{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:31:33Z","timestamp":1783787493927,"version":"3.55.0"},"reference-count":282,"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":"am","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":[{"name":"National Key Research and Development Program of China","award":["2024YFC3014900"],"award-info":[{"award-number":["2024YFC3014900"]}]},{"name":"National NSFC","award":["62372072"],"award-info":[{"award-number":["62372072"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024CDJGF-003"],"award-info":[{"award-number":["2024CDJGF-003"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Key Research and Development Program of Chongqing","award":["CSTB2024TIAD-STX0024"],"award-info":[{"award-number":["CSTB2024TIAD-STX0024"]}]},{"name":"Science and Technology Innovation Key Research and Development Program of Chongqing","award":["CSTB2023TIAD-STX0035"],"award-info":[{"award-number":["CSTB2023TIAD-STX0035"]}]},{"name":"Chongqing Talent Program Contract System Project","award":["cstc2024ycjh-bgzxm0042"],"award-info":[{"award-number":["cstc2024ycjh-bgzxm0042"]}]},{"name":"Haihe Lab of ITAI","award":["22HHXCJC00002"],"award-info":[{"award-number":["22HHXCJC00002"]}]},{"name":"Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications","award":["BDIC-2023-B-003"],"award-info":[{"award-number":["BDIC-2023-B-003"]}]},{"name":"Sichuan Science and Technology Program","award":["2024YFHZ0097"],"award-info":[{"award-number":["2024YFHZ0097"]}]},{"name":"Regional Science and Technology Innovation Cooperation Project of Chengdu City","award":["2023-YF11-00023-HZ"],"award-info":[{"award-number":["2023-YF11-00023-HZ"]}]},{"name":"NSF","award":["ECCS-2302469"],"award-info":[{"award-number":["ECCS-2302469"]}]},{"name":"NSF","award":["CMMI-2222810"],"award-info":[{"award-number":["CMMI-2222810"]}]},{"DOI":"10.13039\/501100004405","name":"Toyota Motor Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004405","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Amazon"},{"name":"Japan Science and Technology Agency (JST) Adopting Sustainable Partnerships for Innovative Research Ecosystem","award":["JPMJAP2326"],"award-info":[{"award-number":["JPMJAP2326"]}]},{"name":"Guangdong Pearl River Talent Recruitment Program","award":["2019ZT08X603"],"award-info":[{"award-number":["2019ZT08X603"]}]},{"name":"Guangdong Pearl River Talent Recruitment Program","award":["2019JC01X235"],"award-info":[{"award-number":["2019JC01X235"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/comst.2025.3587225","type":"journal-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:23:01Z","timestamp":1752103381000},"page":"1248-1284","source":"Crossref","is-referenced-by-count":5,"title":["Edge-Enhanced Intelligence: A Comprehensive Survey of Large Language Models and Edge-Cloud Computing Synergy"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9041-0297","authenticated-orcid":false,"given":"Xiuhua","family":"Li","sequence":"first","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0222-5150","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5512-687X","authenticated-orcid":false,"given":"Chuan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computer and Information Science, Chongqing Normal University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0856-3695","authenticated-orcid":false,"given":"Qilin","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6606-5822","authenticated-orcid":false,"given":"Zhu","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3529-2640","authenticated-orcid":false,"given":"Victor C. M.","family":"Leung","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30761-2"},{"key":"ref2","article-title":"An overview of research on human-centered design in the development of artificial general intelligence","author":"Yue","year":"2023","journal-title":"arXiv:2309.12352"},{"key":"ref3","article-title":"Towards artificial general intelligence (AGI) in the Internet of Things (IoT): Opportunities and challenges","author":"Dou","year":"2023","journal-title":"arXiv:2309.07438"},{"key":"ref4","volume-title":"Planning for AGI and beyond","author":"Altman","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref6","article-title":"Artificial general intelligence (AGI) for education","author":"Latif","year":"2023","journal-title":"arXiv:2304.12479"},{"key":"ref7","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref9","article-title":"One small step for generative AI, one giant leap for AGI: A complete survey on ChatGPT in AIGC era","author":"Zhang","year":"2023","journal-title":"arXiv:2304.06488"},{"key":"ref10","volume-title":"GPT-4 technical report","year":"2023"},{"key":"ref11","volume-title":"Deploy and run LLMs at the edge","author":"Munday","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3617689"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2917084"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2023.3312369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3107424"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00076"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586176"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00405"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3183098"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3177782"},{"key":"ref21","article-title":"Revolutionizing mobile interaction: Enabling a 3 billion parameter GPT LLM on mobile","author":"Carreira","year":"2023","journal-title":"arXiv:2310.01434"},{"key":"ref22","article-title":"LAMBO: Large language model empowered edge intelligence","author":"Dong","year":"2023","journal-title":"arXiv:2308.15078"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3650203.3663331"},{"key":"ref24","article-title":"Federated fine-tuning of billion-sized language models across mobile devices","author":"Xu","year":"2023","journal-title":"arXiv:2308.13894"},{"key":"ref25","article-title":"Empowering LLM to use smartphone for intelligent task