AWhat changed
Trained a causal denoising sequence model with independent per-token noise levels, permitting variable-horizon generation, guidance and planning within one training/sampling framework.
Scientific scope
Trained a causal denoising sequence model with independent per-token noise levels, permitting variable-horizon generation, guidance and planning within one training/sampling framework. Inherits diffusion, teacher forcing and planning. The paper's conditional variational-bound result is source-reported, not proof-audited here. Long-rollout examples do not guarantee indefinite physical fidelity, bounded control error or all-environment planning.
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 diffusion, teacher forcing and planning. The paper's conditional variational-bound result is source-reported, not proof-audited here. Long-rollout examples do not guarantee indefinite physical fidelity, bounded control error or all-environment planning.
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