Google DeepMind broadly releases Gemini 4 Argon - 2026-10-13 - Research Publication - Google reports an 87% score on its Embodied Reasoning benchmark for physical and spatial problems. In an internal test, Argon reconstructed a human cornhole video, generated simulation code and transferred a skill to an… - source: blog.google
Google DeepMind introduces Gemini Robotics On-Device for local robot control - 2025-06-24 - Research Publication - Google DeepMind introduced Gemini Robotics On-Device as an efficient VLA model optimized to run locally on robotic devices. The model supports general-purpose dexterity, fast task adaptation and SDK-based evaluation in… - source: deepmind.google
Google DeepMind introduces RT-2 vision-language-action model - 2023-07-28 - Research Publication - RT-2 was presented as a robotics model trained on both web-scale vision-language data and robot action data. The release described improved generalization on emergent robotic skills compared with RT-1 and visual-language… - source: deepmind.google