{"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/pay-less-attention-with-lightweight-and","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","arxiv_id":"1901.10430","date":"2019-01-29","proceeding":"ICLR 2019 5","authors":["Felix Wu","Angela Fan","Alexei Baevski","Yann N. Dauphin","Michael Auli"],"abstract":"Self-attention is a useful mechanism to build generative models for language\nand images. It determines the importance of context elements by comparing each\nelement to the current time step. In this paper, we show that a very\nlightweight convolution can perform competitively to the best reported\nself-attention results. Next, we introduce dynamic convolutions which are\nsimpler and more efficient than self-attention. We predict separate convolution\nkernels based solely on the current time-step in order to determine the\nimportance of context elements. The number of operations required by this\napproach scales linearly in the input length, whereas self-attention is\nquadratic. Experiments on large-scale machine translation, language modeling\nand abstractive summarization show that dynamic convolutions improve over\nstrong self-attention models. On the WMT'14 English-German test set dynamic\nconvolutions achieve a new state of the art of 29.7 BLEU.","url_abs":"http://arxiv.org/abs/1901.10430v2","url_pdf":"http://arxiv.org/pdf/1901.10430v2.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":"pay-less-attention-with-lightweight-and","repo_url":"https://github.com/pytorch/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"pay-less-attention-with-lightweight-and","repo_url":"https://github.com/bytedance/neurst","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"pay-less-attention-with-lightweight-and","repo_url":"https://github.com/dqqcasia/st","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"abstractive-text-summarization","task_name":"Abstractive Text Summarization"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"dropconnect","method_name":"DropConnect"},{"method_slug":"dynamicconv","method_name":"DynamicConv"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"lightconv","method_name":"LightConv"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"dynamicconv","name":"DynamicConv","full_name":"Dynamic Convolution"}],"results":[{"leaderboard":"/sota/abstractive-text-summarization-on-cnn-daily","task":"Abstractive Text Summarization","dataset":"CNN / Daily Mail","model":"Dynamic Conv","rank_in_archive_order":45,"of":53,"metrics":{"ROUGE-1":"39.84","ROUGE-2":"16.25","ROUGE-L":"36.73"},"uses_additional_data":false},{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","task":"Document Summarization","dataset":"CNN / Daily Mail","model":"DynamicConv","rank_in_archive_order":21,"of":26,"metrics":{"ROUGE-1":"39.84","ROUGE-2":"16.25","ROUGE-L":"36.73"},"uses_additional_data":false},{"leaderboard":"/sota/document-summarization-on-cnn-daily-mail","task":"Document Summarization","dataset":"CNN / Daily Mail","model":"LightConv","rank_in_archive_order":22,"of":26,"metrics":{"ROUGE-1":"39.52","ROUGE-2":"15.97","ROUGE-L":"36.51"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"DynamicConv","rank_in_archive_order":15,"of":27,"metrics":{"Number of params":"0.34B","PPL":"26.67"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-iwslt2014-german","task":"Machine Translation","dataset":"IWSLT2014 German-English","model":"DynamicConv","rank_in_archive_order":24,"of":34,"metrics":{"BLEU score":"35.2"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-iwslt2014-german","task":"Machine Translation","dataset":"IWSLT2014 German-English","model":"LightConv","rank_in_archive_order":26,"of":34,"metrics":{"BLEU score":"34.8"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt-2017-english-1","task":"Machine Translation","dataset":"WMT 2017 English-Chinese","model":"DynamicConv","rank_in_archive_order":1,"of":3,"metrics":{"BLEU score":"24.4"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt-2017-english-1","task":"Machine Translation","dataset":"WMT 2017 English-Chinese","model":"LightConv","rank_in_archive_order":2,"of":3,"metrics":{"BLEU score":"24.3"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"DynamicConv","rank_in_archive_order":13,"of":57,"metrics":{"BLEU score":"43.2"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"LightConv","rank_in_archive_order":15,"of":57,"metrics":{"BLEU score":"43.1"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"DynamicConv","rank_in_archive_order":18,"of":91,"metrics":{"BLEU score":"29.7","Number of Params":"213M"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"LightConv","rank_in_archive_order":35,"of":91,"metrics":{"BLEU score":"28.9","Number of Params":"202M"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.10430","atlas_url":"https://app.syntology.ai/?focus=1901.10430","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":"1901.10430"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1901.10430\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1901.10430"},"call":"get_concepts_for_paper(arxiv_id=\"1901.10430\")"}],"by_repo":[{"repo":"pytorch/fairseq","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2105.08206","2105.14850","2203.09163"],"harvested_for_calls":[{"arxiv_id":"2105.08206","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.08206"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.08206\")"},{"arxiv_id":"2105.14850","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2105.14850"},"call":"get_harvested_code_for_paper(arxiv_id=\"2105.14850\")"},{"arxiv_id":"2203.09163","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09163"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09163\")"}]},{"repo":"bytedance/neurst","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"dqqcasia/st","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":"92977283614b2c81d8e01fd330450c20d012c0e2118f7731a5925f5bef76f0e9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}