Google DeepMind introduces Genie 4 as an interactive world modelA world model learns how an environment is structured and how it may change in response to actions. that generates environments from prompts and imagesGenerative AI creates new text, images, audio, video, code or other content from learned patterns and supplied context.. The demonstration shows users exploring scenes, moving a camera and changing details as the environment responds, with ambient sound.
The video also illustrates character control and simulated scenarios for robots to practise tasks virtuallyRobotics develops machines that sense their surroundings and perform physical actions through coordinated hardware and software.. Google DeepMind presents potential physical-world applications as a future possibility rather than a demonstrated result.
Watch on YouTube
