{"url":"/method/fff","slug":"fff","name":"FFF","full_name":"Fast Feedforward Networks","full_name_withheld":false,"description_markdown":"A log-time alternative to feedforward layers outperforming both the vanilla feedforward and mixture-of-experts approaches.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Fast Feedforward Networks","paper":"/paper/fast-feedforward-networks","first_author":"Peter Belcak","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/fast-feedforward-networks"},"source":{"url":"https://arxiv.org/abs/2308.14711v2","title":"Fast Feedforward Networks","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Backbone Architectures","url":"/methods/category/backbone-architectures","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"title":"MagicStyle: Portrait Stylization Based on Reference Image","date":"2024-09-12","arxiv_id":"2409.08156","n_code_links":0,"syntology":null},{"paper":null,"title":"The Dial-a-Ride Problem with Limited Pickups per Trip","date":"2024-08-14","arxiv_id":"2408.07602","n_code_links":0,"syntology":null},{"paper":"/paper/mathematical-methods-for-assessing-the","title":"Mathematical Methods for Assessing the Accuracy of Pre-Planned and Guided Surgical Osteotomies","date":"2024-06-04","arxiv_id":"2406.02824","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-fast-feed-forward-networks-with","title":"Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf Node","date":"2024-05-27","arxiv_id":"2405.16836","n_code_links":1,"syntology":null},{"paper":"/paper/exponentially-faster-language-modelling","title":"Exponentially Faster Language Modelling","date":"2023-11-15","arxiv_id":"2311.10770","n_code_links":3,"syntology":null},{"paper":"/paper/fast-feedforward-networks","title":"Fast Feedforward Networks","date":"2023-08-28","arxiv_id":"2308.14711","n_code_links":4,"syntology":null}],"papers_shown":6,"tasks":[{"task":"/task/mixture-of-experts","name":"Mixture-of-Experts","papers":2},{"task":"/task/arc","name":"ARC","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/image-stylization","name":"Image Stylization","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2023","papers":2},{"year":"2024","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/fff"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}