{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T20:02:16Z","timestamp":1784318536246,"version":"3.55.0"},"reference-count":331,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20233160"],"award-info":[{"award-number":["GZC20233160"]}]},{"name":"Changsha Municipal Natural Science Foundation","award":["kq2208284"],"award-info":[{"award-number":["kq2208284"]}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ9173"],"award-info":[{"award-number":["2024JJ9173"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2023jj40774"],"award-info":[{"award-number":["2023jj40774"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302527"],"award-info":[{"award-number":["62302527"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010021","name":"High Performance Computing Center of Central South University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010021","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/comst.2025.3526606","type":"journal-article","created":{"date-parts":[[2025,1,7]],"date-time":"2025-01-07T15:08:23Z","timestamp":1736262503000},"page":"3915-3949","source":"Crossref","is-referenced-by-count":99,"title":["A Survey on Intelligent Network Operations and Performance Optimization Based on Large Language Models"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4394-5493","authenticated-orcid":false,"given":"Sifan","family":"Long","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0598-7698","authenticated-orcid":false,"given":"Jingjing","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7780-5972","authenticated-orcid":false,"given":"Bomin","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Cybersecurity, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2414-4802","authenticated-orcid":false,"given":"Fengxiao","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3640-5088","authenticated-orcid":false,"given":"Yangfan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2317-5359","authenticated-orcid":false,"given":"Ming","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8769-302X","authenticated-orcid":false,"given":"Nei","family":"Kato","sequence":"additional","affiliation":[{"name":"Graduate School of Information Sciences, Tohoku University, Sendai, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jii.2021.100224"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3146552"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3135829"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3477091.3482761"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000195"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2021.102180"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SERVICES48979.2020.00060"},{"issue":"1","key":"ref10","first-page":"8","article-title":"Integration of wireless sensor networks, Internet of Things, artificial intelligence, and deep learning in smart agriculture: A comprehensive survey: Integration of wireless sensor networks, Internet of Things","volume":"1","author":"Mushtaque","year":"2024","journal-title":"J. Innov. Intell. Comput. Emerg. Technol."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-021-09622-6"},{"issue":"2","key":"ref12","first-page":"77","article-title":"Internet of Things (IoT)","volume":"9","author":"Mouha","year":"2021","journal-title":"J. Data Anal. Inf. Process."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/info12020087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.9734\/ajrcos\/2023\/v16i1330"},{"issue":"4","key":"ref15","first-page":"53","article-title":"The future of cloud computing: benefits and challenges,\u201d International Journal of Communications","volume":"16","author":"Islam","year":"2023","journal-title":"Netw. Syst. Sci."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-023-04541-9"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2998584"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.139"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2021.1953181"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.12928\/biste.v5i1.7603"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2758763"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/9781119792406.ch9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00549-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.54489\/ijcim.v2i1.75"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9614520"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3130901"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.019.2100721"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3073009"},{"key":"ref29","article-title":"What do learning dynamics reveal about generalization in LLM reasoning?","author":"Kang","year":"2024","journal-title":"arxiv:2411.07681"},{"key":"ref30","first-page":"1","article-title":"Can LLM already serve as a database interface? A big bench for large-scale database grounded text-to-SQLs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2809670"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3079510"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126073"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3421306"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3456549"},{"key":"ref36","first-page":"13","article-title":"Improving large language model hardware generating quality through post-LLM search","volume-title":"Proc. Mach. Learn. Syst.","author":"Chang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-1274-8_6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.30574\/msarr.2024.10.1.0028"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2021.108974"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900252"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3110988"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3390\/s22155750"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3234693"},{"issue":"2","key":"ref44","first-page":"1","article-title":"Quantum-inspired optimization techniques for IoT networks: Focusing on resource allocation and network efficiency enhancement for improved IoT functionality","volume":"2","author":"Raparthi","year":"2022","journal-title":"Adv. Deep Learn. Techn."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06059-7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JCN.2020.000006"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.008.2200157"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2707140"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119587"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3199689"},{"key":"ref51","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Li"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-023-04203-7"},{"key":"ref53","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kojima"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580688"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICALT58122.2023.00100"},{"key":"ref56","first-page":"1","article-title":"ToolQA: A dataset for LLM question answering with external tools","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhuang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-13428-4"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1097\/JGP.0b013e3181953a02"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324916000334"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3375395.3387641"},{"key":"ref64","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014","journal-title":"arxiv:1409.3215"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3274895.3274983"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref68","volume-title":"The