LATEST NEWS :
FREE Orientation @ Kapoorthala Branch on 30th April 2024 , FREE Workshop @ Kanpur Branch on 29th April , New Batch of Modern History W.e.f. 01.05.2024 , Indian Economy @ Kanpur Branch w.e.f. 25.04.2024. Interested Candidates may join these workshops and batches .
Print Friendly and PDF

Genie AI Model

29.02.2024

 

Genie AI Model , Daily Current Affairs , RACE IAS : Best IAS Coaching in Lucknow 

 

For Prelims:About Genie AI Model

 

 Why in the news?

Recently, Google DeepMind has just introduced Genie, a new model that can generate interactive video games from just a text or image prompt.

 

About Genie AI Model:

  • It is a foundation world model that is trained on videos sourced from the Internet.
  • The model can “generate an endless variety of playable (action-controllable) worlds from synthetic images, photographs, and even sketches.”
  • It is the first generative interactive environment that has been trained in an unsupervised manner from unlabelled internet videos.
  • Specifications: When it comes to size, Genie stands at 11B parameters and consists of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model.
  • These technical specifications let Genie act in generated environments on a frame-by-frame basis even in the absence of training, labels, or any other domain-specific requirements.
  • Genie can be prompted to generate a diverse set of interactive and controllable environments although it is trained on video-only data.
  • It makes playable environments from a single image prompt.
  • It can be prompted with images it has never seen. This includes real-world photographs, and sketches, allowing people to interact with their imagined virtual worlds.
  • It is trained more on videos of 2D platformer games and robotics.
  • Genie is trained on a general method, allowing it to function on any type of domain, and it is scalable to even larger Internet datasets.
  • The standout aspect of Genie is its ability to learn and reproduce controls for in-game characters exclusively from internet videos.
  • This is noteworthy because internet videos do not have labels about the action that is performed in the video, or even which part of the image should be controlled.
  • It allows you to create an entirely new interactive environment from a single image.

 

                                                      Source: Indian Express