Grounded Action Models: a robot foundation model paradigm built on 3D grounding

DJiafei · x · 2026-09-26

HuggingPapers highlights Grounded Action Models, a new paradigm for robot foundation models built on 3D grounding.

Language, points, or bounding boxes are mapped into a shared object-centric representation, which is combined with robot state history to predict action chunks. The approach unifies diverse grounding signals into one representation space for action prediction, making it a notable new architecture direction in embodied AI.

Original post →

More from Embodied

Embodied channel →