Author

Hanbyul Joo

h-index 10 View on Semantic Scholar

We have 2 of 32 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning

Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand trackers regress pose from cropped frames with limited priors on hand motion and object interaction, resulting in inaccurate and physically inconsistent estimates. Moreover,...

Seung-Jun Moon, Subin Jeon, Sangwoo Kim et al. · 2 citations

Jul 2026

Robot-Factored World Models via Robot Rendering

This work proposes robot-factored world models, which move two robot-specific factors outside the world model, and shows that the rendered interface outperforms vector-conditioned baselines and generalizes to unseen robot embodiments at inference.

Byungjun Kim, Taeksoo Kim, Hyunsoo Cha et al. · arXiv.org · 5 citations