Jaeseok Jeong (Chung)

Ph.D. Student, ViLab (Visual Intelligence Lab), Yonsei University Research Advisor: Prof. Yongjung Uh

Co-founding technical staff member, Familiar, Inc.

Email: jete_jeong@yonsei.ac.kr (Personal, Research)

jaeseok@thefamiliarlab.com (Bussiness)

CV / Google Scholar / Youtube Channel / Semantic Scholar / GitHub / LinkedIn

About

As a Ph.D. student

I am currently a Ph.D. student at the Dept. of Artificial Intelligence, Yonsei University. My research interests are generative AI especially image/video generation and editing. I have developed diffusion-based image editing methods. Recently, my focus on research has been on extending video generation and control including talking head and world model.

One of my open source projects, which has accumulated a total of +750 stars on GitHub, involves contributions to "ComfyUI" and other repositories. This project is based on my paper "Visual Style Prompting," reflecting my contributions and passion in the field.

I also run a YouTube channel called Welch Labs Korea, where I share fun and engaging content about AI, science, and math.

Previously, I completed my internship at NAVER AI Lab(2023 Sep- 2024 Feb), advised by Yunjey Choi, Junho Kim and other great team members.

As a Co-founder

I co-founded CINELINGO with Mingi Kwon, a video translation startup, and am now continuing the journey as a co-founding technical staff member at Familiar, Inc., alongside Andrew and Xu.

Papers

🧡 [2026] "JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching" was accepted at ECCV 2026.

🧡 [2025] "Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers" was accepted at ICLR2026.
❤️ [2025] "StyleKeeper: Prevent content leakage via a negative visual query guidance" was accepted at ICCV 2025!
❤️ [2025] "TTS-CtrlNet: Time-varying emotion-aligned text-to-speech generation with ControlNet" was arXived.
🧡 [2025] "Balanced Conic Rectified Flow" was accepted at NeurIPS 2025.
🧡 [2025] "TCFG: Tangential Damping Classifier-free Guidance" was accepted in CVPR2025!
❤️ [2024] "Visual Style Prompting" was accepted in CVPR2024 Workshop (Best Paper Award + Oral presentation)!
❤️ [2024] "Training-free Style Transfer Emerges from h-space in Diffusion models" was accepted in WACV2024!
🧡 [2023] "Diffusion Models already have a Semantic Latent Space" was accepted at ICLR 2023 as a notable-top-25%!

❤️ : First author or co-first author 🧡 : My favorite co-working papers!

Research Experience

Mar 2022 - Present, Graduate Student Researcher, ViLab (Visual Intelligence Lab), Research Advisor: Prof. Yongjung Uh
Sep 2023 - Fed 2024, NAVER Cloud AI Lab (full‐time internship), advised by Yunjey Choi, Junho Kim and other great team members. .

Awards

Best Paper Award in CVPR2024 AI4CC Workshop ($1500)
Gold prize in Samsung Humantech Paper Award, 2022 (1st prize in the category ‐ Computer Science, $8000 (Authors) + $4000 (Corresponding Author)

Academic reviewing

Reveiwer in Neurips, CVPR and Siggraph Asia

Page updated

Report abuse