{"id":"https://openalex.org/W7133205375","doi":"https://doi.org/10.1109/tmc.2026.3668982","title":"Criticality-Aware Gen-AI Inference via Dynamic Step Control in Resource-Efficient Vehicular Computing","display_name":"Criticality-Aware Gen-AI Inference via Dynamic Step Control in Resource-Efficient Vehicular Computing","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133205375","doi":"https://doi.org/10.1109/tmc.2026.3668982"},"language":null,"primary_location":{"id":"doi:10.1109/tmc.2026.3668982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2026.3668982","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":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Criticality-Aware_Gen-AI_Inference_via_Dynamic_Step_Control_in_Resource-Efficient_Vehicular_Computing/32760165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076570346","display_name":"Jinmei Shu","orcid":"https://orcid.org/0009-0006-9274-4745"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinmei Shu","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0009-0006-9274-4745","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jia Hu","orcid":"https://orcid.org/0000-0001-5406-8420"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jia Hu","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5406-8420","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127823003","display_name":"Geyong Min","orcid":null},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geyong Min","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1395-7314","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, U.K","institution_ids":["https://openalex.org/I23923803"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu Xiao","orcid":"https://orcid.org/0000-0001-5645-160X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Xiao","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-5645-160X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hongbo Jiang","orcid":"https://orcid.org/0000-0001-7372-2539"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Jiang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-7372-2539","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.18619339,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":"8","first_page":"11935","last_page":"11948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10761","display_name":"Vehicular Ad Hoc Networks (VANETs)","score":0.4943000078201294,"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/T10761","display_name":"Vehicular Ad Hoc Networks (VANETs)","score":0.4943000078201294,"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/T13553","display_name":"Age of Information Optimization","score":0.0925000011920929,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.041099999099969864,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.8190000057220459},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48829999566078186},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.43389999866485596},{"id":"https://openalex.org/keywords/vehicular-ad-hoc-network","display_name":"Vehicular ad hoc network","score":0.38350000977516174},{"id":"https://openalex.org/keywords/bandwidth-allocation","display_name":"Bandwidth allocation","score":0.3418999910354614},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.3416000008583069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883899986743927},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8190000057220459},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C192448918","wikidata":"https://www.wikidata.org/wiki/Q682677","display_name":"Vehicular ad hoc network","level":4,"score":0.38350000977516174},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmc.2026.3668982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2026.3668982","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"},{"id":"pmh:oai:figshare.com:article/32760165","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Criticality-Aware_Gen-AI_Inference_via_Dynamic_Step_Control_in_Resource-Efficient_Vehicular_Computing/32760165","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/32760165","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Criticality-Aware_Gen-AI_Inference_via_Dynamic_Step_Control_in_Resource-Efficient_Vehicular_Computing/32760165","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.47115078568458557,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1105131427","display_name":null,"funder_award_id":"101129910","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Integrating":[0],"Generative":[1],"AI":[2],"(Gen-AI)":[3],"into":[4],"vehicular":[5,21],"computing":[6,22,138],"can":[7,36,51],"significantly":[8],"enhance":[9],"road":[10],"safety":[11],"and":[12,42,81,116,136,151,164,190],"driving":[13],"experience.":[14],"The":[15,141],"performance":[16],"of":[17,29,77,145],"Gen-AI":[18],"inference":[19,30,43,52,79,108,124],"in":[20],"is":[23,155],"highly":[24],"sensitive":[25],"to":[26,68,74,113,131],"the":[27,38,61,75,180],"number":[28],"steps,":[31],"where":[32,107],"even":[33],"minor":[34],"adjustments":[35],"disrupt":[37],"balance":[39,114],"between":[40],"delay":[41,115],"quality.":[44],"This":[45],"raises":[46],"a":[47,93,158,167],"critical":[48],"question:":[49],"how":[50],"steps":[53,109],"be":[54],"optimally":[55],"determined":[56],"for":[57,118,177],"diverse":[58],"tasks,":[59,179],"given":[60],"inherent":[62],"delay-quality":[63],"trade-offs?":[64],"Existing":[65],"approaches":[66],"fail":[67],"offer":[69],"an":[70,122],"optimal":[71],"solution":[72],"due":[73],"lack":[76],"flexible":[78],"services":[80],"efficient":[82],"memory":[83,148],"bandwidth":[84,149],"allocation":[85],"strategies.":[86],"To":[87],"address":[88],"these":[89],"challenges,":[90],"we":[91],"develop":[92],"<underline":[94,99,102],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[95,97,100,103,185,192],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">C</u>riticality-<underline":[96],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">a</u>ware":[98],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">R</u>esource-efficient":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">In</u>ference":[104],"(CARIN)":[105],"framework,":[106],"are":[110],"dynamically":[111],"adjusted":[112],"quality":[117,195],"multi-criticality":[119],"tasks.":[120],"Leveraging":[121],"accurate":[123],"model,":[125],"CARIN":[126],"fully":[127],"exploits":[128],"in-vehicle":[129],"resources":[130],"accelerate":[132],"both":[133],"parameter":[134],"loading":[135],"task":[137],"during":[139],"inference.":[140],"joint":[142],"optimization":[143],"problem":[144],"step":[146],"control,":[147],"allocation,":[150],"compute":[152],"resource":[153],"scheduling":[154],"formulated":[156],"as":[157],"mixed-integer":[159],"nonlinear":[160],"programming":[161],"(MINLP)":[162],"problem,":[163],"solved":[165],"by":[166],"novel":[168],"learning-to-optimize":[169],"(L2O)":[170],"algorithm":[171],"efficiently.":[172],"Experimental":[173],"results":[174],"demonstrate":[175],"that,":[176],"high-criticality":[178],"proposed":[181],"approach":[182],"achieves":[183],"<inline-formula":[184,191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[186,193],"notation=\"LaTeX\">$28.4\\%$</tex-math></inline-formula>":[187],"latency":[188],"reduction":[189],"notation=\"LaTeX\">$36\\%$</tex-math></inline-formula>":[194],"improvement":[196],"over":[197],"baseline":[198],"methods.":[199]},"counts_by_year":[],"updated_date":"2026-07-07T06:14:10.401900","created_date":"2026-03-03T00:00:00"}
