{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/fast-feedforward-networks","title":"Fast Feedforward Networks","arxiv_id":"2308.14711","date":"2023-08-28","proceeding":null,"authors":["Peter Belcak","Roger Wattenhofer"],"abstract":"We break the linear link between the layer size and its inference cost by introducing the fast feedforward (FFF) architecture, a log-time alternative to feedforward networks. We demonstrate that FFFs are up to 220x faster than feedforward networks, up to 6x faster than mixture-of-experts networks, and exhibit better training properties than mixtures of experts thanks to noiseless conditional execution. Pushing FFFs to the limit, we show that they can use as little as 1% of layer neurons for inference in vision transformers while preserving 94.2% of predictive performance.","url_abs":"https://arxiv.org/abs/2308.14711v2","url_pdf":"https://arxiv.org/pdf/2308.14711v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-feedforward-networks","repo_url":"https://github.com/pbelcak/fastfeedforward","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-feedforward-networks","repo_url":"https://github.com/BrianPulfer/PapersReimplementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-feedforward-networks","repo_url":"https://github.com/andreascharalamp/fastfeedforward-experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fast-feedforward-networks","repo_url":"https://github.com/fabianwinter93/JAX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"fff","method_name":"FFF"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"fff","name":"FFF","full_name":"Fast Feedforward Networks"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.14711","atlas_url":"https://app.syntology.ai/?focus=2308.14711","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2308.14711"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.14711\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.14711"},"call":"get_concepts_for_paper(arxiv_id=\"2308.14711\")"}],"by_repo":[{"repo":"pbelcak/fastfeedforward","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"BrianPulfer/PapersReimplementations","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1706.03762","1707.06347","2006.11239","2010.11929"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"1707.06347","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1707.06347"},"call":"get_harvested_code_for_paper(arxiv_id=\"1707.06347\")"},{"arxiv_id":"2006.11239","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.11239"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.11239\")"},{"arxiv_id":"2010.11929","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.11929"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.11929\")"}]},{"repo":"andreascharalamp/fastfeedforward-experiments","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fabianwinter93/JAX","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9c4b2a427db37a6130f2f2a88a6dabef39916d49ae2809fc39b9d170012ff81c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}