Bryan Sangwoo Kim | KAIST Graduate School of AI

About Me

Hi! I’m a second-year M.S. student at KAIST AI, advised by Prof. Jong Chul Ye. I earned my B.S. in Computer Science and Biological Sciences (Double Major) from 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.

I’m greatly interested in research opportunities for 2026. Please feel free to contact me!

News

[2025.09] A paper (Chain-of-Zoom) is accepted to NeurIPS 2025 as a Spotlight paper.
[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

NeurIPS

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

Bryan Sangwoo Kim, Jeongsol Kim, Jong Chul Ye

NeurIPS 2025

Spotlight Presentation (688/21575=3.19%)

PDF Code Project Page

ICCV

FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems

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

ICCV 2025

PDF Code

ICCV

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

Jaemin Kim, Bryan Sangwoo Kim, Jong Chul Ye

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)

CVPR 2025

PDF Code Project Page

Preprints

Align Your Query: Representation Alignment for Multimodality Medical Object Detection

Ara Seo*, Bryan Sangwoo Kim*, Hyungjin Chung, Jong Chul Ye (*equal contribution)

Under Review (Submitted to arXiv in Oct. 2025)

PDF Project Page

Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck

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

Under Review (Submitted to arXiv in Oct. 2025)

PDF

Patents

Method for Image Super-Resolution and Apparatus
Jong Chul Ye, Bryan Sangwoo Kim , Jeongsol Kim
Korean Patent, Filed, No. 10-2025-0112631, 2025
US Patent Application in Process

Awards and Honors

KAIST Graduate Scholarship, KAIST, 2024-2025
KAIST Department Honors Scholarship (Department Valedictorian), KAIST, 2020
National Excellence Scholarship (Natural Sciences & Engineering), KOSAF, 2020-2023
KAIST Dean's List, KAIST, 2018
KAIST Presidential Fellowship (KPF), Honor Society of KAIST, 2018-2024
KAIST Undergraduate Scholarship, KAIST, 2018-2019
Hansung Scholarship for Gifted Students ($10,000), Hansung Son Jae-han Foundation, 2016

Research Projects (Government/Industrial)

Acquisition of 3D Precise Information of Microstructure and Development of Authoring Technology for Ultra-high Precision Cultural Restoration
Ministry of Culture, Sports and Tourism (South Korea), 2024-2025
Project Leader & Main Researcher
Development of a PPG-based Respiratory Rate Prediction Algorithm
Skylabs Co., 2024-2025
Project Leader & Main Researcher
Development of ECG-based Seizure Prediction, Detection, Post-Detection Models
Skylabs Co., 2024
Project Leader & Main Researcher

Teaching Experience

Teaching Assistant, KAIST, AI618 Generative Models and Unsupervised Learning, 2025
Teaching Assistant, SK mySUNI Education Platform, 2025
Teaching Assistant, Samsung Financial Networks, 2025
Teaching Assistant & Mentor, KSOP (KAIST Science Outreach Program), 2020
Teaching Assistant & Mentor, Hansung Scholarship Summer Camp, 2019