{"id":"https://openalex.org/W7164490748","doi":"https://doi.org/10.1109/msp.2026.3682808","title":"Sequence Modeling Architectures: Foundations [Special Issue on the Mathematics of Deep Learning]","display_name":"Sequence Modeling Architectures: Foundations [Special Issue on the Mathematics of Deep Learning]","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7164490748","doi":"https://doi.org/10.1109/msp.2026.3682808"},"language":null,"primary_location":{"id":"doi:10.1109/msp.2026.3682808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2026.3682808","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081031189","display_name":"Felix Sarnthein","orcid":null},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Sarnthein","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems, ELLIS Institute T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":"https://orcid.org/0009-0004-0010-4472","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, ELLIS Institute T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034947184","display_name":"Arshia Afzal","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Arshia Afzal","raw_affiliation_strings":["Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043910056","display_name":"Razvan Pascanu","orcid":"https://orcid.org/0000-0002-5470-1238"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Razvan Pascanu","raw_affiliation_strings":["Google DeepMind, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081990239","display_name":"Antonio Orvieto","orcid":"https://orcid.org/0000-0002-1914-0367"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Antonio Orvieto","raw_affiliation_strings":["ELLIS Institute T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1914-0367","affiliations":[{"raw_affiliation_string":"ELLIS Institute T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041145688","display_name":"\u00c7a\u011flar G\u00fcl\u00e7ehre","orcid":"https://orcid.org/0009-0003-4124-1687"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Caglar Gulcehre","raw_affiliation_strings":["Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049400969","display_name":"Jonas Geiping","orcid":null},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonas Geiping","raw_affiliation_strings":["ELLIS Institute T&#x00FC;bingen, T&#x00FC;bingen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2752-574X","affiliations":[{"raw_affiliation_string":"ELLIS Institute T&#x00FC;bingen, T&#x00FC;bingen, Germany","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017601648","display_name":"Francesco Tonin","orcid":"https://orcid.org/0000-0002-5644-0086"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Francesco Tonin","raw_affiliation_strings":["Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5644-0086","affiliations":[{"raw_affiliation_string":"Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025386668","display_name":"Albert Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Gu","raw_affiliation_strings":["Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027059837","display_name":"Volkan Cevher","orcid":"https://orcid.org/0000-0002-5004-201X"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Volkan Cevher","raw_affiliation_strings":["Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5004-201X","affiliations":[{"raw_affiliation_string":"Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94779785,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"3","first_page":"115","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.06350000202655792,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.06350000202655792,"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/T10320","display_name":"Neural Networks and Applications","score":0.0364999994635582,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.026200000196695328,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6295999884605408},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3598000109195709},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.33149999380111694},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.30809998512268066},{"id":"https://openalex.org/keywords/calculus","display_name":"Calculus (dental)","score":0.267300009727478}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6171000003814697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45179998874664307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4052000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2768000066280365},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C153046414","wikidata":"https://www.wikidata.org/wiki/Q12482","display_name":"Set theory","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2026.3682808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2026.3682808","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4489926587","display_name":null,"funder_award_id":"2000-1-240094","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1485981043","https://openalex.org/W1832693441","https://openalex.org/W2064675550","https://openalex.org/W2105934661","https://openalex.org/W2110485445","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W3213111742","https://openalex.org/W4385245566","https://openalex.org/W4388979610","https://openalex.org/W4413146579","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,7,46,90],"success":[2],"of":[3,27,48,99,128],"deep":[4,29],"learning":[5,30],"in":[6,97],"past":[8],"decade,":[9],"neural":[10,54],"networks":[11,55],"transitioned":[12],"from":[13,52],"simple":[14],"layer":[15],"stacking":[16],"to":[17,57,88],"sophisticated,":[18],"highly":[19],"complex":[20],"designs.":[21],"This":[22],"article":[23],"provides":[24],"an":[25],"overview":[26],"such":[28,68,111],"architectures":[31,93],"for":[32],"sequence":[33,50,82],"modeling,":[34],"with":[35],"a":[36,85],"focus":[37],"on":[38,125],"their":[39,65,118,123],"core":[40],"mathematical":[41],"principles:":[42],"1)":[43],"we":[44,121],"review":[45],"evolution":[47],"common":[49],"models":[51,62],"recurrent":[53],"(RNNs),":[56],"Transformers,":[58],"and":[59,72,94,102,114,136],"modern":[60],"state-space":[61],"(SSMs),":[63],"exploring":[64],"foundational":[66],"components":[67],"as":[69,84,112],"gating,":[70],"attention,":[71],"linear":[73,81],"dynamical":[74],"systems":[75],"mechanisms.":[76],"2)":[77],"We":[78,106],"present":[79],"general":[80],"mixers":[83],"unifying":[86],"framework":[87],"highlight":[89],"relationship":[91],"between":[92],"compare":[95],"them":[96],"terms":[98],"inductive":[100],"biases":[101],"algorithmic":[103],"complexity.":[104],"3)":[105],"examine":[107],"how":[108],"practical":[109],"considerations":[110],"parallelizability":[113],"hardware":[115],"awareness":[116],"dictate":[117],"success.":[119],"Finally,":[120],"discuss":[122],"impact":[124],"diverse":[126],"fields":[127],"signal":[129],"processing,":[130],"including":[131],"time-series":[132],"analysis,":[133],"natural":[134],"language,":[135],"computer":[137],"vision.":[138]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-06-13T00:00:00"}
