DeepMind is already using Genie-generated spaces to train other AIs. Genie can help these navigate a world made up by another AI, and in real time, too. One system dreams, another learns.

However, there are even limitations to what Genie 2 can do in this regard. DeepMind says the model can generate “consistent” worlds for up to 60 seconds, with the majority of the examples the ...

Google DeepMind has presented "Genie 2", which generates interactive 3D environments from individual images. It is intended to be used for training AI agents.

DeepMind’s new AI model, Genie 2, makes creating 3D interactive worlds as easy as describing them with text or showing an image. Whether it’s a robot exploring a forest or other imaginative ...

Google DeepMind announced Genie 2 , a basic world model that can generate playable 3D environments from a single input image, on December 4, 2024. The world generated by Genie 2 can be navigated ...

Called Genie 2, the model — the successor to DeepMind's Genie, which was released earlier this year — can generate an interactive, real-time scene from a single image and text description (e.g.

Last week, Google DeepMind announced Genie 2, a new video model that generates plausible, consistent, playable 3D environments based on a prompt image. DeepMind claims that Genie 2 has a slew of ...

DeepMind has unveiled its Genie 2, an advanced AI model that creates immersive 3D worlds from text prompts or images, enhancing interactivity with physics-based actions. It offers significant ...

DeepMind, Google's AI research org, has unveiled a model that can generate an "endless" variety of playable 3D worlds. Called Genie 2, the model — the successor to DeepMind's Genie, which was released ...