{"id":"https://openalex.org/W4414110614","doi":"https://doi.org/10.1109/tmc.2025.3608303","title":"Joint Inference Offloading and Model Caching for Small and Large Language Model Collaboration","display_name":"Joint Inference Offloading and Model Caching for Small and Large Language Model Collaboration","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W4414110614","doi":"https://doi.org/10.1109/tmc.2025.3608303"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2025.3608303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3608303","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},"type":"article","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/A5024429126","display_name":"Xinyi Xu","orcid":"https://orcid.org/0000-0001-6916-5629"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyi Xu","raw_affiliation_strings":["National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086335553","display_name":"Gang Feng","orcid":"https://orcid.org/0000-0002-2512-2392"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Feng","raw_affiliation_strings":["National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041176339","display_name":"Yi-Jing Liu","orcid":"https://orcid.org/0009-0006-3019-5795"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijing Liu","raw_affiliation_strings":["National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103062487","display_name":"Shuang Qin","orcid":"https://orcid.org/0000-0001-9264-6850"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Qin","raw_affiliation_strings":["National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101484166","display_name":"Jian Wang","orcid":"https://orcid.org/0000-0003-1667-9516"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033316089","display_name":"Yunxiang Wang","orcid":"https://orcid.org/0000-0001-6141-810X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxiang Wang","raw_affiliation_strings":["National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024429126"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.4849,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91407291,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"25","issue":"2","first_page":"2691","last_page":"2706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9905999898910522,"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/T10028","display_name":"Topic Modeling","score":0.9905999898910522,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9580000042915344,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9007999897003174,"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":0.8043000102043152},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6008999943733215},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5443999767303467},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4738999903202057},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46799999475479126},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.4480000138282776},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4147000014781952},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41449999809265137},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.364300012588501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8914999961853027},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8043000102043152},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5443999767303467},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4738999903202057},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45190000534057617},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42399999499320984},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2549999952316284},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3608303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3608303","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2140502378","https://openalex.org/W2175160295","https://openalex.org/W2416799949","https://openalex.org/W2624989916","https://openalex.org/W2789406751","https://openalex.org/W2896457183","https://openalex.org/W2900490252","https://openalex.org/W2911573951","https://openalex.org/W2913729121","https://openalex.org/W2923014074","https://openalex.org/W2982287213","https://openalex.org/W2990530686","https://openalex.org/W3034457371","https://openalex.org/W3093651199","https://openalex.org/W3107559527","https://openalex.org/W3132925507","https://openalex.org/W4212799982","https://openalex.org/W4385249922","https://openalex.org/W4385819926","https://openalex.org/W4388284731","https://openalex.org/W4388579751","https://openalex.org/W4390828922","https://openalex.org/W4393160654","https://openalex.org/W4400447774","https://openalex.org/W4402671080","https://openalex.org/W4405232231","https://openalex.org/W4405934565","https://openalex.org/W4408324654","https://openalex.org/W4409348182","https://openalex.org/W4412877000","https://openalex.org/W4414535423","https://openalex.org/W4417439031"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Language":[1,46],"Models":[2,47],"(LLMs),":[3],"with":[4,70,220],"advanced":[5],"content":[6],"creation":[7],"and":[8,52,82,102,106,133,143,161,187],"inference":[9,95,116,137,148,158,196,216],"capabilities,":[10],"can":[11,58,208],"provide":[12],"immersive":[13],"intelligent":[14],"services":[15],"to":[16,39,64,75,92,130,135,139,151,175,180,192],"users":[17],"in":[18,165,213],"mobile":[19,121],"edge":[20,80,122,185],"networks.":[21],"However,":[22],"the":[23,33,40,76,83,100,157,184,194,204],"increasing":[24],"demand":[25],"for":[26,55,66],"real-time":[27],"artificial":[28],"intelligence":[29],"(AI)":[30],"applications":[31],"aggravates":[32],"limitations":[34],"of":[35,79,86,104,215,223],"cloud-based":[36],"LLMs":[37,65,105],"due":[38],"long":[41],"response":[42],"time.":[43],"Meanwhile,":[44],"Small":[45],"(SLMs),":[48],"which":[49,126],"are":[50],"cost-effective":[51],"locally":[53],"deployable":[54],"terminal":[56],"devices,":[57],"serve":[59],"as":[60],"an":[61,94,113],"efficient":[62],"supplement":[63],"performing":[67],"latency-sensitive":[68],"tasks":[69,138],"lower":[71],"generalization":[72],"capability.":[73],"Due":[74],"resource":[77,144,152],"constraints":[78],"networks":[81],"diverse":[84],"requirements":[85],"user":[87],"tasks,":[88],"it":[89],"is":[90],"critical":[91],"design":[93],"framework":[96],"that":[97,203],"effectively":[98],"coordinates":[99],"deployment":[101],"collaboration":[103],"SLMs.":[107],"In":[108],"this":[109],"paper,":[110],"we":[111,154,169],"propose":[112],"LLM-SLM":[114],"collaborative":[115],"(LSCI)":[117],"scheme":[118,207],"under":[119],"a":[120,221],"computing":[123],"(MEC)":[124],"architecture,":[125],"jointly":[127,155],"decides":[128],"where":[129],"cache":[131],"models":[132],"how":[134],"offload":[136],"balance":[140],"latency,":[141],"accuracy,":[142],"costs.":[145],"To":[146],"optimize":[147],"performance":[149,211,217],"subject":[150],"constraints,":[153],"solve":[156,193],"task":[159,197],"offloading":[160,198],"model":[162],"caching":[163],"problem":[164],"LSCI":[166,206],"scheme.":[167],"Specifically,":[168],"employ":[170],"deep":[171],"reinforcement":[172],"learning":[173],"(DRL)":[174],"select":[176],"highly":[177],"popular":[178],"SLMs":[179],"be":[181],"cached":[182],"on":[183],"server,":[186],"distributed":[188],"belief":[189],"propagation":[190],"technique":[191],"associated":[195],"issue.":[199],"Numerical":[200],"results":[201],"show":[202],"proposed":[205],"achieve":[209],"significant":[210],"gain":[212],"terms":[214],"when":[218],"compared":[219],"number":[222],"baseline":[224],"solutions.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}