{"id":"https://openalex.org/W7162998468","doi":"https://doi.org/10.1145/3812835.3814861","title":"Poster: Selective Semantic Cache Transfer for Mobile-Cloud LLM Inference","display_name":"Poster: Selective Semantic Cache Transfer for Mobile-Cloud LLM Inference","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7162998468","doi":"https://doi.org/10.1145/3812835.3814861"},"language":null,"primary_location":{"id":"doi:10.1145/3812835.3814861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3812835.3814861","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 24th Annual International Conference on Mobile Systems, Applications and Services Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3812835.3814861","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018441731","display_name":"Gibum Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gibum Park","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-3659-2615","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137381404","display_name":"Sanghyun Han","orcid":"https://orcid.org/0009-0001-8667-5521"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghyun Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-8667-5521","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137354545","display_name":"Yonghwa Cho","orcid":"https://orcid.org/0009-0002-2430-0270"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yonghwa Cho","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-2430-0270","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080027404","display_name":"Chanjeong Park","orcid":"https://orcid.org/0009-0000-3975-2566"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanjeong Park","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-3975-2566","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020806825","display_name":"Kyunghan Lee","orcid":"https://orcid.org/0000-0001-8647-1476"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I158743462","display_name":"Seoul National University of Education","ror":"https://ror.org/01xts9v65","country_code":"KR","type":"education","lineage":["https://openalex.org/I158743462"]},{"id":"https://openalex.org/I2802457231","display_name":"New Generation University College","ror":"https://ror.org/015aem925","country_code":"ET","type":"education","lineage":["https://openalex.org/I2802457231"]}],"countries":["ET","KR"],"is_corresponding":false,"raw_author_name":"Kyunghan Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8647-1476","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467","https://openalex.org/I2802457231","https://openalex.org/I158743462"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.88772054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.120899997651577,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.120899997651577,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07419999688863754,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.06239999830722809,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7918999791145325},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6546000242233276},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.590399980545044},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.4927999973297119},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4697999954223633},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.445499986410141},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.4309000074863434},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.3986000120639801},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.37869998812675476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8596000075340271},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7918999791145325},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6546000242233276},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.4927999973297119},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.4309000074863434},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.3986000120639801},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.35010001063346863},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.30880001187324524},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.2971000075340271},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3812835.3814861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3812835.3814861","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 24th Annual International Conference on Mobile Systems, Applications and Services Companion","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3812835.3814861","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3812835.3814861","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 24th Annual International Conference on Mobile Systems, Applications and Services Companion","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W3004127093","https://openalex.org/W7162756064"],"related_works":[],"abstract_inverted_index":{"Direct":[0],"key-value":[1],"(KV)":[2],"cache":[3,22,49,66,87],"transfer":[4,116,123],"between":[5],"large":[6],"language":[7,73],"models":[8],"(LLMs)":[9],"is":[10,23],"emerging":[11],"as":[12,51],"a":[13,44,52],"richer":[14],"alternative":[15],"to":[16,99,104],"token":[17],"exchange,":[18],"but":[19],"the":[20,60,70,110,129],"KV":[21],"orders":[24],"of":[25,119,128],"magnitude":[26],"larger":[27],"than":[28,56,102],"tokens,":[29],"and":[30,90],"mobile-cloud":[31],"inference":[32,93],"systems":[33],"are":[34],"not":[35],"yet":[36],"prepared":[37],"for":[38],"this":[39],"shift.":[40],"We":[41],"present":[42],"CAIL,":[43],"system":[45],"that":[46,114],"reframes":[47],"semantic":[48],"delivery":[50],"selection":[53,79],"problem:":[54],"rather":[55,101],"compressing":[57],"or":[58],"scheduling":[59],"entire":[61],"cache,":[62],"CAIL":[63],"identifies":[64],"which":[65,97],"positions":[67,98,120],"genuinely":[68],"help":[69],"edge":[71,92],"small":[72],"model":[74],"(SLM)":[75],"using":[76],"an":[77],"uncertainty-aware":[78],"policy.":[80],"Building":[81],"on":[82,109],"recent":[83],"advances":[84],"in":[85,124],"cross-model":[86],"projection":[88],"(C2C)":[89],"server-assisted":[91],"(SAIL),":[94],"we":[95],"ask":[96],"send":[100],"how":[103],"compress":[105],"them.":[106],"Preliminary":[107],"experiments":[108],"WikiText-103":[111],"dataset":[112],"show":[113],"selective":[115],"at":[117],"25%":[118],"outperforms":[121],"full-cache":[122],"perplexity,":[125],"closing":[126],"28.7%":[127],"SLM-to-LLM":[130],"gap.":[131]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-06-02T00:00:00"}