unreasonable effectiveness of recurrent neural networks.","author":"Blog","year":"2015"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-75304-1_5"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2016.2582924"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2013.6707742"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref76","article-title":"Music transformer","author":"Huang","year":"2018","journal-title":"arxiv:1809.04281"},{"key":"ref77","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Han"},{"key":"ref78","first-page":"12","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30493-5_78"},{"key":"ref80","first-page":"1","article-title":"Graph transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yun"},{"key":"ref81","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arxiv:1810.04805"},{"key":"ref82","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arxiv:2005.14165"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000601"},{"key":"ref85","volume-title":"Improving language understanding by generative pre-training.","author":"Radford","year":"2018"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.05.111"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/11575832_13"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00206"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5599556"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-273"},{"key":"ref91","first-page":"246","article-title":"Hierarchical probabilistic neural network language model","volume-title":"Proc. Int. Workshop Artif. Intell. Stat.","author":"Morin"},{"key":"ref92","first-page":"246","article-title":"Word representations: A simple and general method for semi-supervised learning","volume-title":"Proc. 48th Annu. Meeting Assoc. Comput. Linguist.","author":"Turian"},{"key":"ref93","first-page":"1","article-title":"A preliminary evaluation of word representations for named-entity recognition","volume-title":"Proc. NIPS Workshop Grammar Induction Rep. Lang. Lang. Learn.","author":"Turian"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01199"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s11600-019-00330-1"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3390\/info11050243"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref98","first-page":"1","article-title":"Learning transformer programs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Friedman"},{"key":"ref99","first-page":"1","article-title":"Focused transformer: Contrastive training for context scaling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tworkowski"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3389497"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2023.03.010"},{"key":"ref102","first-page":"1","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"Proc. 11th Int. Conf. Learn. Rep.","author":"Frantar"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.4018\/979-8-3693-1950-5.ch003"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/IISEC56263.2022.9998298"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3390\/info15020099"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2023.1224976"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-3177-4_41"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18103\/mra.v11i11.4700"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1093\/postmj\/qgad128"},{"key":"ref110","first-page":"12","article-title":"Event Stream GPT: A data pre-processing and modeling library for generative, pre-trained transformers over continuous-time sequences of complex events","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"McDermott"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbenv.2023.06.005"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.56294\/mr202333"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1093\/cid\/ciad407"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2309350120"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1227\/neu.0000000000002632"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1963\/1\/012173"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/Confluence47617.2020.9058044"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00041"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118258"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-023-07840-7"},{"key":"ref122","article-title":"Multi-modal generative AI: Multi-modal LLM, diffusion and beyond","author":"Chen","year":"2024","journal-title":"arxiv:2409.14993"},{"key":"ref123","article-title":"Keqing: Knowledge-based question answering is a nature chain-of-thought mentor of LLM","author":"Wang","year":"2023","journal-title":"arxiv:2401.00426"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00191"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30374"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1080\/15228053.2023.2233814"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.21541\/apjess.1293702"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6576-5_6"},{"key":"ref129","article-title":"Training a whole-book LSTM-based recognizer with an optimal training set","volume-title":"Proc. 10th Int. Conf. Mach. Vis. (ICMV)","author":"Soheili"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111740"},{"key":"ref131","first-page":"23818","article-title":"Efficient training of visual transformers with small datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3326377"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3584406"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.47738\/ijiis.v4i1.73"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3250241"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0355-x"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108307"},{"issue":"8","key":"ref138","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100048"},{"key":"ref141","first-page":"1","article-title":"On the connection between pre-training data diversity and fine-tuning robustness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ramanujan"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.5220\/0012357400003660"},{"key":"ref143","first-page":"1","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Mu"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3348762"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-58547-0_17"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.wmt-1.60"},{"key":"ref147","first-page":"1","article-title":"ToolkenGPT: Augmenting Frozen language models with massive tools via tool embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Hao"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3126456"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-67529-x"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20150"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1051\/shsconf\/202214402006"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.005"},{"issue":"2","key":"ref155","first-page":"13","article-title":"Optimizing large language models: Performance, efficiency, and scalability","volume":"3","author":"Ali","year":"2024","journal-title":"Eastern Eur. J. Multidiscipl. Res."