{"id":"https://openalex.org/W7204040643","doi":"https://doi.org/10.1007/978-981-92-4805-6_5","title":"JSQKV: Joint Sparsification and Quantization for KV-Cache Compression and Decode Acceleration","display_name":"JSQKV: Joint Sparsification and Quantization for KV-Cache Compression and Decode Acceleration","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204040643","doi":"https://doi.org/10.1007/978-981-92-4805-6_5"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-4805-6_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-4805-6_5","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5147909348","display_name":"Hao Zhang","orcid":"https://orcid.org/0009-0001-1044-0312"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0001-1044-0312","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045499166","display_name":"Xiaoli Gong","orcid":"https://orcid.org/0000-0002-9836-558X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoli Gong","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-9836-558X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327721","display_name":"Haoran Li","orcid":"https://orcid.org/0000-0002-2379-1541"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070555846","display_name":"Huayou Su","orcid":"https://orcid.org/0000-0002-3587-0917"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huayou Su","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011155701","display_name":"Qingxia Chen","orcid":"https://orcid.org/0000-0003-0507-1847"},"institutions":[{"id":"https://openalex.org/I194716290","display_name":"China Academy of Space Technology","ror":"https://ror.org/025397a59","country_code":"CN","type":"government","lineage":["https://openalex.org/I194716290","https://openalex.org/I2802615301"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxia Chen","raw_affiliation_strings":["Qian Xuesen Laboratory of Space Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qian Xuesen Laboratory of Space Technology, Beijing, China","institution_ids":["https://openalex.org/I194716290"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101829311","display_name":"Jin Zhang","orcid":"https://orcid.org/0000-0001-9086-1178"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Zhang","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-9086-1178","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045499166"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6021999716758728},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5964999794960022},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5823000073432922},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5573999881744385},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.531499981880188},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"Compressed sensing","score":0.5288000106811523},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.46790000796318054},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.42739999294281006},{"id":"https://openalex.org/keywords/hadamard-transform","display_name":"Hadamard transform","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8615999817848206},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5823000073432922},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5789999961853027},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5573999881744385},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.531499981880188},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C60292330","wikidata":"https://www.wikidata.org/wiki/Q1014065","display_name":"Hadamard transform","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C153338461","wikidata":"https://www.wikidata.org/wiki/Q2651","display_name":"Arithmetic coding","level":4,"score":0.40049999952316284},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.36559998989105225},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34880000352859497},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.34459999203681946},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C156872377","wikidata":"https://www.wikidata.org/wiki/Q6786281","display_name":"Matching pursuit","level":3,"score":0.2687000036239624},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-4805-6_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-4805-6_5","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3190126809","https://openalex.org/W4387321091","https://openalex.org/W4415796210","https://openalex.org/W4415798906","https://openalex.org/W4415799217","https://openalex.org/W7092177792","https://openalex.org/W7196959279"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2026-08-24T00:00:00"}
