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 ...

Genie 2 is a new video model that generates plausible, consistent, playable 3D environments based on a prompt image.

TL;DR: Google DeepMind's Genie 2 is a foundation world model that generates 3D environments from a single image, improving on its predecessor's 2D capabilities. It supports complex interactions ...

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 ...

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 ...

He tracks AI progress toward AGI and beyond. Alan determines that we are 84% of the way to AGI after the release of Google Genie 2 with world models and other releases that advance agent capabilities.