Methods › Natural Language Processing › Transformers › Fastformer
Fastformer
Introduced by Chuhan Wu et al. in Fastformer: Additive Attention Can Be All You Need
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Fastformer is an type of Transformer which uses additive attention as a building block. Instead of modeling the pair-wise interactions between tokens, additive attention is used to model global contexts, and then each token representation is further transformed based on its interaction with global context representations.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Multi-Granularity Vision Fastformer with Fusion Mechanism for Skin Lesion Segmentation 4 Apr 2025 · 0 repositories · arXiv:2504.03108
-
An Analysis of Linear Complexity Attention Substitutes with BEST-RQ 4 Sep 2024 · 0 repositories · arXiv:2409.02596
-
FUM: Fine-grained and Fast User Modeling for News Recommendation 10 Apr 2022 · 0 repositories · arXiv:2204.04727
-
Fastformer: Additive Attention Can Be All You Need 20 Aug 2021 · 13 repositories · arXiv:2108.09084Syntology ran 4 of 4 samples · 0 unverified · 3 pointer-only (licence)
Tasks archive 2025-07-28
12 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections