AWhat changed
Adapts Fourier neural operators into a vision token mixer using block-diagonal channel mixing, shared Fourier-domain MLPs and soft-thresholded frequency features.
Scientific scope
Adapts Fourier neural operators into a vision token mixer using block-diagonal channel mixing, shared Fourier-domain MLPs and soft-thresholded frequency features. Guibas and Mardani share first authorship, second leads project. Quasi-linear sequence-length cost assumes fixed channel/block dimensions and is not exact attention-output equivalence, arbitrary-resolution accuracy or a blanket end-to-end speed guarantee.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Guibas and Mardani share first authorship, second leads project. Quasi-linear sequence-length cost assumes fixed channel/block dimensions and is not exact attention-output equivalence, arbitrary-resolution accuracy or a blanket end-to-end speed guarantee.
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