{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:17:26Z","timestamp":1783405046825,"version":"3.54.6"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"U.K. Research and Innovation","award":["EP\/Y036786\/1"],"award-info":[{"award-number":["EP\/Y036786\/1"]}]},{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"crossref","award":["101129910"],"award-info":[{"award-number":["101129910"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tmc.2026.3668982","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:57:44Z","timestamp":1772485064000},"page":"11935-11948","source":"Crossref","is-referenced-by-count":0,"title":["Criticality-Aware Gen-AI Inference via Dynamic Step Control in Resource-Efficient Vehicular Computing"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9274-4745","authenticated-orcid":false,"given":"Jinmei","family":"Shu","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5406-8420","authenticated-orcid":false,"given":"Jia","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-7314","authenticated-orcid":false,"given":"Geyong","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5645-160X","authenticated-orcid":false,"given":"Zhu","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7372-2539","authenticated-orcid":false,"given":"Hongbo","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3377226"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3613178"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3497918"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.004.2300015"},{"key":"ref6","article-title":"Inference steps","author":"AI","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3609152"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2024-Spring62846.2024.10683477"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01209"},{"key":"ref10","first-page":"12562","article-title":"LLM in a flash: Efficient large language model inference with limited memory","volume-title":"Proc. 62nd Annu. Meeting Assoc. Computational Linguist.","author":"Alizadeh","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.004.2200473"},{"key":"ref13","article-title":"LLM inference speed of light","author":"Kapoulkine","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3153996"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2024.3379983"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3414628"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICC51166.2024.10622411"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jiixd.2022.10.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3430112"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3393529"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3215523"},{"key":"ref23","article-title":"Trends in ai inference energy consumption: Beyond the performance-vs-parameter laws of deep learning","volume-title":"Sustainable Comput.: Informatics Syst.","volume":"38","author":"Desislavov","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3227027"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3190276"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT59356.2023.10419509"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM45741.2023.10413890"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3213426"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012210"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISORC52572.2022.9812757"},{"key":"ref31","first-page":"199","article-title":"System architecture for digital twin based collision avoidance through private 5G networks","volume-title":"Proc. IEEE 12th Int. Conf. Intell. Data Acquisition Adv. Comput. Syst.: Technol. Appl.","author":"Ulrich","year":"2023"},{"key":"ref32","article-title":"Voice assistant for an autonomous vehicle aimed at elderly","volume-title":"Proc. 7th Iberian Robotics Conf.","volume":"2024","author":"Berriales-Mateos"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00453"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet47604.2019.9064135"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s22228780"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681072"},{"key":"ref37","article-title":"LiveMind: Low-latency large language models with simultaneous inference","author":"Chen","year":"2024"},{"key":"ref38","article-title":"Visual prompting with iterative refinement for design critique generation","author":"Duan","year":"2025"},{"key":"ref39","article-title":"Mini-omni: Language models can hear, talk while thinking in streaming","author":"Xie","year":"2024"},{"key":"ref40","article-title":"NVIDIA H100 tensor core GPU architecture","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00268"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-52370-3"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.52202\/079017-4153","article-title":"Resfusion: Denoising diffusion probabilistic models for image restoration based on prior residual noise","author":"Shi","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01204"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3304418"},{"key":"ref47","article-title":"Understanding size tradeoffs with generative models - how to select the right model (GPT4 vs LLAMA2)?","author":"Dibia","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3439628"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111838"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT52419.2022.9711641"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLCN59089.2024.10624796"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279243"},{"key":"ref53","article-title":"NVIDIA A100 tensor core GPU","year":"2025"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11595771\/11417741.pdf?arnumber=11417741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:34:45Z","timestamp":1783402485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417741\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":53,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2026.3668982","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}