RewardAI's OM-1 zero-shot generalizes across arms and humanoids

zipengfu · x · 2026-09-15

RewardAI's OM-1 demonstrates zero-shot generalization across different embodiments: the same model controls small arms, industrial arms, and even humanoids (paired with their 7-DoF Omnibody Hands) without any robot-specific finetuning.

The core pitch: with hardware advancing every month, robot models and data need to be future-proof rather than tied to a specific body.

Related event: RewardAI Launches OM-1: Robot Foundation Model Zero-Shot Trained on Pure Human Data(51 posts)→

Original post →

More from Embodied

Embodied channel →