Bryan Sangwoo Kim | KAIST Graduate School of AI

About Me

I am a second-year M.S. student at KAIST AI, advised by Prof. Jong Chul Ye. Before that, I received my B.S. degree in Computer Science and Biological Sciences (Double Major) at KAIST in Feb. 2024.

I have a broad interest in generative models that work across various modalities (images, video, text) and their applications. Much of my recent research involves using such multimodal systems to drive tangible solutions for practical, real-world challenges. Please refer to my CV for details.

News

[2025.06] 2 papers (FlowDPS, Free²Guide) are accepted to ICCV 2025.
[2025.02] A paper (VideoGuide) is accepted to CVPR 2025.
[2024.03] I started M.S. at KAIST Graduate School of AI. (Advisor: Prof. Jong Chul Ye)

Publications

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye

ArXiv 2025

PDF Code Project Page 600+ Github Stars

ICCV

FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems

Jeongsol Kim*, Bryan Sangwoo Kim*, Jong Chul Ye (*equal contribution)

IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

PDF Code

ICCV

Free²Guide: Training-Free Text-to-Video Alignment using Image LVLM

Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye

IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

PDF Project Page

CVPR

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide

Dohun Lee*, Bryan Sangwoo Kim*, Geon Yeong Park, Jong Chul Ye (*equal contribution)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

PDF Code Project Page