RewardAI unveils OM-1, a robot foundation model that zero-shot generalizes across arms and humanoids

yifengzhu_ut · x · 2026-09-15

RewardAI has introduced OM-1, its first robot foundation model, which zero-shot generalizes to table-top arms, industrial arms, and humanoids. The team says it was learned directly from human manipulation data with no teleop or robot data, achieving near human-level dexterity and efficiency plus multi-robot collaboration. Observers highlighted how smooth the resulting motions look.

Related event: Physical Intelligence unveils OM-1 robot foundation model(31 posts)→

Original post →

More from Embodied

Embodied channel →