{"id":"https://openalex.org/W7162756064","doi":"https://doi.org/10.1145/3745756.3809224","title":"SAIL: Redesigning Collaborative Language Inference with a Single Server-to-Mobile Handoff","display_name":"SAIL: Redesigning Collaborative Language Inference with a Single Server-to-Mobile Handoff","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162756064","doi":"https://doi.org/10.1145/3745756.3809224"},"language":null,"primary_location":{"id":"doi:10.1145/3745756.3809224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809224","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","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3745756.3809224","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":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-3659-2615","affiliations":[{"raw_affiliation_string":"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":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-8667-5521","affiliations":[{"raw_affiliation_string":"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":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-2430-0270","affiliations":[{"raw_affiliation_string":"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":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-3975-2566","affiliations":[{"raw_affiliation_string":"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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyunghan Lee","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8647-1476","affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9128,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97367978,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"580","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.20090000331401825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.20090000331401825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.04280000180006027,"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":0.04270000010728836,"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/inference","display_name":"Inference","score":0.6550999879837036},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6534000039100647},{"id":"https://openalex.org/keywords/handover","display_name":"Handover","score":0.6517000198364258},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5519000291824341},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.46790000796318054},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4544999897480011},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.45080000162124634},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.37229999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504999876022339},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6534000039100647},{"id":"https://openalex.org/C111852164","wikidata":"https://www.wikidata.org/wiki/Q1414679","display_name":"Handover","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.48750001192092896},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.45080000162124634},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C38601921","wikidata":"https://www.wikidata.org/wiki/Q1757693","display_name":"Protocol stack","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3745756.3809224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809224","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","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3745756.3809224","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3745756.3809224","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","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2058373514","https://openalex.org/W2605258629","https://openalex.org/W2891920428","https://openalex.org/W4399534541","https://openalex.org/W4409348018"],"related_works":[],"abstract_inverted_index":{"While":[0],"on-device":[1,153],"small":[2],"language":[3,22],"models":[4,23],"(SLMs)":[5],"enable":[6,183],"responsive":[7],"inference,":[8],"they":[9],"often":[10],"lack":[11],"the":[12,96,105,119,131,136,145,156,160],"accuracy":[13,27,77,190,199],"required":[14],"for":[15,32,118],"complex":[16],"reasoning":[17],"tasks;":[18],"conversely,":[19],"server-based":[20],"large":[21],"(LLMs)":[24],"deliver":[25,186],"high":[26,76],"but":[28],"incur":[29],"prohibitive":[30],"latency":[31,80,204],"real-time":[33],"mobile":[34,106,193],"applications.":[35],"Collaborative":[36],"inference":[37,71],"approaches,":[38],"such":[39],"as":[40],"split":[41],"computing":[42],"and":[43,78,100,159,166,172,209],"speculative":[44],"decoding,":[45],"promise":[46],"to":[47,104,121,141,175,185,188],"bridge":[48],"this":[49],"gap,":[50],"yet":[51],"both":[52,75],"require":[53],"repeated":[54],"network":[55,171],"synchronization":[56],"during":[57],"generation,":[58],"accumulating":[59],"delays":[60],"that":[61,73],"negate":[62],"their":[63],"computational":[64],"benefits.":[65],"We":[66],"present":[67],"SAIL,":[68],"a":[69,82,92,111],"collaborative":[70],"framework":[72],"achieves":[74],"low":[79],"through":[81,127],"strategy":[83],"we":[84],"term":[85],"Prefix":[86],"Handoff":[87],"Inference":[88],"(PHI).":[89],"In":[90],"PHI,":[91],"server":[93,157,173,197],"LLM":[94,198],"generates":[95],"difficult":[97],"early":[98],"tokens":[99],"hands":[101],"off":[102],"completion":[103],"SLM,":[107],"consolidating":[108],"communication":[109],"into":[110],"single":[112],"handoff":[113,132],"while":[114,154,201],"providing":[115],"sufficient":[116],"context":[117],"SLM":[120],"maintain":[122],"accuracy.":[123],"SAIL":[124,184],"operationalizes":[125],"PHI":[126],"three":[128],"core":[129],"modules:":[130],"decision":[133],"module":[134,148,163],"determining":[135],"optimal":[137],"prefix":[138],"length":[139],"tailored":[140],"each":[142],"query's":[143],"difficulty,":[144],"branch":[146,167],"prediction":[147,168],"speculatively":[149],"generating":[150],"candidate":[151],"continuations":[152],"awaiting":[155],"prefix,":[158],"adaptive":[161],"control":[162],"coordinating":[164],"hand-off":[165],"under":[169],"fluctuating":[170],"conditions":[174],"meet":[176],"service":[177],"level":[178,211],"objectives.":[179],"Together,":[180],"these":[181],"modules":[182],"up":[187],"76%":[189],"improvement":[191],"over":[192],"SLMs":[194],"with":[195],"98.9%":[196],"retention,":[200],"strictly":[202],"meeting":[203],"constraints":[205],"across":[206],"translation,":[207],"math,":[208],"expert":[210],"QA.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}