automation","author":"Wen","year":"2023","journal-title":"arXiv:2308.15272"},{"key":"ref26","article-title":"EdgeMoE: Fast on-device inference of MoE-based large language models","author":"Yi","year":"2023","journal-title":"arXiv:2308.14352"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/mcom.001.2300550"},{"key":"ref28","article-title":"ModuLoRA: Finetuning 3-bit LLMs on consumer GPUs by integrating with modular quantizers","author":"Yin","year":"2023","journal-title":"arXiv:2309.16119"},{"key":"ref29","article-title":"Evaluating large language models: A comprehensive survey","author":"Guo","year":"2023","journal-title":"arXiv:2310.19736"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3649506"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.25082\/IJAH.2023.01.003"},{"key":"ref32","first-page":"12312","article-title":"Distributed inference and fine-tuning of large language models over the Internet","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Borzunov"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3008711"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2966870"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3200431"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3315746"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-022-00377-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486998"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3111731"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM57956.2023.00015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3223119"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2021.02.011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.23919\/jcc.ja.2021-0776"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3205551"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107556"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3199544"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/OJCS.2023.3300321"},{"key":"ref50","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv:2303.18223"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2970550"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3218527"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2022.04.004"},{"key":"ref54","article-title":"Pushing large language models to the 6G edge: Vision, challenges, and opportunities","author":"Lin","year":"2023","journal-title":"arXiv:2309.16739"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3736721"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3527641"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2024.3353265"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.006.2300223"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"ref61","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv:2206.07682"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"240","key":"ref63","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/s41368-023-00239-y"},{"key":"ref66","first-page":"16083","article-title":"Any-to-any generation via composable diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Tang"},{"key":"ref67","article-title":"Macaw-LLM: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023","journal-title":"arXiv:2306.09093"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1561\/0600000110"},{"key":"ref69","article-title":"PanGu-Coder2: Boosting large language models for code with ranking feedback","author":"Shen","year":"2023","journal-title":"arXiv:2307.14936"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref71","article-title":"BloombergGPT: A large language model for finance","author":"Wu","year":"2023","journal-title":"arXiv:2303.17564"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3571884.3604313"},{"key":"ref73","article-title":"How abilities in large language models are affected by supervised fine-tuning data composition","author":"Dong","year":"2023","journal-title":"arXiv:2310.05492"},{"key":"ref74","article-title":"Secrets of RLHF in large language models part I: PPO","author":"Zheng","year":"2023","journal-title":"arXiv:2307.04964"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/tr.2023.3297124"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tnse.2023.3296511"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD57460.2023.10152842"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3464419"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2023.3332507"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC55385.2023.10119013"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3119181"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3624478"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178211"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3362031"},{"key":"ref85","article-title":"NetGPT: A native-AI network architecture beyond provisioning personalized generative services","author":"Chen","year":"2023","journal-title":"arXiv:2307.06148"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/tsusc.2023.3291365"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.10.033"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3520129"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-2879-6_6"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56950-0_47"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3511094"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3469660"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2022.3216360"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"ref95","article-title":"AI-native interconnect framework for integration of large language model technologies in 6G systems","author":"Tarkoma","year":"2023","journal-title":"arXiv:2311.05842"},{"key":"ref96","first-page":"21702","article-title":"LLM-Pruner: On the structural pruning of large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ma"},{"key":"ref97","first-page":"1","article-title":"A simple and effective pruning approach for large language models","volume-title":"Proc. ICLR","author":"Sun"},{"key":"ref98","first-page":"1","article-title":"QLLM: