{"id":"https://openalex.org/W4412889616","doi":"https://doi.org/10.18653/v1/2025.acl-long.1597","title":"Towards Economical Inference: Enabling DeepSeek\u2019s Multi-Head Latent Attention in Any Transformer-based LLMs","display_name":"Towards Economical Inference: Enabling DeepSeek\u2019s Multi-Head Latent Attention in Any Transformer-based LLMs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889616","doi":"https://doi.org/10.18653/v1/2025.acl-long.1597"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1597","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1597","pdf_url":"https://aclanthology.org/2025.acl-long.1597.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1597.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101794864","display_name":"Tao Ji","orcid":"https://orcid.org/0000-0002-7671-5921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078005520","display_name":"Bin Guo","orcid":"https://orcid.org/0000-0001-6097-2467"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118458994","display_name":"Yuanbin Wu","orcid":"https://orcid.org/0000-0002-4665-6350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanbin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030290474","display_name":"Qipeng Guo","orcid":"https://orcid.org/0000-0001-7113-651X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qipeng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181815","display_name":"Shenlixing Shenlixing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenlixing Shenlixing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181816","display_name":"Chenzhan Chenzhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenzhan Chenzhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014306843","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-5203-8778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058353652","display_name":"Tao Gui","orcid":"https://orcid.org/0000-0002-6154-0751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Gui","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":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33313","last_page":"33328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9846000075340271,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9700000286102295,"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/inference","display_name":"Inference","score":0.6652024388313293},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6525850296020508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5354685187339783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2827731966972351},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12151622772216797},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11583617329597473},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06601524353027344}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6652024388313293},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6525850296020508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5354685187339783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2827731966972351},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12151622772216797},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11583617329597473},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06601524353027344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1597","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1597","pdf_url":"https://aclanthology.org/2025.acl-long.1597.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1597","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1597","pdf_url":"https://aclanthology.org/2025.acl-long.1597.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3471270673","display_name":null,"funder_award_id":"61976056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G655273820","display_name":null,"funder_award_id":"62076069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321851","display_name":"Fudan University","ror":"https://ror.org/013q1eq08"},{"id":"https://openalex.org/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null},{"id":"https://openalex.org/F4320335796","display_name":"Program of Shanghai Academic Research Leader","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889616.pdf","grobid_xml":"https://content.openalex.org/works/W4412889616.grobid-xml"},"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/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Tao":[0,16],"Ji,":[1],"Bin":[2],"Guo,":[3,7],"Yuanbin":[4],"Wu,":[5],"Qipeng":[6],"Shenlixing":[8],"Shenlixing,":[9],"Chenzhan":[10],"Chenzhan,":[11],"Xipeng":[12],"Qiu,":[13],"Qi":[14],"Zhang,":[15],"Gui.":[17],"Proceedings":[18],"of":[19,24],"the":[20,25],"63rd":[21],"Annual":[22],"Meeting":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"1:":[31],"Long":[32],"Papers).":[33],"2025.":[34]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
