Robotics researcher pushes back on 'omni embodiment' hype: it's the hands, not the abstraction

chris_j_paxton · x · 2026-09-16

Robotics researcher Chris Paxton offered a contrarian take on Reward AI's impressive multi-embodiment autonomous manipulation demo.

Context: the quoted tweet praises Reward AI (Zipeng Fu et al.) for autonomous manipulation across embodiments at high speed, attributing it to an omni-embodiment model with model-level abstraction — past cross-embodiment relied on retargeting human actions, while Reward AI works at the policy level, likely learning an embodiment-agnostic action representation from human data (representation unpublished).

Paxton's view: "omni embodiment" is the wrong frame right now — it's still one embodiment, and the real key is the hands: put the right hands in the right place.

Original post →

More from Embodied

Embodied channel →