{"id":"https://openalex.org/W4415317893","doi":"https://doi.org/10.18653/v1/2026.acl-long.176","title":"Native Hybrid Attention for Efficient Sequence Modeling","display_name":"Native Hybrid Attention for Efficient Sequence Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415317893","doi":"https://doi.org/10.18653/v1/2026.acl-long.176"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.176","pdf_url":"https://aclanthology.org/2026.acl-long.176.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.176.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010481586","display_name":"Jianbang Du","orcid":"https://orcid.org/0000-0003-4960-3155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jusen Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034314444","display_name":"Jiaxi Hu","orcid":"https://orcid.org/0000-0002-7795-334X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxi Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001088762","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0001-7650-3980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037718676","display_name":"Weigao Sun","orcid":"https://orcid.org/0000-0003-2551-924X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weigao Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622622","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0001-8754-5457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01561336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3826","last_page":"3842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9532999992370605,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9532999992370605,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9348999857902527,"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/T10028","display_name":"Topic Modeling","score":0.9280999898910522,"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/transformer","display_name":"Transformer","score":0.6201000213623047},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5766000151634216},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.37380000948905945},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.33309999108314514},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.32409998774528503},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6948999762535095},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6201000213623047},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5766000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4625000059604645},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.176","pdf_url":"https://aclanthology.org/2026.acl-long.176.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.07019","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07019","pdf_url":"https://arxiv.org/pdf/2510.07019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.07019","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07019","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.176","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.176","pdf_url":"https://aclanthology.org/2026.acl-long.176.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415317893.pdf","grobid_xml":"https://content.openalex.org/works/W4415317893.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transformers":[0,129],"excel":[1],"at":[2],"sequence":[3],"modeling":[4],"but":[5,15],"face":[6],"quadratic":[7],"complexity,":[8],"while":[9,118,151],"linear":[10,36,61,114],"attention":[11,39,75,117],"offers":[12],"improved":[13],"efficiency":[14,154],"often":[16],"compromises":[17],"recall":[18],"accuracy":[19,150],"over":[20,80],"long":[21],"contexts.In":[22],"this":[23],"work,":[24],"we":[25],"introduce":[26],"Native":[27],"Hybrid":[28],"Attention":[29],"(NHA),":[30],"a":[31,48,60,70,101],"novel":[32],"hybrid":[33,132],"architecture":[34],"of":[35],"and":[37,63,83,87,115,130,136],"full":[38,116],"that":[40,126],"integrates":[41],"both":[42],"intra":[43],"&":[44],"inter-layer":[45,96],"hybridization":[46],"into":[47],"unified":[49],"layer":[50],"design.NHA":[51],"maintains":[52],"longterm":[53],"context":[54],"in":[55],"key-value":[56],"slots":[57],"updated":[58],"by":[59],"RNN,":[62],"augments":[64],"them":[65],"with":[66,146],"shortterm":[67],"tokens":[68],"from":[69],"sliding":[71,105],"window.A":[72],"single":[73,102],"softmax":[74],"operation":[76],"is":[77,98],"then":[78],"applied":[79],"all":[81,120],"keys":[82],"values,":[84],"enabling":[85],"pertoken":[86],"per-head":[88],"context-dependent":[89],"weighting":[90],"without":[91],"requiring":[92],"additional":[93],"fusion":[94],"parameters.The":[95],"behavior":[97],"controlled":[99],"through":[100],"hyperparameter,":[103],"the":[104],"window":[106],"size,":[107],"which":[108],"allows":[109],"smooth":[110],"adjustment":[111],"between":[112],"purely":[113],"keeping":[119],"layers":[121],"structurally":[122,144],"uniform.Experimental":[123],"results":[124],"show":[125],"NHA":[127],"surpasses":[128],"other":[131],"baselines":[133],"on":[134],"recall-intensive":[135],"commonsense":[137],"reasoning":[138],"tasks.Furthermore,":[139],"pretrained":[140],"LLMs":[141],"can":[142],"be":[143],"hybridized":[145],"NHA,":[147],"achieving":[148],"competitive":[149],"delivering":[152],"significant":[153],"gains.":[155]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-18T00:00:00"}