Byeonghyun Pak

Hi! I'm Byeonghyun, and I also go by Ben. I'm a first-year Ph.D. student in the Department of Computer Science at the University of Maryland (UMD), where I am fortunate to be 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).

Feel free to reach out to me via my email.

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)

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

paper website code

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

paper website code

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

paper website code

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)

paper website code

Recent News

Selected Publications

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

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

Textual Query-Driven Mask Transformer for Domain Generalized Segmentation

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