BWhat changed
Combined channel projections with multiplicative gates driven by learned spatial projections, testing attention-free blocks on image classification and masked language modeling.
Scientific scope
Combined channel projections with multiplicative gates driven by learned spatial projections, testing attention-free blocks on image classification and masked language modeling. The spatial projection is tied to sequence length and has quadratic sequence cost in the original formulation. Attention-free does not mean token-independent or linear-time. Matching a Transformer on selected tasks may require greater model capacity.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The spatial projection is tied to sequence length and has quadratic sequence cost in the original formulation. Attention-free does not mean token-independent or linear-time. Matching a Transformer on selected tasks may require greater model capacity.
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