BWhat changed
Trained a representation-autoencoder latent diffusion world model on RocketLeague gameplay with multiple player action streams, studying shared dynamics and targeted physical-behavior evaluations.
Scientific scope
Trained a representation-autoencoder latent diffusion world model on RocketLeague gameplay with multiple player action streams, studying shared dynamics and targeted physical-behavior evaluations. Inherits RAE/diffusion/world-model methods. Four-player20fps operation is reported on a B200; measured quality horizons reach five minutes, while hours-long stability is observational. Neither establishes indefinite physical fidelity, arbitrary environments or certified agent-training transfer.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits RAE/diffusion/world-model methods. Four-player20fps operation is reported on a B200; measured quality horizons reach five minutes, while hours-long stability is observational. Neither establishes indefinite physical fidelity, arbitrary environments or certified agent-training transfer.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Multiplayer Interactive World Models with Representation Autoencoders
- Kyutai scientific publications index
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction