Google presents Genie
AK
Auf X besuchen@_akhaliq528.977 Follower
684.738 Aufrufe
Google presents Genie
Generative Interactive Environments
introduce Genie, the first generative interactive environment trained in an unsupervised manner from unlabelled Internet videos. The model can be prompted to generate an endless variety of action-controllable virtual worlds described through text, synthetic images, photographs, and even sketches. At 11B parameters, Genie can be considered a foundation world model. It is comprised of a spatiotemporal video tokenizer, an autoregressive dynamics model, and a simple and scalable latent action model. Genie enables users to act in the generated environments on a frame-by-frame basis despite training without any ground-truth action labels or other domain-specific requirements typically found in the world model literature. Further the resulting learned latent action space facilitates training agents to imitate behaviors from unseen videos, opening the path for training generalist agents of the future.
9 Kommentare
Kommentare aus dem Originalbeitrag auf X (Twitter)

@_akhaliq
paper page:
124 Likes

@_akhaliq
project page:
70 Likes

@XRMultiverse
Google's warehouse of unused tech
21 Likes

@crispyshh
@apples_jimmy Text to Mario achieved externally
19 Likes

@untitled01ipynb
that's so cool
14 Likes

@griswold
Can it make Wolfenstein? If not, why not.
11 Likes

@SmokeAwayyy
🔥🔥🔥
10 Likes

@matgee01
all these papers, no public releases 🫠
7 Likes

@madebyollin
Demo page with more videos.
6 Likes