Jung Yi

Education

Korea Advanced Institute of Science and Technology (KAIST)
M.S in Artificial Intelligence, advised by Seungryong Kim.

Spring 2025 - Now

Yonsei University
B.S. in Electrical & Electronic Engineering.

Fall 2024

Reactor

Research Scientist Intern Sep 2026 - Now

Project: Efficient Inference & Infrastructure for Video World Models. San Francisco, California

Kakao

Research Intern Mar 2026 - Jun 2026

Project: Real-time Talking Avatar with Autoregressive Video Diffusion. Pangyo, South Korea

J. Yi, M. Kim, P. Cho, W. Jang, S. Yun, S. Kim

Efficient World Memory by combining World Retrieval and World Compression.

arxiv, 2026

J. Yi, W. Jang, P. Cho, J. Nam, H. Yoon, S. Kim

Long-video generation by combining Deep Sink and Participative Compression.

ICML, 2026

P. Cho*, J. Jang*, S. Lee, J. Lee, S. Jin, H. Shin, J. Yi, Y. Park, C. Park, S. Kim

Real-time lip synchronization using few-step autoregressive diffusion.

arxiv, 2026

S. Son, H. An, C. Kim, H. Ko, J. Nam, D. Chung, S. Jin, J. Yi, J. Min, J. Hur, S. Kim

Video Diffusion Model for Point Tracking.

arxiv, 2025

J. Koo*, I. Kim*, M. Kim, J. Park, S. Park, J. Kim, J. Yi, S. Cho, S. Kim

Multi-view point tracker that uses camera and cross-view attention.

CVPR, 2026

I. Kim*, S. Cho*, J. Huang, J. Yi, J. Lee, S. Kim

Feature backbone specifically designed for point tracking with built-in temporal awareness.

CVPR, 2025

Y. Chang, Y. Kim, S. Seo, J. Yi, N. Kwak

Outdoor scene relighting for Neural Radiance Fields (NeRF).

WACV, 2024