Accurate and efficient low-bitwidth quantization for large language models","volume-title":"Proc. ICLR","author":"Liu"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2022.3229221"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1145\/3539606"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3434770.3459730"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.2025.3539338"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124736"},{"key":"ref105","first-page":"709","article-title":"Characterization of large language model development in the datacenter","volume-title":"Proc. USENIX NSDI","author":"Hu"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3603287.3651205"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"ref108","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Lin"},{"key":"ref109","first-page":"1","article-title":"TinyAgent: Quantization-aware model compression and adaptation for on-device LLM agent deployment","volume-title":"Proc. ICML Workshop","author":"Kong"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2024.3524255"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3415661"},{"key":"ref112","first-page":"4226","article-title":"CulturaX: A cleaned, enormous, and multilingual dataset for large language models in 167 languages","volume-title":"Proc. LREC-COLING","author":"Nguy\u1ebdn"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/MSN48538.2019.00030"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2021.3120003"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3112186"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2952645"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3095285"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/SECON58729.2023.10287530"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3560905.3567762"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2938861"},{"key":"ref121","article-title":"When foundation model meets federated learning: Motivations, challenges, and future directions","author":"Zhuang","year":"2023","journal-title":"arXiv:2306.15546"},{"key":"ref122","first-page":"7174","article-title":"Federated foundation models: Privacy-preserving and collaborative learning for large models","volume-title":"Proc. LREC-COLING","author":"Yu"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3338153"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671573"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-7707-5_28"},{"key":"ref127","article-title":"FATE-LLM: A industrial grade federated learning framework for large language models","author":"Fan","year":"2023","journal-title":"arXiv:2310.10049"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3191748"},{"key":"ref129","article-title":"FusionAI: Decentralized training and deploying LLMs with massive consumer-level GPUs","author":"Tang","year":"2023","journal-title":"arXiv:2309.01172"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3225292"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2882588"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155413"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109430"},{"key":"ref134","first-page":"353","article-title":"Modeling and optimization for computing power resource-aware in CPN","volume-title":"Proc. IEEE APNOMS","author":"Li"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2021.10.006"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2913169"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109311"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3597023"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2022.3201544"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.09.001"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-023-02243-2"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2023.3288021"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3249745"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.11.026"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3189962"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2200131"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3140080"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3240301"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS57198.2023.10188741"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2020.2994737"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3041453"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN58024.2023.10230190"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3222509"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3280174"},{"key":"ref156","first-page":"663","article-title":"AlpaServe: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"Proc. USENIX Symp. OSDI","author":"Li"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413553"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3272567"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036971"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.045"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3282648"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2022.3210905"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2020.3022080"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3059305"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986015"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01467"},{"key":"ref169","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sanh"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/586"},{"key":"ref171","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. PMLR ICML","author":"Frantar"},{"key":"ref172","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. ACM ICML","author":"Xiao"},{"key":"ref173","first-page":"177","article-title":"Octo: INT8 training with loss-aware compensation and backward quantization for tiny on-device learning","volume-title":"Proc. USENIX ATC","author":"Zhou"},{"key":"ref174","article-title":"Understanding the impact of post-training quantization on large-scale language