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.
More from Embodied
- Lighthouse extends Obsidian welding foundation model to run on any robotic platform — bennash · 2026-11-11
- Sipeed's MaixStation Dock PCB returns, 14-layer SOM still in fab — AIFlow_ML · 2026-11-11
- NAE EU-US Frontiers of Engineering symposium explores AI-driven materials, robotics, neuromorphic computing — ProfBuehlerMIT · 2026-11-11
- Paper link for FLEX: robots generalize language corrections into preferences — JafarNajafov · 2026-11-11
- MIT and NYU's FLEX lets robots generalize a single spoken correction into broad preferences — JafarNajafov · 2026-11-11
- AI lets robotics research thrive in labs with no robotics experts — 4310sy · 2026-11-11