{"id":"https://openalex.org/W7160601778","doi":"https://doi.org/10.1145/3774906.3800479","title":"An Efficient Context Management System for On-Device LLMaaS","display_name":"An Efficient Context Management System for On-Device LLMaaS","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160601778","doi":"https://doi.org/10.1145/3774906.3800479"},"language":null,"primary_location":{"id":"doi:10.1145/3774906.3800479","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774906.3800479","pdf_url":null,"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 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774906.3800479","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101293258","display_name":"Wangsong Yin","orcid":null},"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":"Wangsong Yin","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-6242-4368","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135713337","display_name":"Mengwei Xu","orcid":"https://orcid.org/0000-0001-6271-6993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengwei Xu","raw_affiliation_strings":["BUPT, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6271-6993","affiliations":[{"raw_affiliation_string":"BUPT, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628298","display_name":"Yuanchun Li","orcid":"https://orcid.org/0000-0002-1591-2526"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanchun Li","raw_affiliation_strings":["Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1591-2526","affiliations":[{"raw_affiliation_string":"Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135649960","display_name":"Xuanzhe Liu","orcid":"https://orcid.org/0000-0002-7908-8484"},"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":"Xuanzhe Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7908-8484","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.71784485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"377","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.11900000274181366,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.11900000274181366,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.10970000177621841,"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"}},{"id":"https://openalex.org/T12799","display_name":"Mobile and Web Applications","score":0.07199999690055847,"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/context","display_name":"Context (archaeology)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4284000098705292},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4117000102996826},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4075999855995178},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.3758000135421753},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.37139999866485596},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.36959999799728394},{"id":"https://openalex.org/keywords/mobile-service","display_name":"Mobile service","score":0.35920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2780559388","wikidata":"https://www.wikidata.org/wiki/Q1247189","display_name":"Mobile service","level":3,"score":0.35920000076293945},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C144097018","wikidata":"https://www.wikidata.org/wiki/Q4329404","display_name":"Service discovery","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C58546491","wikidata":"https://www.wikidata.org/wiki/Q1150207","display_name":"Competitive advantage","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C200789330","wikidata":"https://www.wikidata.org/wiki/Q7000834","display_name":"Network Functions Virtualization","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C15587899","wikidata":"https://www.wikidata.org/wiki/Q7455812","display_name":"Service system","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774906.3800479","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774906.3800479","pdf_url":null,"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 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774906.3800479","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774906.3800479","pdf_url":null,"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 2026 ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8414340155","display_name":null,"funder_award_id":"62325201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1964531213","https://openalex.org/W2005697616","https://openalex.org/W2073601450","https://openalex.org/W2102346651","https://openalex.org/W2126143263","https://openalex.org/W2129652681","https://openalex.org/W2133253683","https://openalex.org/W2251939518","https://openalex.org/W2625865100","https://openalex.org/W2759112196","https://openalex.org/W2760656271","https://openalex.org/W2888482885","https://openalex.org/W2963748441","https://openalex.org/W2979826702","https://openalex.org/W2989743967","https://openalex.org/W2994850640","https://openalex.org/W4318541554","https://openalex.org/W4366549767","https://openalex.org/W4385567149","https://openalex.org/W4387321091","https://openalex.org/W4395685061","https://openalex.org/W4399121418","https://openalex.org/W4401176373","https://openalex.org/W4402671659","https://openalex.org/W4404331863","https://openalex.org/W4405717632","https://openalex.org/W6890025973"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"renovating":[5],"the":[6,27,85,90,127,132,149,162],"mobile":[7,11,22,33],"AI,":[8],"catalyzing":[9],"novel":[10,103],"applications":[12],"such":[13],"as":[14,31,40],"UI":[15],"task":[16],"automation.":[17],"A":[18],"new":[19],"paradigm":[20],"of":[21],"AI":[23],"ecosystem":[24],"emerges":[25],"in":[26,72],"LLM":[28,30,38,75,86,128],"era:":[29],"a":[32,41,56,66],"OS":[34],"service":[35,43],"(LLMaaS),":[36],"where":[37],"runs":[39],"system":[42,67],"and":[44,50,97,125,143,171],"exposes":[45],"its":[46],"functionality":[47],"(language":[48],"understanding":[49],"generation)":[51],"to":[52,112,130,145,147,168,177],"third-party":[53],"apps.":[54],"As":[55],"giant":[57],"step":[58],"towards":[59],"on-device":[60],"LLMaaS,":[61],"this":[62],"work":[63],"presents":[64],"Libra,":[65],"that":[68],"tackles":[69],"with":[70],"challenge":[71],"managing":[73],"persistent":[74],"contexts":[76,87,129],"(KV":[77],"cache)":[78],"under":[79],"tight":[80],"memory":[81],"constraint.":[82],"Libra":[83,160],"manages":[84],"based":[88,115],"on":[89,116,156,172],"fine-grained,":[91],"chunk-wise,":[92],"globally-optimized":[93],"KV":[94],"cache":[95],"compression":[96,110],"swapping.":[98],"Specifically,":[99],"it":[100],"integrates":[101],"three":[102],"techniques:":[104],"(1)":[105],"Tolerance-Aware":[106],"Compression":[107],"applies":[108],"different":[109],"rates":[111],"each":[113],"chunk":[114],"their":[117],"attention":[118],"scores.":[119],"(2)":[120],"Swapping-Recompute":[121],"Pipeline":[122],"simultaneously":[123],"swaps":[124],"recomputes":[126],"improve":[131],"hardware":[133],"resource":[134],"utilization.":[135],"(3)":[136],"Chunk":[137],"Lifecycle":[138],"Management":[139],"judiciously":[140],"determines":[141],"when":[142],"what":[144],"evict":[146],"reduce":[148],"context":[150,163],"switching":[151,164],"overhead.":[152],"Through":[153],"comprehensive":[154],"experiments":[155],"various":[157],"edge":[158],"devices,":[159],"reduces":[161],"latency":[165],"by":[166],"up":[167],"20":[169],"\u00d7":[170,175],"average":[173],"9.7":[174],"compared":[176],"competitive":[178],"baselines.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-09T00:00:00"}