RESEARCH PAPERYear 2024
Genie: Generative Interactive Environments
Classification
View four quadrants- Major category
- Benchmarks & simulators
- Quadrant
- Not applicable
- Architecture
- Not applicable
- Prediction paradigm
- Not applicable
- Subcategories
- Neural world simulatorsLatent action pretraining
- Source review status
- Verified from primary sources
Category review. Genie assembles a video tokenizer, latent-action model and dynamics transformer into an interactive learned environment. At interaction time the user chooses latent codes and the model generates frames; the separately calibrated imitation experiment does not turn the general simulator into a canonical encoder/backbone. Reading evidence
Contribution
A contribution summary has not been added yet.
Abstract
An abstract has not been added yet.
Affiliations
Not listed in the collection.