{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:07:01Z","timestamp":1780949221120,"version":"3.54.1"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272046"],"award-info":[{"award-number":["62272046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132019"],"award-info":[{"award-number":["62132019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872337"],"award-info":[{"award-number":["61872337"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["CEIEC-20240"],"award-info":[{"award-number":["CEIEC-20240"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Project of Beijing Institute of Technology","award":["2023CX01017"],"award-info":[{"award-number":["2023CX01017"]}]},{"name":"Open Project of Key Laboratory of the Ministry of Education","award":["2023PY002"],"award-info":[{"award-number":["2023PY002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tmc.2026.3667390","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:50:16Z","timestamp":1771879816000},"page":"10438-10454","source":"Crossref","is-referenced-by-count":0,"title":["ConvertNet: Training-Time Model Scaling for In-Vehicle Continuous Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4072-1198","authenticated-orcid":false,"given":"Qinglong","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6894-1921","authenticated-orcid":false,"given":"Rui","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0252-329X","authenticated-orcid":false,"given":"Chi Harold","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-8379","authenticated-orcid":false,"given":"Guoren","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4228-6735","authenticated-orcid":false,"given":"Lydia Y.","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Neuchatel and TU Delft, Delft, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588476"},{"key":"ref2","article-title":"VADV2: End-to-end vectorized autonomous driving via probabilistic planning","author":"Chen","year":"2024"},{"key":"ref3","first-page":"4698","article-title":"DriveVLM: The convergence of autonomous driving and large vision-language models","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Tian","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref8","article-title":"LLAMA: Open and efficient foundation language models","volume":"10","author":"Touvron","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588848"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IV55156.2024.10588595"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"issue":"11","key":"ref12","first-page":"1586","article-title":"No-scope: Optimizing neural network queries over video at scale","volume":"10","author":"Kang","year":"2017","journal-title":"VLDB\u201917"},{"key":"ref13","article-title":"Microsoft rocket for live video analytics","year":"2021"},{"key":"ref14","article-title":"Custom on-device ML models withlearn2compress","year":"2018"},{"key":"ref15","first-page":"119","article-title":"Ekya: Continuous learning of video analytics models on edge compute servers","volume-title":"Proc. 19th USENIX Symp. Networked Syst. Des. Implementation","author":"Bhardwaj","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3539765"},{"key":"ref17","first-page":"22941","article-title":"On-device training under 256 KB memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3062575"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414299"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3200245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3375608"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3504859"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612585"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3316388"},{"key":"ref26","first-page":"917","article-title":"RECL: Responsive resource-efficient continuous learning for video analytics","volume-title":"Proc. 20th USENIX Symp. Netw. Syst. Des. Implementation","author":"Khani","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596852"},{"key":"ref28","first-page":"28699","article-title":"The quantization model of neural scaling","volume":"36","author":"Michaud","year":"2023","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02223"},{"key":"ref30","first-page":"36:1","article-title":"PruneTrain: Fast neural network training by dynamic sparse model reconfiguration","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Lym","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref33","article-title":"Intelligent vehicle e\/e architecture research report","year":"2022"},{"key":"ref34","article-title":"NVIDIA driveOS","author":"Developer","year":"2024"},{"key":"ref35","article-title":"Automotive open system architecture-an industry-wide initiative to manage the complexity of emerging automotive e\/e-architectures","author":"Heinecke","year":"2004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02895-8_52"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00289"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCES51560.2020.9334619"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1547"},{"key":"ref42","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","volume":"78","author":"Dosovitskiy"},{"key":"ref43","article-title":"GPT-Neo: Large scale autoregressive language modeling with Mesh-Tensorflow","author":"Black","year":"2021"},{"key":"ref44","first-page":"25908","article-title":"DriveGPT: Scaling autoregressive behavior models for driving","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00367"},{"key":"ref46","first-page":"4552","article-title":"Real-time video inference on edge devices via adaptive model streaming","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Shirkoohi"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8079-6_23"},{"key":"ref48","first-page":"1","article-title":"Dynamic channel pruning: Feature boosting and suppression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao","year":"2019"},{"key":"ref49","first-page":"1","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00508"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3136244"},{"key":"ref54","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref57","first-page":"6028","article-title":"Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liang","year":"2020"},{"key":"ref58","first-page":"3647","article-title":"Continual learning with node-importance based adaptive group sparse regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jung","year":"2020"},{"key":"ref59","article-title":"End-to-end solutions for autonomous vehicles","year":"2024"},{"key":"ref60","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref62","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref63","first-page":"32100","article-title":"DoRA: Weight-decomposed low-rank adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref64","first-page":"1","article-title":"VeRA: Vector-based random matrix adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kopiczko","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00288"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref67","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Riquelme"},{"key":"ref68","first-page":"22137","article-title":"Deja vu: Contextual sparsity for efficient LLMs at inference time","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Liu","year":"2023"},{"key":"ref69","article-title":"Downsampled ImageNet datasets","year":"2020"},{"key":"ref70","first-page":"1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Hendrycks","year":"2019"},{"key":"ref71","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE55515.2023.00033"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00432"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2019.04.007"},{"key":"ref75","first-page":"2820","article-title":"MnasNet: Platform-aware neural architecture search for mobile","volume-title":"Proc. CVPR\u201919. Comput. Vis. Found. \/ IEEE","author":"Tan","year":"2019"},{"key":"ref76","first-page":"1","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cai","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00098"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2676"},{"key":"ref79","article-title":"SWAP-NAS: Sample-wise activation patterns for ultra-fast NAS","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2024"},{"key":"ref80","article-title":"DARTS: Differentiable architecture search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2019"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592529"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3398202"},{"key":"ref83","first-page":"21702","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma","year":"2023"},{"key":"ref84","article-title":"Distilbert, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483249"},{"key":"ref90","article-title":"Slimmable neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2019"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref94","first-page":"9782","article-title":"DynaBERT: Dynamic BERT with adaptive width and depth","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hou","year":"2020"},{"key":"ref95","article-title":"SkipDecode: Autoregressive skip decoding with batching and caching for efficient LLM inference","author":"Corro","year":"2023"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11552380\/11408214.pdf?arnumber=11408214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:54:48Z","timestamp":1780948488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":95,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2026.3667390","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":[[2026,7]]}}}