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.

Google DeepMind CEO Demis Hassabis showed 60 Minutes Genie 2, an AI model that generates 3D interactive environments, which could be used to train robots in the not-so-distant future.

DeepMind didn’t detail how it trained Genie 2 other than to state it relied “on a large-scale video dataset.” Don’t expect DeepMind to release Genie 2 to the public anytime soon, either.

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, a leader in AI innovation , has unveiled Genie 2, a groundbreaking tool capable of creating limitless, diverse 3D environments for training and evaluating AI agents.

DeepMind claims that Genie 2 has a slew of new and exciting emerging capabilities that improve the lighting, reflections, and can even generate videos from real-world images.

Activists staged a mock courtroom outside Google DeepMind, accusing the tech giant of backtracking on its AI safety pledge ...

Genie 2. And then there’s Genie 2, DeepMind’s new world-modeling system. If Astra understands the world as it exists, Genie builds worlds that don’t.

DeepMind says that Genie 2 can generate consistent worlds with different perspectives, like first-person and isometric views, for up to a minute, with the majority lasting 10 to 20 seconds.

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 ...

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 ...