Canonical event

DeepMind introduces RT-2

DeepMind introduced RT-2, a vision-language-action model trained from web and robotics data for generalized robot control.

Artifacts

RT-2
evidenced_by · vision_language_action_research

Signals

Web-scale vision-language representations were adapted directly into robot-action models, strengthening semantic transfer from general models into physical control.
supported inference

View canonical JSON