧡 [2025] "TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with controlnet" will be arxived soon.
❤️ [2025] "TCFG: Tangential Damping Classifier-free Guidance" was accepted in CVPR2025!
❤️ [2024] "Harnessing Text-to-Image Models for Video Generation" was accepted in ECCV2024!
🧡 [2024] "Motion Customization Video Diffusion Model" was accepted in ECCV2024!
❤️ [2024] "Attribute Based Interpretable Evaluation Metrics for Generative Models" was accepted in ICML2024!
🧡 [2024] "Plug-and-Play Diffusion Distillation" was accepted in CVPR2024!
❤️ [2024] "Training-free Style Transfer Emerges from h-space in Diffusion models" was accepted in WACV2024!
❤️ [2023] "Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry" was accepted in Neurips2023!
❤️ [2023] "Unsupervised Discovery of Semantic Latent Directions in Diffusion Models" was arxived.
❤️ [2023] "Diffusion Models already have a Semantic Latent Space" was accepted in ICLR2023 as a notable-top-25%!
🧡 [2022] "FurryGAN: High Quality Foreground-aware Image Synthesis" was accepted in ECCV2022!
❤️ : First author or co-first author 🧡 : My favorite co-working papers!
Research Experience
Research Experience
Mar 2021 - August 2026, Graduate Student Researcher, ViLab (Visual Intelligence Lab), Research Advisor: Prof. Yongjung Uh
June 2025 - September 2025, research internship, working with Yi-Hsuan Tsai, Yumin Suh, and other great team members.
May 2023 - Dec 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.
Awards
Awards
Won the Intra-University Merit Paper Award
Gold prize in Samsung Humantech Paper Award, 2022 (1st prize in the category ‐ Computer Science, $8000 (Authors) + $4000 (Corresponding Author)
Won the Best Graduation Project Award across my entire undergraduate university - Received the University President's Award
Received the Dean's Award from the College of Engineering at Korea University
Gold Medal at the National Research Council of Thailand (Patent Number: 4‐2019‐084383‐5)
Patents
Patents
P12986-US: MOTION CUSTOMIZATION FOR DIGITAL VIDEOS
8828-361-NP1_P12631-US: VIDEO GENERATION USING FRAME-WISE TOKEN EMBEDDINGS
Academic Services
Academic Services
Reviewer in CVPR, ICLR, Neurips, ICML, ECCV, AAAI, and some journals
Page updated
Google Sites
Report abuse