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works at the policy level, likely learning an embodiment-agnostic action representation from human data (representation unpublished).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.
More from Embodied
- Travis Kalanick: Tesla is 'the Google of this era' in the physical AI age — rohanpaul_ai · 2026-09-16
- Slovenia's Deputy PM tries Tesla FSD on public roads: 'doesn't get tired, doesn't fall asleep' — elonmusk · 2026-09-16
- DRS-VPT: feed-forward camera pose estimation from a point cloud scan and a single image — kwangmoo_yi · 2026-09-16
- Bionic Robobird Demonstrates Nature-Mimicking Flapping-Wing Flight — TinfoilTricorn · 2026-09-16
- StarVLA's VLAct trains VLAs on 16 GPUs by reshaping action representations, not data scaling — jiqizhixin · 2026-09-16
- World Labs launches Atlas: an omni world model natively spanning text, images, video and 3D — YunzhuLiYZ · 2026-09-16