Jay van Zyl @ ecosystem.Ai

Jay van Zyl @ ecosystem.Ai

Google Deepmind presents RT-2, the first vision-language-action (VLA) Robotics Transformer and it may have drastic implications our future.

The latest article published by Google Deepmind is seriously approaching a Blade Runner type future. Their research paper is on the first VLA (vision-language-action) Model RT-2 (see paper), a multi-modal algorithm which tokenizes robotic inputs …