},{"key":"ref156","article-title":"Adapprox: Adaptive approximation in adam optimization via randomized low-rank matrices","author":"Zhao","year":"2024","journal-title":"arxiv:2403.14958"},{"key":"ref157","first-page":"12","article-title":"AdaMeM: Memory efficient momentum for adafactor","volume-title":"Proc. 2nd Workshop Adv. Neural Netw. Training Comput. Efficiency Scalability Resource Optim.","author":"Vyas"},{"key":"ref158","first-page":"4603","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shazeer"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-42536-3_32"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3190307"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-10966-8"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.72"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929141"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-023-00235-6"},{"key":"ref165","volume-title":"Attention mechanism, transformers, BERT, and GPT: tutorial and survey.","author":"Ghojogh","year":"2020"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1016\/j.surfcoat.2023.129680"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975321.77"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016473"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3520312.3534862"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1515\/lingty-2019-0025"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3195888"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/305"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2962617"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_33"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1080\/13645579.2016.1252188"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.87"},{"key":"ref178","first-page":"2405","article-title":"SiBert: Enhanced Chinese pre-trained language model with sentence insertion","volume-title":"Proc. 12th Lang. Resources Eval. Conf.","author":"Chen"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2014.6920341"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09918-2"},{"issue":"112","key":"ref182","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"Shallue","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00914-1"},{"key":"ref184","first-page":"642","article-title":"UnilMv2: Pseudo-masked language models for unified language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bao"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657807"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2994657"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3003307"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2795007"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3399813"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2024.107523"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2022.04.024"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8979-9_14"},{"key":"ref193","article-title":"Domain-specific fine-tuning of large language models for interactive robot programming","author":"Alt","year":"2023","journal-title":"arxiv:2312.13905"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03272-4"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73103-8_16"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1080\/08351813.2017.1340698"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/MIPRO60963.2024.10569238"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3376419"},{"key":"ref202","article-title":"GEMMA: Open models based on Gemini research and technology","author":"Team","year":"2024","journal-title":"arxiv:2403.08295"},{"key":"ref203","article-title":"GEMINI: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arxiv:2312.11805"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1561\/0600000110"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.26615\/issn.2683-0078.2023_008"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10423-5"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-6684-6001-6.ch005"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1007\/s10928-024-09921-y"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1145\/3657631"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1145\/3583781.3590256"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2024.104149"},{"key":"ref213","article-title":"TEGIT: Generating high-quality instruction-tuning data with text-grounded task design","author":"Chen","year":"2023","journal-title":"arxiv:2309.05447"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-50590-4_19"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1177\/01423312231188777"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad493"},{"key":"ref217","article-title":"A new era in LLM security: Exploring security concerns in real-world LLM-based systems","author":"Wu","year":"2024","journal-title":"arxiv:2402.18649"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628183"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.2024.3511662"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3420120"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2024.112127"},{"key":"ref222","article-title":"Large language model (LLM) assisted end-to-end network health management based on multi-scale semanticization","author":"Tang","year":"2024","journal-title":"arxiv:2406.08305"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA60707.2024.10666634"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2013.2266095"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1145\/3707649"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.521913"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2023.10272352"},{"key":"ref228","article-title":"A semantic invariant robust watermark for large language models","author":"Liu","year":"2023","journal-title":"arxiv:2310.06356"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1049\/icp.2023.2538"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1145\/3626111.3628194"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.112346"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.3390\/s24061888"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1587\/transcom.2022TMI0001"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.2478\/kbo-2023-0072"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/8658278"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.53555\/ephijse.v9i3.212"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3270368"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1145\/3656296"},{"key":"ref239","volume-title":"Explainable AI and random forest based reliable intrusion detection system.","author":"Wali","year":"2023"},{"key":"ref240","article-title":"Scalable, distributed AI frameworks: Leveraging cloud computing for enhanced deep learning performance and efficiency","author":"Mungoli","year":"2023","journal-title":"arxiv:2304.13738"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.131.2200477"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.3390\/app13179489"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3312155"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/IC2EM59347.2023.10419512"},{"key":"ref245","volume-title":"Simple mechanisms, rich structure: Statistical co-occurrence regularities in language shape the development of semantic