Kwang Bin Lee

Seoul, South Korea

Hey everyone! I’m Kwang Bin, a returning Master’s student in Computer Science at Johns Hopkins University, advised by Prof. Tianmin Shu in the SCAI Lab. Before that, I was a Master’s student at KAIST’s Graduate School of Culture Technology, advised by Prof. Sung-Hee Lee in the LAVA Lab.

My research sits at the intersection of spatial intelligence and task planning for embodied agents. I’m particularly interested in using foundation models to help embodied agents understand the 3D scenes they’re situated in and translate high-level tasks into scene-aware, visually grounded, actionable steps—a skill I’ve always admired in humans, too.

Outside of research, I really love books and films. My favorite author is Roald Dahl, and one of my favorite movies is Paddington!

news

Apr 24, 2026	Our paper MaskAdapt has been selected as a Highlight at CVPR 2026!
Mar 05, 2026	I will be presenting Situately as a Research Demo at IEEE VR 2026!
Mar 05, 2026	Our paper MaskAdapt has been accepted to CVPR 2026!

Research Works

MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters

Soomin Park, Eunseong Lee, Kwang Bin Lee, and Sung-Hee Lee

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Highlight DOI Bib

true

@inproceedings{park2026maskadapt,
  title = {MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters},
  author = {Park, Soomin and Lee, Eunseong and Lee, Kwang Bin and Lee, Sung-Hee},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  publisher = {IEEE},
  doi = {10.48550/arXiv.2603.29272},
}

Scene-agnostic Hierarchical Bimanual Task Planning via Visual Affordance Reasoning

Kwang Bin Lee, Jiho Kang, and Sung-Hee Lee

2025

arxiv preprint

DOI Bib

@book{lee2025sceneagnostichierarchicalbimanualtask,
  title = {Scene-agnostic Hierarchical Bimanual Task Planning via Visual Affordance
  Reasoning},
  author = {Lee, Kwang Bin and Kang, Jiho and Lee, Sung-Hee},
  year = {2025},
  note = {arxiv preprint},
  publisher = {arxiv},
  doi = {10.48550/arXiv.2512.09310},
}

Situated Embodied XR Agents via Spatial Reasoning and Prompting

Jihun Shin, Hyeonjin Kim, Eunseong Lee, Donghwan Shin, Kwang Bin Lee, Taehei Kim, Hyeshim Kim, Joonsik An, and Sung-Hee Lee

In 2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), 2025

Research Demo

DOI Bib

@inproceedings{shin2025situatedxr,
  title = {Situated Embodied XR Agents via Spatial Reasoning and Prompting},
  author = {Shin, Jihun and Kim, Hyeonjin and Lee, Eunseong and Shin, Donghwan and Lee, Kwang Bin and Kim, Taehei and Kim, Hyeshim and An, Joonsik and Lee, Sung-Hee},
  booktitle = {2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)},
  year = {2025},
  publisher = {IEEE},
  note = {Research Demo},
  doi = {10.1109/ISMAR-Adjunct68609.2025.00255},
}