{"id":"https://openalex.org/W4415480994","doi":"https://doi.org/10.1145/3704413.3764429","title":"Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings","display_name":"Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415480994","doi":"https://doi.org/10.1145/3704413.3764429"},"language":null,"primary_location":{"id":"doi:10.1145/3704413.3764429","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704413.3764429","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704413.3764429","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 Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3704413.3764429","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022883297","display_name":"Liangqi Yuan","orcid":"https://orcid.org/0000-0002-9994-6773"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangqi Yuan","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0002-9994-6773","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403023","display_name":"Dong-Jun Han","orcid":"https://orcid.org/0000-0003-2970-7336"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Jun Han","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2970-7336","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443968","display_name":"Shiqiang Wang","orcid":"https://orcid.org/0000-0003-2090-5512"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqiang Wang","raw_affiliation_strings":["IBM Research, Yorktown Heights, USA"],"raw_orcid":"https://orcid.org/0000-0003-2090-5512","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020399355","display_name":"Christopher G. Brinton","orcid":"https://orcid.org/0000-0003-2771-3521"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Brinton","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"raw_orcid":"https://orcid.org/0000-0003-2771-3521","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"201","last_page":"210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9976000189781189,"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":0.9976000189781189,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9952999949455261,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7204999923706055},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7141000032424927},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7095999717712402},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5393000245094299},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5329999923706055},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48809999227523804},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.3799000084400177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687000036239624},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7204999923706055},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7141000032424927},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7095999717712402},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C3017813396","wikidata":"https://www.wikidata.org/wiki/Q17078173","display_name":"Resource constraints","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3704413.3764429","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704413.3764429","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704413.3764429","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 Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3704413.3764429","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3704413.3764429","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3704413.3764429","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 Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3676035599","display_name":null,"funder_award_id":"FA9550-24-1-0083","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5490050121","display_name":"Collaborative Research: CPS Medium: Learning through the Air: Cross-Layer UAV Orchestration for Online Federated Optimization","funder_award_id":"2313109","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5809100787","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G637786994","display_name":null,"funder_award_id":"N00014-23-C-1016","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G848880661","display_name":null,"funder_award_id":"CPS-2313109","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415480994.pdf","grobid_xml":"https://content.openalex.org/works/W4415480994.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W4390659326","https://openalex.org/W4391957569","https://openalex.org/W4396832611","https://openalex.org/W4401508022","https://openalex.org/W4401508395","https://openalex.org/W4401508464","https://openalex.org/W4403017403","https://openalex.org/W4403017434","https://openalex.org/W4403018511"],"related_works":[],"abstract_inverted_index":{"Compared":[0],"to":[1,135,141,154,192],"traditional":[2],"machine":[3],"learning":[4,117],"models,":[5],"recent":[6],"large":[7,30],"language":[8],"models":[9],"(LLMs)":[10],"can":[11,93,107],"exhibit":[12],"multi-task-solving":[13],"capabilities":[14],"through":[15],"multiple":[16,173],"dialogues":[17],"and":[18,48,63,83,100,131,149,169,177,195,204],"multi-modal":[19,109,132],"data":[20,110,133],"sources.":[21,111],"These":[22],"unique":[23],"characteristics":[24],"of":[25,182,189],"LLMs,":[26],"together":[27],"with":[28,78],"their":[29,34],"model":[31],"size,":[32],"make":[33],"deployment":[35],"more":[36],"challenging.":[37],"Specifically,":[38],"(i)":[39,87],"deploying":[40,54],"LLMs":[41],"on":[42],"local":[43,90,128],"devices":[44],"faces":[45],"computational,":[46],"memory,":[47],"energy":[49],"resource":[50,155],"issues,":[51],"while":[52,152],"(ii)":[53,101],"them":[55],"in":[56,201],"the":[57,124,143,187],"cloud":[58,104],"cannot":[59],"guarantee":[60],"real-time":[61],"service":[62],"incurs":[64],"communication/usage":[65],"costs.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,164],"design":[71],"TMO,":[72],"a":[73,88,102,114,161],"local-cloud":[74],"LLM":[75,91,105,178],"inference":[76,125],"system":[77],"Three-M":[79],"Offloading:":[80],"Multi-modal,":[81],"Multi-task,":[82],"Multi-dialogue.":[84],"TMO":[85,121,190],"incorporates":[86],"lightweight":[89],"that":[92,106,122,166],"process":[94],"simple":[95],"tasks":[96],"at":[97],"high":[98],"speed":[99],"large-scale":[103],"handle":[108],"We":[112,157,185],"develop":[113],"resource-constrained":[115],"reinforcement":[116],"(RCRL)":[118],"strategy":[119],"for":[120,137],"optimizes":[123],"location":[126],"(i.e.,":[127],"vs.":[129],"cloud)":[130],"sources":[134],"use":[136],"each":[138],"task/dialogue,":[139],"aiming":[140],"maximize":[142],"long-term":[144],"reward":[145,168],"(response":[146],"quality,":[147],"latency,":[148,202],"usage":[150],"cost)":[151],"adhering":[153],"constraints.":[156],"also":[158],"contribute":[159],"M4A1,":[160],"new":[162],"dataset":[163],"curated":[165],"contains":[167],"cost":[170],"metrics":[171],"across":[172],"modality,":[174],"task,":[175],"dialogue,":[176],"configurations,":[179],"enabling":[180],"evaluation":[181],"offloading":[183],"decisions.":[184],"demonstrate":[186],"effectiveness":[188],"compared":[191],"several":[193],"exploration-decision":[194],"LLM-as-Agent":[196],"baselines,":[197],"showing":[198],"significant":[199],"improvements":[200],"cost,":[203],"response":[205],"quality.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-23T00:00:00"}