{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:02:40Z","timestamp":1784390560150,"version":"3.55.0"},"reference-count":257,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62301151"],"award-info":[{"award-number":["62301151"]}],"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":["62301336"],"award-info":[{"award-number":["62301336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2023YFB2905603"],"award-info":[{"award-number":["2023YFB2905603"]}]},{"name":"Research Fund of National Mobile Communications Research Laboratory, Southeast University","award":["2025A05"],"award-info":[{"award-number":["2025A05"]}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2023-03759"],"award-info":[{"award-number":["RGPIN-2023-03759"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009192","name":"Alberta Innovates","doi-asserted-by":"publisher","award":["242505861"],"award-info":[{"award-number":["242505861"]}],"id":[{"id":"10.13039\/501100009192","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tnse.2025.3639401","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T18:49:35Z","timestamp":1764701375000},"page":"4369-4405","source":"Crossref","is-referenced-by-count":11,"title":["Integration of Generative AI and Mobile Networking: A Comprehensive Survey"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7104-7100","authenticated-orcid":false,"given":"Junling","family":"Li","sequence":"first","affiliation":[{"name":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4747-5890","authenticated-orcid":false,"given":"Mingcheng","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5727-2432","authenticated-orcid":false,"given":"Conghao","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Telecommunications Engineering, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3391-6675","authenticated-orcid":false,"given":"Xi","family":"Huang","sequence":"additional","affiliation":[{"name":"Around Tech (Shenzhen) Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5602-1738","authenticated-orcid":false,"given":"Lian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer, and Biomedical Engineering, Toronto Metropolitan University, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9729-9592","authenticated-orcid":false,"given":"Cheng-Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3497-6437","authenticated-orcid":false,"given":"Huaqing","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3249835"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2021.12.013"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366873"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3393230"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2024.3482327"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3156632"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3135829"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3487627"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3384500"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-023-00980-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3362271"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3558992"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.009.2300165"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3353265"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3527641"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2025.100755"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3535554"},{"key":"ref18","article-title":"Wireless large AI model: Shaping the AI-native future of 6G and beyond","author":"Zhu","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2022.1068478"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3190765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2400408"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2023.9020033"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2021.00.084"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300364"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3704262"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3576322"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2025.3527729"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3200939"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2968430"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3278235"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3220784"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC53906.2023.10304477"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.007.2400133"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3522103"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3541078"},{"key":"ref36","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"ref37","article-title":"Model context protocol (MCP): Landscape, security threats, and future research directions","author":"Hou","year":"2025"},{"key":"ref38","article-title":"Overview of the core architecture behind the agent communication protocol","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2022.3169213"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180802"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3376602"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3381866"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02316-z"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00565"},{"key":"ref45","first-page":"16739","article-title":"EmerNeRF: Emergent spatial-temporal scene decomposition via self-supervision","volume-title":"Proc. ICRL\u201924","author":"Yang","year":"2024"},{"key":"ref46","article-title":"Periodic vibration Gaussian: Dynamic urban scene reconstruction and real-time rendering","author":"Chen","year":"2023"},{"key":"ref47","article-title":"ReconDreamer: Harmonizing generative and reconstructive models for driving scene representation","author":"Zhao","year":"2025"},{"key":"ref48","first-page":"91560","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Gao","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102752"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00920"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2006.1683241"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3221159"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3451561"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3140102"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191334"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3395670"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3549592"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3109908"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2024.10582829"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3092350"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3195299"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322515"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IPIN54987.2022.9918146"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2019.2958201"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1109\/COMST.2025.3648577","article-title":"AI-driven wireless positioning: Fundamentals, standards, state-of-the-art, and challenges","author":"Pan","year":"2025"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3474570"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3047100"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3013257"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3103971"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12071752"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3511960"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3424842"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2023.3294754"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3078489"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3522579"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3152729"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD48534.2019.9142082"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3077249"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3445177"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3395698"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.002.2300564"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3400011"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3525410"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2400074"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3547370"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.007.2300582"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3396860"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3317629"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.003.2300351"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3435524"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3401712"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3526839"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2023.07.015"},{"key":"ref95","article-title":"Integration