{"id":"https://openalex.org/W7166679604","doi":"https://doi.org/10.1109/ipdps65963.2026.00058","title":"Near-Zero Cost KV Cache Compression for Large Language Model Inference","display_name":"Near-Zero Cost KV Cache Compression for Large Language Model Inference","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7166679604","doi":"https://doi.org/10.1109/ipdps65963.2026.00058"},"language":null,"primary_location":{"id":"doi:10.1109/ipdps65963.2026.00058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps65963.2026.00058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5015061310","display_name":"B O Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyuan Zhang","raw_affiliation_strings":["Indiana University,Bloomington,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050662958","display_name":"Ding Zhou","orcid":"https://orcid.org/0000-0002-4053-3712"},"institutions":[{"id":"https://openalex.org/I4210091247","display_name":"University for Peace","ror":"https://ror.org/00cxrw595","country_code":"CR","type":"education","lineage":["https://openalex.org/I1286959531","https://openalex.org/I4210091247"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Ding Zhou","raw_affiliation_strings":["ByteDance,San Jose,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,San Jose,USA","institution_ids":["https://openalex.org/I4210091247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074539156","display_name":"Yafan Huang","orcid":"https://orcid.org/0000-0001-7370-6766"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yafan Huang","raw_affiliation_strings":["University of Iowa,Iowa City,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Iowa,Iowa City,USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025805788","display_name":"Shihui Song","orcid":"https://orcid.org/0009-0007-9426-8591"},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihui Song","raw_affiliation_strings":["University of Iowa,Iowa City,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Iowa,Iowa City,USA","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729574","display_name":"Hao Feng","orcid":"https://orcid.org/0000-0001-5404-7136"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Feng","raw_affiliation_strings":["Indiana University,Bloomington,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139708237","display_name":"Jinda Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinda Jia","raw_affiliation_strings":["Indiana University,Bloomington,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Bloomington,USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139694858","display_name":"Chengming Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121988","display_name":"Film Independent","ror":"https://ror.org/036cy3843","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210121988"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengming Zhang","raw_affiliation_strings":["Independent Researcher,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher,USA","institution_ids":["https://openalex.org/I4210121988"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139675453","display_name":"Zhi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091247","display_name":"University for Peace","ror":"https://ror.org/00cxrw595","country_code":"CR","type":"education","lineage":["https://openalex.org/I1286959531","https://openalex.org/I4210091247"]}],"countries":["CR"],"is_corresponding":false,"raw_author_name":"Zhi Zhang","raw_affiliation_strings":["ByteDance,San Jose,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,San Jose,USA","institution_ids":["https://openalex.org/I4210091247"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.78189169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"612","last_page":"625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.24570000171661377,"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":0.24570000171661377,"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":0.164900004863739,"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/T14347","display_name":"Big Data and Digital Economy","score":0.0754999965429306,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/compression","display_name":"Compression (physics)","score":0.48649999499320984},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.47940000891685486},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44589999318122864},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41190001368522644},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504000067710876},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2985999882221222},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps65963.2026.00058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps65963.2026.00058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W2052440657","https://openalex.org/W2060108852","https://openalex.org/W2107745473","https://openalex.org/W2122962290","https://openalex.org/W3138054712","https://openalex.org/W4367176010","https://openalex.org/W4376864771","https://openalex.org/W4388105305","https://openalex.org/W4388979610","https://openalex.org/W4391876619","https://openalex.org/W4399694067","https://openalex.org/W4402671258","https://openalex.org/W4402683788","https://openalex.org/W4402683949","https://openalex.org/W4405756077","https://openalex.org/W4405756379","https://openalex.org/W4410040007","https://openalex.org/W4412886690","https://openalex.org/W4413411750","https://openalex.org/W4415795958","https://openalex.org/W4415797147","https://openalex.org/W4415799038","https://openalex.org/W4415799217","https://openalex.org/W7133224090","https://openalex.org/W7133244816"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-01T00:00:00"}
