AWhat changed
Trained one transformer on interleaved text and continuous image latents with next-token text loss, image diffusion loss and causal-text/bidirectional-image attention.
Scientific scope
Trained one transformer on interleaved text and continuous image latents with next-token text loss, image diffusion loss and causal-text/bidirectional-image attention. Not first multimodal modeling or diffusion. Acquired delta is the joint recipe/controlled integration, not a claim of information-lossless pixels: image encoding and patch compression remain. Controlled Chameleon-style comparisons are not blanket superiority over every trained 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. Not first multimodal modeling or diffusion. Acquired delta is the joint recipe/controlled integration, not a claim of information-lossless pixels: image encoding and patch compression remain. Controlled Chameleon-style comparisons are not blanket superiority over every trained 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