BWhat changed
Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system.
Scientific scope
Integrated spatial-temporal causal video compression, text/video expert-adaptive normalization, full spatiotemporal attention and progressive-duration/resolution training into an openly released video diffusion system. Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical 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. Diffusion, DiT, VAE compression and text conditioning have earlier sources; this record covers their video-specific expert/compression/training integration. Early released resolution and duration differ from later versions; video examples and comparative quality are source-reported, not a physical 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.
- CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
- Yang et al.: CogVideoX causal video compression and expert transformer — official research provenance
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