of mixture of experts and multimodal generative AI in internet of vehicles: A survey","author":"Xu","year":"2024"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3396276"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2025.3526826"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400284"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3529513"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT56141.2022.10073433"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3522088"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.3390\/app14188419"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3382192"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2025.3539355"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3549234"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.003.2300645"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3519664"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3459037"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.016.2300547"},{"key":"ref110","article-title":"The impact of large language models on scientific discovery: A preliminary study using GPT-4","author":"AI4Science","year":"2023"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.4108\/eai.27-2-2020.2303255"},{"key":"ref112","article-title":"ONTAP AI-NVIDIA DGX-2 POD with NetApp AFF A800","author":"Arnette","year":"2019","journal-title":"NetApp, NetApp Verified Architecture (NVA) Design NVA-1135-DESIGN"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3496491"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3497923"},{"key":"ref115","article-title":"DiffusionBee: Stable diffusion for macOS","year":"2025"},{"key":"ref116","article-title":"Mcdonalds gives its restaurants an AI makeover","author":"Bousquette","year":"2025"},{"key":"ref117","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1145\/3680207.3765696","article-title":"Poster: MOE$^{2}$: Optimizing collaborative inference for edge large language models","volume-title":"Proc. ACM MOBICOM","author":"Jin","year":"2025"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3243955"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3527649"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.003.2300568"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3595801"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1038\/s44287-024-00053-6"},{"key":"ref123","article-title":"Impact of GenAI on mobile network traffic","year":"2024"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3542473"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3240707"},{"key":"ref126","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref128","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref129","first-page":"1","article-title":"From one thousand pages of specification to unveiling hidden bugs: Large language model assisted fuzzing of matter IoT devices","volume-title":"Proc. USENIX Secur. Symp.","author":"Ma","year":"2024"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.banglalp-1.15"},{"key":"ref131","first-page":"1","article-title":"Copy is all you need","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2023"},{"key":"ref132","article-title":"Corrective retrieval augmented generation","author":"Yan","year":"2024"},{"key":"ref133","article-title":"TableGPT: Towards unifying tables, nature language and commands into one GPT","author":"Zha","year":"2023"},{"key":"ref134","article-title":"Augmented large language models with parametric knowledge guiding","author":"Luo","year":"2023"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21312"},{"key":"ref136","article-title":"KnowledGPT: Enhancing large language models with retrieval and storage access on knowledge bases","author":"Wang","year":"2023"},{"key":"ref137","first-page":"132876","article-title":"G-retriever: Retrieval-augmented generation for textual graph understanding and question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"He","year":"2024"},{"key":"ref138","first-page":"31210","article-title":"Large language models can be easily distracted by irrelevant context","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Shi","year":"2023"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.845"},{"issue":"3","key":"ref140","first-page":"1390","article-title":"Image data augmentation for deep learning: A survey","volume":"36","author":"Yang","year":"2025","journal-title":"J. Softw."},{"key":"ref141","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. 29th Int. Conf. Neural Inf. Process. Syst. - Vol. 1","author":"Zhang","year":"2015"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363576"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1111\/1754-9485.13261"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00020"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557474"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3360414"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2015.12.004"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/IRI.2015.39"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482106"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00139"},{"key":"ref151","first-page":"19339","article-title":"No subclass left behind: Fine-grained robustness in coarse-grained classification problems","volume-title":"Proc. NIPS20","author":"Sohoni","year":"2020"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20468"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/395"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16851"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375850"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375812"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref160","first-page":"6106","article-title":"Poison frogs! Targeted clean-label poisoning attacks on neural networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Shafahi","year":"2018"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref162","first-page":"3122","article-title":"Detecting and correcting for label shift with black box predictors","volume-title":"Proc. 2022 Int. Conf. Advance. Technol.","author":"Lipton","year":"2018"},{"key":"ref163","first-page":"205","article-title":"No more companion apps hacking but one dongle: Hub-based blackbox fuzzing of loT firmware","volume-title":"Proc. ACM MobiSys23","author":"Ma","year":"2023"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref165","first-page":"1","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. ICLR21","author":"Hendrycks","year":"2021"},{"key":"ref166","first-page":"1","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref167","article-title":"Evaluating Large Language Models Trained on Code","author":"Chen"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1177\/15291006211051956"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350263"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3239220"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900184"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/3680207.3765257"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3224279"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3076230"},{"key":"ref175","first-page":"1","article-title":"DELIFT: Data efficient language model instruction fine tuning","volume-title":"Proc. ICLR25","author":"Agarwal","year":"2025"},{"key":"ref176","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2020","author":"Lewis"},{"key":"ref177","first-page":"1","article-title":"KVLink: