← Search

Seonho Kim

2 accepted papers

2026

INSIGHT Bench: Towards Grounded IN-SItu Guidance for Robotic ManipulaTion

CVPR 2026

Humans intuitively rely on text and symbols inscribed on objects (e.g. "PULL", "Squeeze and Turn") to perform tasks safely and correctly. In contrast, vision-language-action models excel at following external language commands, but remain largely unaware of this object-centric information. This capa

Cited by 0SourcecodeScholar