OM-1 robot foundation model generalizes zero-shot to arms and humanoids from human data alone

yifengzhu_ut · x · 2026-09-15

RewardAI introduces OM-1, its first robot foundation model that zero-shot generalizes to any robot: tabletop arms, industrial arms, and humanoids.

Key claims: learned directly from human manipulation data with no teleop or robot data collection, near human-level dexterity and efficiency, and multi-robot collaboration. The reposter highlights that the demo runs at 1x speed, implying the capabilities are real-time.

Related event: RewardAI Unveils OM-1, a Robot Foundation Model Trained Purely on Human Data with Zero-Shot Cross-Embodiment Generalization(48 posts)→

Original post →

More from Embodied

Embodied channel →