// ◐ World Models & Self-Supervised Learning
Genie (Generative Interactive Environments)
Learns playable, controllable worlds from unlabeled videos.
Genie 可交互世界生成 2024 Research frontier core
IN PLAIN WORDS
A video tokenizer, latent action model and dynamics model infer actions without labels, turning an image into a playable 2D world; Genie 2/3 extend to 3D.
Used in: Genie 2/3, game and robotics training environments
TIMELINE · prerequisites → this → what builds on it
01Original paper
Genie: Generative Interactive Environments
Jake Bruce, Michael Dennis, Ashley Edwards, et al. · 2024
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Then you can learn
- Nothing in the atlas builds on it yet
Related:Diffusion Transformer (DiT)
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Explainers
04Where the course teaches it
On learning paths:Generative Models & Frontier Research
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
genie)