{"id":"https://openalex.org/W4409364153","doi":"https://doi.org/10.1609/aaai.v39i17.34024","title":"On the Power of Convolution-Augmented Transformer","display_name":"On the Power of Convolution-Augmented Transformer","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409364153","doi":"https://doi.org/10.1609/aaai.v39i17.34024"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i17.34024","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i17.34024","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34024/36179","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34024/36179","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004058458","display_name":"Mingchen Li","orcid":"https://orcid.org/0009-0007-3999-0450"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingchen Li","raw_affiliation_strings":["University of Michigan - Ann Arbor"],"affiliations":[{"raw_affiliation_string":"University of Michigan - Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101979632","display_name":"Xuechen Zhang","orcid":"https://orcid.org/0000-0002-0907-0027"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuechen Zhang","raw_affiliation_strings":["University of Michigan - Ann Arbor"],"affiliations":[{"raw_affiliation_string":"University of Michigan - Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113142777","display_name":"Yixiao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixiao Huang","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050547472","display_name":"Samet Oymak","orcid":"https://orcid.org/0000-0001-5203-0752"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samet Oymak","raw_affiliation_strings":["University of Michigan - Ann Arbor"],"affiliations":[{"raw_affiliation_string":"University of Michigan - Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004058458"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19724771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"17","first_page":"18393","last_page":"18402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7692000269889832,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7692000269889832,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.6772000193595886,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10573","display_name":"Power Quality and Harmonics","score":0.6420000195503235,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.480352520942688},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.41490742564201355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4068840742111206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3457653522491455},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3120775818824768},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14832791686058044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.142461359500885},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12937253713607788}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.480352520942688},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.41490742564201355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4068840742111206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3457653522491455},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3120775818824768},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14832791686058044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.142461359500885},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12937253713607788},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i17.34024","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i17.34024","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34024/36179","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i17.34024","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i17.34024","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34024/36179","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1454431072","display_name":"CAREER: Foundations of Resource Efficient Machine Learning","funder_award_id":"2046816","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3761471208","display_name":"Collaborative Research:  Biomass Burning Emissions Over Southern Africa","funder_award_id":"0001424","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5638980531","display_name":null,"funder_award_id":"2008020","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7331127713","display_name":"Collaborative Research: CIF:Medium:Theoretical Foundations of Compositional Learning in Transformer Models","funder_award_id":"2403075","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409364153.pdf","grobid_xml":"https://content.openalex.org/works/W4409364153.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2864363823"],"abstract_inverted_index":{"The":[0],"transformer":[1],"architecture":[2],"has":[3],"catalyzed":[4],"revolutionary":[5],"advances":[6],"in":[7,45],"language":[8,149],"modeling.":[9],"However,":[10],"recent":[11],"architectural":[12],"recipes,":[13],"such":[14,74],"as":[15,75],"state-space":[16],"models,":[17],"have":[18],"bridged":[19],"the":[20,28,46,58,61,65,69,83,115,122,148],"performance":[21],"gap.":[22],"Motivated":[23],"by":[24,109,120],"this,":[25],"we":[26,55],"examine":[27],"benefits":[29],"of":[30,49,60,68],"Convolution-Augmented":[31],"Transformer":[32],"(CAT)":[33],"for":[34,117],"recall,":[35],"copying,":[36],"and":[37,87,107,125,139,143],"length":[38,98],"generalization":[39],"tasks.":[40],"CAT":[41,79,142],"incorporates":[42],"convolutional":[43],"filters":[44],"K/Q/V":[47],"embeddings":[48],"an":[50],"attention":[51,108,119],"layer.":[52],"Through":[53],"CAT,":[54],"show":[56],"that":[57,141],"locality":[59],"convolution":[62,106,112],"synergizes":[63],"with":[64],"global":[66],"view":[67],"attention.":[70],"Unlike":[71],"comparable":[72],"architectures,":[73],"Mamba":[76],"or":[77],"transformer,":[78],"can":[80,113],"provably":[81],"solve":[82],"associative":[84],"recall":[85],"(AR)":[86],"copying":[88],"tasks":[89],"using":[90],"a":[91],"single":[92],"layer":[93],"while":[94],"also":[95,101],"enjoying":[96],"guaranteed":[97],"generalization.":[99],"We":[100],"establish":[102],"computational":[103],"tradeoffs":[104],"between":[105],"characterizing":[110],"how":[111],"mitigate":[114],"need":[116],"full":[118],"summarizing":[121],"context":[123],"window":[124],"creating":[126],"salient":[127],"summary":[128],"tokens":[129],"to":[130],"attend.":[131],"Evaluations":[132],"on":[133],"real":[134],"datasets":[135],"corroborate":[136],"our":[137],"findings":[138],"demonstrate":[140],"its":[144],"variations":[145],"indeed":[146],"enhance":[147],"modeling":[150],"performance.":[151]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}