World ↗Canonical event
OpenVLA publishes a vision-language-action research model
The original OpenVLA preprint introduced a 7B robot policy trained on 970,000 demonstrations with open adaptation tooling.
Artifacts
Signals
- Licensed language-model weights and open robot-policy tooling broadened developer adaptation; openness and deployment guarantees remained distinct.supported inference
- Research linked responsive video/speech assistant prototypes and open robot-action policies while transfer and deployment limitations remained explicit.supported inference
- Open robot-policy adaptation research progressed alongside a multi-year commercial humanoid logistics agreement, with bounded tasks distinct from general autonomy.supported inference