models","author":"Roy","year":"2023","journal-title":"arXiv:2309.05210"},{"key":"ref175","article-title":"A survey on model compression for large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2308.07633"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096632"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.240"},{"key":"ref178","article-title":"FPTQ: Fine-grained post-training quantization for large language models","author":"Li","year":"2023","journal-title":"arXiv:2308.15987"},{"key":"ref179","article-title":"EdgeQAT: Entropy and distribution guided quantization-aware training for the acceleration of lightweight LLMs on the edge","author":"Shen","year":"2024","journal-title":"arXiv:2402.10787"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.09.015"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531775"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref184","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00895"},{"key":"ref186","first-page":"20852","article-title":"Less is more: Task-aware layer-wise distillation for language model compression","volume-title":"Proc. ACM ICML","author":"Liang"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3237749"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21423"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00296"},{"key":"ref191","article-title":"Fusion of mixture of experts and generative artificial intelligence in mobile edge metaverse","author":"Liu","year":"2024","journal-title":"arXiv:2404.03321"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323651"},{"key":"ref193","article-title":"Serving MoE models on resource-constrained edge devices via dynamic expert swapping","author":"Kong","year":"2023","journal-title":"arXiv:2308.15030"},{"key":"ref194","article-title":"Infinite-LLM: Efficient LLM service for long context with distattention and distributed kvcache","author":"Lin","year":"2024","journal-title":"arXiv:2401.02669"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref196","article-title":"RankAdaptor: Hierarchical dynamic low-rank adaptation for structural pruned LLMs","author":"Zhou","year":"2024","journal-title":"arXiv:2406.15734"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.178"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467078"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.15"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.450"},{"key":"ref201","article-title":"Examining post-training quantization for mixture-of-experts: A benchmark","author":"Li","year":"2024","journal-title":"arXiv:2406.08155"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2300346"},{"key":"ref203","article-title":"Towards semantic communication protocols for 6G: From protocol learning to language-oriented approaches","author":"Park","year":"2023","journal-title":"arXiv:2310.09506"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-69474-5"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3320646"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref207","article-title":"Analyzing the efficacy of an LLM-only approach for image-based document question answering","author":"Hegde","year":"2023","journal-title":"arXiv:2309.14389"},{"key":"ref208","first-page":"42961","article-title":"UniControl: A unified diffusion model for controllable visual generation in the wild","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Qin"},{"key":"ref209","article-title":"VideoDirectorGPT: Consistent multi-scene video generation via LLM-guided planning","author":"Lin","year":"2023","journal-title":"arXiv:2309.15091"},{"key":"ref210","first-page":"1","article-title":"Large language models are frame-level directors for zero-shot text-to-video generation","volume-title":"Proc. ICML Workshop","author":"Hong"},{"key":"ref211","article-title":"Towards language-guided interactive 3D generation: LLMs as layout interpreter with generative feedback","author":"Lin","year":"2023","journal-title":"arXiv:2305.15808"},{"key":"ref212","first-page":"20482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Hong"},{"key":"ref213","first-page":"21487","article-title":"Generating images with multimodal language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Koh"},{"key":"ref214","article-title":"LLM-grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models","author":"Lian","year":"2023","journal-title":"arXiv:2305.13655"},{"key":"ref215","first-page":"1","article-title":"LLM Blueprint: Enabling text-to-image generation with complex and detailed prompts","volume-title":"Proc. ICRL","author":"Gani"},{"key":"ref216","article-title":"Reuse and diffuse: Iterative denoising for text-to-video generation","author":"Gu","year":"2023","journal-title":"arXiv:2309.03549"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327197"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3427313"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2024.103645"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3363469"},{"key":"ref221","article-title":"Achieving >97% on GSM8K: Deeply understanding the problems makes LLMs perfect reasoners","author":"Zhong","year":"2024","journal-title":"arXiv:2404.14963"},{"key":"ref222","article-title":"LLM-empowered resource allocation in wireless communications systems","author":"Lee","year":"2024","journal-title":"arXiv:2408.02944"},{"key":"ref223","article-title":"Wireless multi-agent generative AI: From connected intelligence to collective intelligence","author":"Zou","year":"2023","journal-title":"arXiv:2307.02757"},{"key":"ref224","first-page":"1","article-title":"NExT-GPT: Any-to-any multimodal LLM","volume-title":"Proc. ICML","author":"Wu"},{"key":"ref225","article-title":"MiniGPT-5: Interleaved vision-and-language generation via generative vokens","author":"Zheng","year":"2023","journal-title":"arXiv:2310.02239"},{"key":"ref226","first-page":"1","article-title":"GenSim: Generating robotic simulation tasks via large language