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