knowledge.","author":"Unger","year":"2020"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.02.010"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3099804"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3026663"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4201"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3054833"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1201\/9781003348689"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/CONIT51480.2021.9498415"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105253"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1002\/pro.4205"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11010141"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.3390\/app10217748"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100255"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-019-10063-9"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.3390\/app8122475"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3519576"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3411008"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/GCAT55367.2022.9972119"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.3991\/ijoe.v19i07.39187"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.23919\/AEIT56783.2022.9951844"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3362889"},{"issue":"1","key":"ref267","first-page":"87","article-title":"Using Cisco VIRL and GNS3 to improve the scale-out of large virtual network testbeds in higher education","volume":"1","author":"Rei\u00dfmann","year":"2018","journal-title":"Int. J. Adv. Telecommun."},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.3390\/fi14010029"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2020.100289"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02056-1"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2962601"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2017.8057130"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjimei.2020.100004"},{"key":"ref276","first-page":"2391","article-title":"Adversarial variational Bayes: Unifying variational autoencoders and generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mescheder"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1568"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.3390\/e24010055"},{"key":"ref279","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"S\u00f8nderby"},{"key":"ref280","article-title":"Large language model (LLM) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities","author":"Zhou","year":"2024","journal-title":"arxiv:2405.10825"},{"key":"ref281","first-page":"1","article-title":"LLM-enhanced deepfake detection: Dense CNN and multi-modal fusion framework for precise multimedia authentication","volume-title":"Proc. IEEE Int. Conf. Adv. Data Eng. Intell. Comput. Syst. (ADICS)","author":"Enathe"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1080\/23270012.2020.1756939"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-3972-7_19"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993527"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107556"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2021.3062045"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/ojcoms.2024.3522103"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.2024.3435752"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.47852\/bonviewJCCE149145205514"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1093\/jigpal\/jzac024"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5276-7"},{"issue":"4","key":"ref293","first-page":"19","article-title":"Improving diagnostic imaging analysis with RPA and deep learning technologies","volume":"45","author":"Venigandla","year":"2021","journal-title":"Power Syst. Technol."},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.4108\/airo.v1i.19"},{"issue":"7","key":"ref295","first-page":"3897","article-title":"Machine learning and deep learning: A review of methods and applications","volume":"10","author":"Sharifani","year":"2023","journal-title":"World Inf. Technol. Eng. J."},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106833"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1145\/3396864.3399701"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/QRS60937.2023.00029"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.13052\/jwe1540-9589.2263"},{"issue":"3","key":"ref301","first-page":"45","article-title":"Advancements in deep learning for natural language processing in software applications","volume":"4","author":"Shah","year":"2020","journal-title":"Int. J. Comput. Sci. Technol."},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-6684-3632-5.ch016"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1145\/3505245"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.05.020"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104403"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2013.6461195"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/SURV.2009.090303"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.03.006"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2020.07.001"},{"key":"ref310","article-title":"6G comprehensive intelligence: Network operations and optimization based on Large Language models","author":"Long","year":"2024","journal-title":"arxiv:2404.18373"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3244674"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.3390\/s20236950"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106870"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1007\/s11668-020-01096-1"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10161-0"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2988208"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-7403-6_11"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05519-w"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.10.042"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijin.2022.08.005"},{"key":"ref321","article-title":"LLM dataset inference: Did you train on my dataset?","author":"Maini","year":"2024","journal-title":"arxiv:2406.06443"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1145\/3641512.3686358"},{"key":"ref323","volume-title":"Large language models: A comprehensive survey of its applications, challenges, limitations, and future prospects.","author":"Hadi","year":"2024"},{"key":"ref324","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-51630-6_6"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/8691095"},{"key":"ref327","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3367788"},{"key":"ref328","doi-asserted-by":"publisher","DOI":"10.1145\/3639372"},{"issue":"1","key":"ref329","first-page":"1","article-title":"Understanding the inner workings of large language models: Interpretability and explainability","volume":"1","author":"Ivanov","year":"2024","journal-title":"MZ J. Artif. Intell."},{"key":"ref330","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-50396-2_17"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3428519"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11303750\/10829820.pdf?arnumber=10829820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:03:44Z","timestamp":1766171024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10829820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":331,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/comst.2025.3526606","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}