Octo is deliberately small and easy to fine-tune, trading raw capability for accessibility. It is one of the most widely cited fully open baselines in the generalist-policy literature, which makes it a common comparison point in academic robotics papers.
More in Robot Foundation Models
Skild Brain
A robotics foundation model from Skild AI, founded in 2023 by researchers Deepak Pathak and Abhinav Gupta.
Physical Intelligence π0.5
Keeps the π0 recipe — a vision-language-model backbone with a flow-matching action expert — but is built around generalization to new environments.
Figure Helix
End-to-end vision-language-action model from Figure that runs entirely on the Figure 02 and Figure 03 humanoids. A dual-system architecture (System 2 ~7B VLM for reasoning, System 1 ~80M transformer for fast control) enables 35-DoF whole-upper-body control. Helix 02 (Jan 2026) extends to whole-body autonomy.
Let's get in touch with us
At the intersection of innovation and technology, we are pioneers crafting a landscape for the digital age.