{"id":"https://openalex.org/W4403488193","doi":"https://doi.org/10.3233/faia240593","title":"MixCon: A Hybrid Architecture for Efficient and Adaptive Sequence Modeling","display_name":"MixCon: A Hybrid Architecture for Efficient and Adaptive Sequence Modeling","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488193","doi":"https://doi.org/10.3233/faia240593"},"language":"en","primary_location":{"id":"doi:10.3233/faia240593","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240593","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240593","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240593","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100646751","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0002-3780-7858"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016399094","display_name":"Zhouchen Lin","orcid":"https://orcid.org/0000-0003-1493-7569"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouchen Lin","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University","Pazhou Laboratory (Huangpu), Guangzhou, Guangdong, China","State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Pazhou Laboratory (Huangpu), Guangzhou, Guangdong, China","institution_ids":[]},{"raw_affiliation_string":"State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47089947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.6589111089706421},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.581225574016571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5302186608314514},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3631584346294403},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1435466706752777},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11275997757911682},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.045554131269454956}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6589111089706421},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.581225574016571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5302186608314514},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3631584346294403},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1435466706752777},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11275997757911682},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.045554131269454956},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240593","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240593","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240593","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240593","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240593","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240593","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403488193.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Sequence":[0],"modeling":[1,32,41,177],"is":[2],"a":[3,37,56,63,67,105,140,159],"critical":[4],"task":[5],"in":[6,26,87,174],"various":[7],"domains":[8],"such":[9],"as":[10],"natural":[11],"language":[12],"processing,":[13],"speech":[14],"recognition,":[15],"and":[16,30,66,96,108,125,165],"time":[17],"series":[18],"analysis.":[19],"The":[20,49,113],"existing":[21],"models":[22],"still":[23],"face":[24],"challenges":[25],"capturing":[27],"long-range":[28],"dependencies":[29],"efficiently":[31],"sequences.":[33],"This":[34],"paper":[35],"proposes":[36],"novel":[38],"hybrid":[39],"sequence":[40,111,176],"architecture":[42,54,93],"called":[43],"MixCon":[44,50,92,146],"to":[45,77,110,136,172],"address":[46],"these":[47],"challenges.":[48],"(Mixture":[51],"of":[52,69,80,134,161],"Conba)":[53],"combines":[55],"Transformer":[57],"layer":[58],"based":[59],"on":[60,139,150,163,167],"attention":[61,82],"mechanism,":[62,83],"Conba":[64],"layer,":[65],"Mixture":[68],"Experts":[70],"(MoE)":[71],"module.":[72],"We":[73],"apply":[74],"this":[75],"idea":[76],"the":[78,81,91],"design":[79],"achieving":[84],"significant":[85],"improvements":[86],"computational":[88],"efficiency.":[89],"Additionally,":[90],"integrates":[94],"feedback":[95],"adaptive":[97],"control":[98,102],"mechanism":[99],"inspired":[100],"by":[101,122,127,154],"theory,":[103],"providing":[104],"new":[106],"perspective":[107],"approach":[109],"modeling.":[112],"experimental":[114],"results":[115],"demonstrate":[116],"MixCon\u2019s":[117],"superior":[118],"throughput,":[119],"outperforming":[120],"Mixtral":[121],"4.5":[123],"times":[124,129],"Jamba":[126],"1.5":[128],"when":[130],"processing":[131],"lengthy":[132],"sequences":[133],"up":[135],"128K":[137],"tokens":[138],"single":[141],"A800":[142],"80GB":[143],"GPU.":[144],"Moreover,":[145],"achieves":[147],"top-tier":[148],"scores":[149],"academic":[151],"benchmarks,":[152],"exemplified":[153],"its":[155,170],"outstanding":[156],"performance":[157],"with":[158],"score":[160],"87.9%":[162],"HellaSwag":[164],"83.4%":[166],"WinoGrande,":[168],"showcasing":[169],"capability":[171],"excel":[173],"complex":[175],"tasks.":[178]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}