Accelerating large language models via efficient KV cache reuse","volume-title":"Proc. NIPS25","author":"Yang","year":"2025"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.003.2200641"},{"key":"ref179","doi-asserted-by":"crossref","DOI":"10.32388\/IZOHCH","article-title":"Optimizing edge AI: A comprehensive survey on data, model, and system strategies","author":"Wang","year":"2025"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279110"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/467"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3438379"},{"key":"ref184","article-title":"Effectively use prompt caching on Amazon bedrock","author":"Li","year":"2025"},{"key":"ref185","article-title":"Prompt caching with OpenAI, anthropic, and Google models","year":"2025"},{"key":"ref186","article-title":"A generative caching system for large language models","author":"Iyengar","year":"2025"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.3390\/technologies13010019"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/mvt.2025.3608414"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00117"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS61813.2024.10682957"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00075"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2025.3575493"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref195","article-title":"DILEMMA: Joint LLM quantization and distributed LLM inference over edge computing systems","author":"Hosseinzadeh","year":"2025"},{"key":"ref196","article-title":"PartialLoading: User scheduling and bandwidth allocation for parameter-sharing edge inference","author":"Qu","year":"2025"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS60910.2024.00013"},{"key":"ref198","first-page":"1","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC61545.2025.10978225"},{"key":"ref200","article-title":"Serving long-context LLMs at the mobile edge: Test-time reinforcement learning-based model caching and inference offloading","author":"Xu","year":"2025"},{"key":"ref201","article-title":"Cached model-as-a-resource: Provisioning large language model agents for edge intelligence in space-air-ground integrated networks","author":"Xu","year":"2024"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"ref203","first-page":"139997","article-title":"MiniCache: KV cache compression in depth dimension for large language models","volume-title":"Proc. 38th Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0722"},{"key":"ref205","first-page":"19233","article-title":"Dialogue without limits: Constant-sized KV caches for extended responses in LLMs","volume-title":"Proc. ICML25","author":"Ghadia","year":"2025"},{"key":"ref206","first-page":"1","article-title":"Cache me if you must: Adaptive key-value quantization for large language models","volume-title":"Proc. ICML25","author":"Shutova","year":"2025"},{"key":"ref207","first-page":"11437","article-title":"Get more with LESS: Synthesizing recurrence with KV cache compression for efficient LLM inference","volume-title":"Proc. ICML24","author":"Dong","year":"2024"},{"key":"ref208","first-page":"50453","article-title":"MemoryLLM: Towards self-updatable large language models","volume-title":"Proc. ICML24","author":"Wang","year":"2024"},{"key":"ref209","first-page":"1","article-title":"M+: Extending MemoryLLM with scalable long-term memory","volume-title":"Proc. ICML\u201925","author":"Wang","year":"2025"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34619"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715490"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1145\/3768628"},{"key":"ref213","article-title":"EdgeRAG: Online-indexed rag for edge devices","author":"Seemakhupt","year":"2024"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.449"},{"key":"ref215","article-title":"KG-RAG: Bridging the gap between knowledge and creativity","author":"Sanmartin","year":"2024"},{"key":"ref216","article-title":"Prompt caching: Saving time and money in LLM applications","author":"Ojeda","year":"2025"},{"key":"ref217","first-page":"325","article-title":"Prompt cache: Modular attention reuse for low-latency inference","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Gim","year":"2024"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3005469"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3148131"},{"key":"ref220","first-page":"160","article-title":"LLMs for test input generation for semantic caches","volume-title":"Proc. CAIN\u201924","author":"Rasool","year":"2024"},{"key":"ref221","article-title":"Efficient prompt caching via embedding similarity","author":"Zhu","year":"2023","journal-title":"NeurIPS Workshop Mach. Learn. Syst."},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.10.036"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436771"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901571"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3527725"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2023.3323757"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3587280"},{"key":"ref228","article-title":"A survey on large language model acceleration based on kv cache management","author":"Li","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref229","article-title":"Keep the cost down: A review on methods to optimize LLMs KV-cache consumption","volume-title":"Proc. COLM\u201924","author":"Shi","year":"2024"},{"key":"ref230","article-title":"RetrievalAttention: Accelerating long-context LLM inference via vector retrieval","volume-title":"Proc. NeurIPS\u201925","author":"Liu","year":"2025"},{"key":"ref231","article-title":"Beyond words: A latent memory approach to internal reasoning in LLMs","author":"Orlicki","year":"2025"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3401159"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae353"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.005.2300481"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671582"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3363240"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3544368"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625793"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3509628"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366531"},{"key":"ref241","article-title":"Large language models in the 6G-enabled computing continuum: A white paper","author":"Abel","year":"2025"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3356178"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400764"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3422309"},{"key":"ref245","first-page":"135","article-title":"ServerlessLLM: Low-latency serverless inference for large language models","volume-title":"Proc. USENIX OSDI24","author":"Fu","year":"2024"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3376419"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3582864"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3391767"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2500073"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3566336"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2025.3603391"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2021.3114655"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2100338"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000644"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901015"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/LNET.2024.3486194"}],"container-title":["IEEE Transactions on Network Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488902\/11264281\/11271809.pdf?arnumber=11271809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T18:24:39Z","timestamp":1766773479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":257,"URL":"https:\/\/doi.org\/10.1109\/tnse.2025.3639401","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.175623872.22465901\/v1","asserted-by":"object"}]},"ISSN":["2327-4697","2334-329X"],"issn-type":[{"value":"2327-4697","type":"electronic"},{"value":"2334-329X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}