{"id":"https://openalex.org/W7084027809","doi":"https://doi.org/10.1109/infocom55648.2025.11044689","title":"Joint Optimization of Model Inferencing and Task Offloading for MEC-Empowered Large Vision Model Services","display_name":"Joint Optimization of Model Inferencing and Task Offloading for MEC-Empowered Large Vision Model Services","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W7084027809","doi":"https://doi.org/10.1109/infocom55648.2025.11044689"},"language":"en","primary_location":{"id":"doi:10.1109/infocom55648.2025.11044689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-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":null,"display_name":"Xinyi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyi Zhuang","raw_affiliation_strings":["School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaqi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wu","raw_affiliation_strings":["School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongjia Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongjia Wu","raw_affiliation_strings":["Education University of Hong Kong,Department of Mathematics and Information Technology,N.T.,Hong Kong"],"affiliations":[{"raw_affiliation_string":"Education University of Hong Kong,Department of Mathematics and Information Technology,N.T.,Hong Kong","institution_ids":["https://openalex.org/I4210086892"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tingting Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Zhang","raw_affiliation_strings":["School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lin Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gao","raw_affiliation_strings":["School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering and the Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":250.5892,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.99972632,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13302","display_name":"Amazonian Archaeology and Ethnohistory","score":0.7347000241279602,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13302","display_name":"Amazonian Archaeology and Ethnohistory","score":0.7347000241279602,"subfield":{"id":"https://openalex.org/subfields/1202","display_name":"History"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10087","display_name":"Archaeology and ancient environmental studies","score":0.19519999623298645,"subfield":{"id":"https://openalex.org/subfields/1911","display_name":"Paleontology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10421","display_name":"Pleistocene-Era Hominins and Archaeology","score":0.016699999570846558,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6025000214576721},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5734999775886536},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5371000170707703},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.5361999869346619},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5358999967575073},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.4934999942779541},{"id":"https://openalex.org/keywords/computation-offloading","display_name":"Computation offloading","score":0.4569999873638153},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44780001044273376},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.44699999690055847},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.4311000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817300021648407},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.5361999869346619},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4959000051021576},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.4934999942779541},{"id":"https://openalex.org/C2781041963","wikidata":"https://www.wikidata.org/wiki/Q18348618","display_name":"Computation offloading","level":4,"score":0.4569999873638153},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3880999982357025},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3555999994277954},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3025999963283539},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C14961307","wikidata":"https://www.wikidata.org/wiki/Q5377176","display_name":"Energy minimization","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C2779333187","wikidata":"https://www.wikidata.org/wiki/Q3132648","display_name":"Quality of experience","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C2779191767","wikidata":"https://www.wikidata.org/wiki/Q6887075","display_name":"Mobile cloud computing","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C140781008","wikidata":"https://www.wikidata.org/wiki/Q1221081","display_name":"Service quality","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom55648.2025.11044689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1174718781","display_name":null,"funder_award_id":"2021YFB2900300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1716234396","display_name":null,"funder_award_id":"61972113,62171160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2803576756","display_name":null,"funder_award_id":"2024A1515010178","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G624034441","display_name":null,"funder_award_id":"2021B1515120008","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7252329763","display_name":null,"funder_award_id":"KQTD20190929172545139,ZDSYS20210623091808025,GXWD20231129103946001,KJZD20231023093055002,KJZD20230923114804009","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,12,56,72,119,133,146,165,169,177,196,212,221,226,235],"rapid":[2],"advancement":[3],"of":[4,15,59,74,122,148],"Large":[5],"Vision":[6],"Models":[7],"(LVMs)":[8],"such":[9,113],"as":[10],"Sora,":[11],"initial":[13],"comprehension":[14],"physical":[16,33],"laws":[17],"by":[18,257,268],"large":[19],"AI":[20],"models":[21],"has":[22],"garnered":[23],"significant":[24],"attention,":[25],"which":[26,162],"enables":[27],"them":[28],"to":[29,42,54,103,106,131,144,175,210,233,259,270],"interpret":[30],"and":[31,38,45,92,95,109,125,140,168,192,216,250,254,261],"apply":[32],"principles":[34],"with":[35],"increasing":[36,265],"accuracy":[37],"sophistication.":[39],"Nevertheless,":[40],"due":[41],"resource":[43,237],"limitations":[44],"delay":[46,108,139,253],"constraints,":[47],"traditional":[48],"cloud-based":[49],"LVM":[50,79,96,149],"services":[51,80],"often":[52],"fail":[53],"meet":[55],"diverse":[57],"needs":[58],"users,":[60],"particularly":[61],"in":[62,81,179],"scenarios":[63],"requiring":[64],"real-time":[65,213],"responsiveness.":[66],"In":[67,112,195,220],"this":[68],"work,":[69],"we":[70,116,151,183,199,224],"explore":[71],"scenario":[73],"Mobile":[75],"Edge":[76],"Computing":[77],"(MEC)-empowered":[78],"wireless":[82],"networks,":[83],"where":[84],"heterogeneous":[85],"LVMs":[86],"are":[87],"deployed":[88],"on":[89,118,159,189],"both":[90,164,190],"cloud":[91],"edge":[93,104],"servers,":[94],"Users":[97],"(LUs)":[98],"can":[99,251],"offload":[100],"computation":[101],"task":[102,126,217],"servers":[105],"reduce":[107,252],"energy":[110,141,255],"consumption.":[111,142],"a":[114,153,180,185,201],"scenario,":[115],"focus":[117],"joint":[120],"optimization":[121,193],"model":[123,214],"inferencing":[124,215],"offloading":[127,218],"for":[128],"LUs,":[129],"aiming":[130],"maximize":[132],"total":[134],"service":[135,266],"utility,":[136],"while":[137,264],"minimizing":[138],"First,":[143],"characterize":[145],"utility":[147,267],"services,":[150],"propose":[152,184],"multi-dimensional":[154],"video":[155,171],"quality":[156,172],"metric":[157],"based":[158,188],"real":[160],"measurements,":[161],"incorporates":[163],"prompt-video":[166],"alignment":[167],"classic":[170],"indicators.":[173],"Then,":[174],"solve":[176],"problem":[178],"decentralized":[181],"manner,":[182],"two-stage":[186],"solution":[187,246],"learning":[191],"techniques.":[194],"first":[197],"stage,":[198,223],"design":[200],"reinforcement":[202],"learning-based":[203],"Multi-Agent":[204],"Proximal":[205],"Policy":[206],"Optimization":[207],"(MAPPO)":[208],"approach":[209],"make":[211,234],"decisions.":[219,239],"second":[222],"employ":[225],"optimization-based":[227],"Sequential":[228],"Least":[229],"Squares":[230],"Programming":[231],"(SLSQP)":[232],"efficient":[236],"allocation":[238],"Simulation":[240],"results":[241],"show":[242],"that":[243],"our":[244],"proposed":[245],"outperforms":[247],"other":[248],"benchmarks,":[249],"consumption":[256],"up":[258,269],"17.2%":[260],"21.7%,":[262],"respectively,":[263],"3%.":[271]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}