models","volume-title":"Proc. ICRL","author":"Wang"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386490"},{"key":"ref228","first-page":"1","article-title":"Towards end-to-end embodied decision making via multi-modal large language model: Explorations with GPT4-vision and beyond","volume-title":"Proc. NeurIPS Workshop","author":"Chen"},{"key":"ref229","article-title":"OlaGPT: Empowering LLMs with human-like problem-solving abilities","author":"Xie","year":"2023","journal-title":"arXiv:2305.16334"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1383-7"},{"key":"ref232","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv:2205.06175"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2023.9150026"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539263"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01276-1"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7587-7_14"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.677"},{"key":"ref238","first-page":"202","article-title":"KITLM: Domain-specific knowledge integration into language models for question answering","volume-title":"Proc. ICON","author":"Ankush"},{"key":"ref239","first-page":"1","article-title":"Domain prompts: Towards memory and compute efficient domain adaptation of ASR systems","volume-title":"Proc. Interspeech","author":"Dingliwa"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.558"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.165"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-7232-2_19"},{"key":"ref243","article-title":"Do LLMs understand user preferences? Evaluating LLMs on user rating prediction","author":"Kang","year":"2023","journal-title":"arXiv:2305.06474"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657807"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.30693\/smj.2023.12.6.35"},{"key":"ref246","article-title":"Memory-augmented LLM personalization with short-and long-term memory coordination","author":"Zhang","year":"2023","journal-title":"arXiv:2309.11696"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3235443"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3155448"},{"key":"ref249","first-page":"10146","article-title":"Large language models for generative recommendation: A survey and visionary discussions","volume-title":"Proc. LREC-COLING","author":"Li"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3392335"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.39"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1145\/3731446"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608874"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625793"},{"key":"ref255","article-title":"LanguageMPC: Large language models as decision makers for autonomous driving","author":"Sha","year":"2023","journal-title":"arXiv:2310.03026"},{"key":"ref256","first-page":"1","article-title":"DiLu: A knowledge-driven approach to autonomous driving with large language models","volume-title":"Proc. ICLR","author":"Wen"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref258","article-title":"Can you text what is happening? Integrating pre-trained language encoders into trajectory prediction models for autonomous driving","author":"Keysan","year":"2023","journal-title":"arXiv:2309.05282"},{"key":"ref259","first-page":"1","article-title":"GPT-Driver: Learning to drive with GPT","volume-title":"Proc. NeurIPS Workshop","author":"Mao"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3307012"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2024.3493775"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2023.08.094"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0300919"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.336"},{"key":"ref267","article-title":"MedEdit: Model editing for medical question answering with external knowledge bases","author":"Shi","year":"2023","journal-title":"arXiv:2309.16035"},{"key":"ref268","article-title":"LLM as a robotic brain: Unifying egocentric memory and control","author":"Mai","year":"2023","journal-title":"arXiv:2304.09349"},{"key":"ref269","article-title":"LLM-based human-robot collaboration framework for manipulation tasks","author":"Liu","year":"2023","journal-title":"arXiv:2308.14972"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341488"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10132-6"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref273","article-title":"Myriad: Large multimodal model by applying vision experts for industrial anomaly detection","author":"Li","year":"2023","journal-title":"arXiv:2310.19070"},{"key":"ref274","article-title":"HuntGPT: Integrating machine learning-based anomaly detection and explainable AI with large language models (LLMs)","author":"Ali","year":"2023","journal-title":"arXiv:2309.16021"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys60770.2023.00045"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1145\/3588195.3595943"},{"key":"ref277","first-page":"1","article-title":"Towards large language models at the edge on mobile, augmented reality, and virtual reality devices with unity","volume-title":"Proc. ACM Workshop SAGE","author":"Morales"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26255"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859804"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3126021"},{"key":"ref281","article-title":"Transfer learning for power outage detection task with limited training data","author":"Owolabi","year":"2023","journal-title":"arXiv:2305.17817"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2019.109585"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9739\/11321210\/11075838-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11321210\/11075838.pdf?arnumber=11075838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T18:18:36Z","timestamp":1767377916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11075838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":282,"URL":"https:\/\/doi.org\/10.1109\/comst.2025.3587225","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}