AWhat changed
Performed autoregressive generated-context rollouts with KV caching during training and video-level losses, using few-step denoising and stochastic gradient truncation to reduce exposure mismatch.
Scientific scope
Performed autoregressive generated-context rollouts with KV caching during training and video-level losses, using few-step denoising and stochastic gradient truncation to reduce exposure mismatch. Inherits teacher/diffusion forcing, DMD and causal video generation. Training reduces an empirical distribution gap, not a proof of no error accumulation, indefinite stability or a physically accurate world model.
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 teacher/diffusion forcing, DMD and causal video generation. Training reduces an empirical distribution gap, not a proof of no error accumulation, indefinite stability or a physically accurate world model.
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.
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