GreenWAM: A World Foundation Model for Robotics

arxiv-cs.RO2026-10-13Abstract screenedOpen source ↗

INVESTOR TAKEAWAY

A robot needs a world model that predicts how its actions will change the scene and a policy that chooses those actions. Models are usually built and evaluated for only one of these roles, and every robot records its actions in its own format.

ORIGINAL PAPER

WHAT WE KNOW

We ask whether one robot world model can serve both roles across different bodies, and what makes this work. We present GreenWAM, a world foundation model for robotics, together with the recipe that produces it: (1) a shared anatomical action space that describes 20 robot families, from bimanual arms to dexterous humanoids, in common joint coordinates; (2) joint training on these families in visual, action-conditioned and world-action modes; and (3) policies that split an action expert off the generator.

WATCH NEXT

Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.

EVIDENCE

What the evidence supports so far

Research signals

VLA

humanoid

imitation-learning

What remains unverified

The full methodology, effect size, and limitations still require analyst review.

Company impact remains unverified until a direct economic transmission is established.