News
Google DeepMind Simulates Robot Behavior Using Veo World Model
DeepMind and the Gemini Robotics team built a simulation system using Veo, Google's generative video model, to evaluate robot control policies without needing physical robots.
DeepMind
Genie 3
DeepMind Launches Genie 3 with Dynamic Scene Generation from Text Prompts
Google DeepMind has released Genie 3, a new world model that generates interactive worlds from text prompts. Users can move through these AI-generated scenes in real time, with visuals running at 720p and staying consistent even when revisiting earlier locations.
News
Google Introduces On-Device Gemini Model for Real-Time Robot Tasks
Google has introduced Gemini Robotics On-Device, a new version of its multimodal robotics AI designed to operate directly on robotic hardware. Based on the Gemini Robotics system launched in March
News
Gemini Robotics Models Unlock General-Purpose Dexterity in Real-World Robots
Google DeepMind has introduced a new family of Gemini Robotics models that enable robots to understand and perform complex physical tasks using natural language.