Byeongju Woo

Byeongju Woo

First year Ph.D. Student

Computer Science & Engineering

University of Michigan

Hi! I am Ph.D. student in Computer Science and Engineering at the University of Michigan, advised by Prof. Stella Yu.
Previously, I completed my bachelor's degree (Summa Cum Laude) in Computer Science and Engineering at POSTECH.

Research
My research interests lie in computer vision and deep learning, with a particular focus on developing systems that emulate human cognitive processes. I aim to create machines that perceive not merely to recognize, but to truly comprehend the physical world. Accordingly, I am currently focusing on the following topics, among others:
Grounded visual understanding
Structured visual priors
Robust generalization
Context-aware representation

Last updated: September 25, 2026

News

Sep 2026

CAFT was accepted to NeurIPS 2026. See you at Atlanta!

Sep 2026

VVSQ was accepted to Neurocomputing

Aug 2026

Started Ph.D. at University of Michigan, advised by Prof. Stella Yu

Jun 2026

Completed military service at the Agency for Defense Development (ADD)

May 2026

Selected as Gold Reviewer at ICML 2026

Older news ▸
May 2026

Google Scholar citations reached 100

Mar 2026

CroBo was accepted to CVPR 2026 Workshop on Pixel-level Video Understanding in the Wild

Selected Publications

Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding

Byeongju Woo, Zilin Wang, Byeonghyun Pak, Sangwoo Mo, Stella X. Yu

NeurIPS 2026

PaperPageCodeCheckpoints
Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition

Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition

Seokmin Lee, Yunghee Lee, Byeonghyun Pak, Byeongju Woo

CVPR 2026 Workshops, Pixel-level Video Understanding in the Wild

PaperPageCode
Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

Byeongju Woo*, Byeonghyun Pak*, Sunghwan Kim*, Dae-hwan Kim, Hoseong Kim

ECCV 2024

PaperPageCode
Human Pose Estimation in Extremely Low-Light Conditions

Human Pose Estimation in Extremely Low-Light Conditions

Sohyun Lee*, Jaesung Rim*, Boseung Jeong, Geonu Kim, Byungju Woo, Haechan Lee, Sunghyun Cho, Suha Kwak

CVPR 2023

PaperPageCode

Work Experience

Agency for Defense Development (ADD)

June 2023 – May 2026

Research Officer for National Defense (ROND)

  • Served as a First Lieutenant in the Republic of Korea Air Force (ROKAF) and worked as a research officer.
  • Researched Domain Generalized Object Detection for UAV detection.
  • Served on the execution team of AI Transformation Task Force (Feb 2026 – Mar 2026).

SK Hynix

June 2021 – July 2021

Computer Vision Research Intern

  • Developed an automated algorithm to pre-check for rejects in 3D NAND manufacturing with DL models.
  • Received an Industry-Academia Scholarship with guaranteed employment upon graduation.