Byeonghyun Pak

Hi! I'm Byeonghyunpronounced "Byung-hyun", a first-year PhD student in the Department of Computer Science at the University of Maryland (UMD), advised by Prof. Furong Huang.

Before joining UMD, I served as a research officer at the Agency for Defense Development (ADD), where I worked on vision-language models and visual representation learning. I received my Bachelor’s degree from Daegu Gyeongbuk Institute of Science and Technology (DGIST).

My research goal is to build robots that can perceive, reason, and act over long horizons while generalizing robustly to real-world environments. I am particularly interested in active world modeling and persistent memory for embodied agents, with a focus on open-world mobile manipulation.

Feel free to reach out to me via my email.

Byeonghyun Pak

Recent News

view all
  • [Sep 2026]Our paper was accepted to NeurIPS 2026.
  • [Sep 2026]Our paper was accepted to CoRL 2026 and selected for a Spotlight!
  • [Aug 2026]I started my PhD journey at UMD, working with Prof. Furong Huang!
  • [Jun 2026]I completed three years of military service as a research officer at ADD.

Selected Publications

view all

SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation

Sunghwan Kim*, Byeonghyun Pak*, Kehan Long, Yulun Tian, Nikolay Atanasov

Conference on Robot Learning (CoRL) 2026 (Spotlight Paper)

ICRA Workshop on MM-Spatial AI 2026 (Best Paper Award)

paperwebsitecode

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

Seokmin Lee, Yunghee Lee, Byeonghyun Pak, Byeongju Woo

CVPR Workshop on Pixel-level Video Understanding in the Wild 2026

paperwebsitecode

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

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

European Conference on Computer Vision (ECCV) 2024

paperwebsitecode
B-spline Texture Coefficients Estimator for Screen Content Image Super-Resolution demo

B-spline Texture Coefficients Estimator for Screen Content Image Super-Resolution

Byeonghyun Pak*, Jaewon Lee*, Kyong Hwan Jin

Computer Vision and Pattern Recognition Conference (CVPR) 2023 (Highlight Paper)

paperwebsitecode