Publications

Conference Papers

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

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

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

Conference on Neural Information Processing Systems (NeurIPS) 2026

paperwebsitecode

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
Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration demo

Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration

Yunghee Lee, Byeonghyun Pak, Junwha Hong, Hoseong Kim

Conference on Neural Information Processing Systems (NeurIPS) 2025

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

Workshop Papers

4D Latent Mapping for Mobile Manipulation Policy Learning

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

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

paperwebsite
Rethinking FID Through the Geometry of the Reference Dataset demo

Rethinking FID Through the Geometry of the Reference Dataset

Yunghee Lee, Byeonghyun Pak

ICML Workshop on Combining Theory and Benchmarks 2026

paper

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