{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T10:03:57Z","timestamp":1784282637352,"version":"3.55.0"},"reference-count":273,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/comst.2025.3641591","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:43:49Z","timestamp":1765219429000},"page":"4051-4085","source":"Crossref","is-referenced-by-count":4,"title":["Mixture of Experts for Decentralized Generative AI and Reinforcement Learning in Wireless Networks: A Comprehensive Survey"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6341-4698","authenticated-orcid":false,"given":"Yunting","family":"Xu","sequence":"first","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1252-8761","authenticated-orcid":false,"given":"Jiacheng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6859-3645","authenticated-orcid":false,"given":"Ruichen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9187-9572","authenticated-orcid":false,"given":"Changyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8218-3490","authenticated-orcid":false,"given":"Jiawen","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Automation, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4440-941X","authenticated-orcid":false,"given":"Zehui","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Electronics, Electrical Engineering and Computer Science (EEECS), Queen’s University Belfast, Belfast, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6964-220X","authenticated-orcid":false,"given":"Bo","family":"Qian","sequence":"additional","affiliation":[{"name":"Information Systems Architecture Science Research Division, National Institute of Informatics, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6549-8917","authenticated-orcid":false,"given":"Haibo","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7052-0007","authenticated-orcid":false,"given":"Shiwen","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1807-7220","authenticated-orcid":false,"given":"Abbas","family":"Jamalipour","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","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\/0000-0001-7711-8072","authenticated-orcid":false,"given":"Dong In","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.015.2300404"},{"key":"ref2","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3541967"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3456549"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.008.2200157"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3452639"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3353265"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2024.10582829"},{"key":"ref9","article-title":"Transformers are provably optimal in-context estimators for wireless communications","author":"Kunde","year":"2023","journal-title":"arXiv:2311.00226"},{"key":"ref10","article-title":"LLM-empowered resource allocation in wireless communications systems","author":"Lee","year":"2024","journal-title":"arXiv:2408.02944"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300364"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.005.2400019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3462556"},{"key":"ref14","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"issue":"240","key":"ref15","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","article-title":"GPT-4: A review on advancements and opportunities in natural language processing","author":"Baktash","year":"2023","journal-title":"arXiv:2305.03195"},{"key":"ref17","article-title":"Mobile edge intelligence for large language models: A contemporary survey","author":"Qu","year":"2024","journal-title":"arXiv:2407.18921"},{"key":"ref18","article-title":"Large language models: A comprehensive survey of its applications, challenges, limitations, and future prospects","author":"Hadi","year":"2023","journal-title":"TechRxiv Preprint"},{"key":"ref19","article-title":"Towards greener LLMs: Bringing energy-efficiency to the forefront of LLM inference","author":"Stojkovic","year":"2024","journal-title":"arXiv:2403.20306"},{"key":"ref20","article-title":"Large language models for wireless networks: An overview from the prompt engineering perspective","author":"Zhou","year":"2024","journal-title":"arXiv:2411.04136"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3465447"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300550"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3359040"},{"key":"ref26","first-page":"17456","article-title":"Confident adaptive language modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Schuster"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200299"},{"key":"ref28","article-title":"The evolution of mixture of experts: A survey from basics to breakthroughs","author":"Vats","year":"2024","journal-title":"Preprints"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"},{"key":"ref30","article-title":"A survey on inference optimization techniques for mixture of experts models","author":"Liu","year":"2024","journal-title":"arXiv:2412.14219"},{"key":"ref31","article-title":"From Google Gemini to OpenAI Q*(Q-star): A survey of reshaping the generative artificial intelligence (AI) research landscape","author":"McIntosh","year":"2023","journal-title":"arXiv:2312.10868"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2025.3554028"},{"key":"ref33","article-title":"Efficient large language models: A survey","author":"Wan","year":"2023","journal-title":"arXiv:2312.03863"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3384500"},{"key":"ref35","article-title":"A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT","author":"Cao","year":"2023","journal-title":"arXiv:2303.04226"},{"key":"ref36","article-title":"Integration of mixture of experts and multimodal generative AI in Internet of Vehicles: A survey","author":"Xu","year":"2024","journal-title":"arXiv:2404.16356"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753633402"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.278"},{"key":"ref39","article-title":"JetMoE: Reaching Llama2 performance with 0.1M dollars","author":"Shen","year":"2024","journal-title":"arXiv:2404.07413"},{"key":"ref40","article-title":"Branch-Train-merge: Embarrassingly parallel training of expert language models","author":"Li","year":"2022","journal-title":"arXiv:2208.03306"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref43","article-title":"LoRAMoE: Alleviate world knowledge forgetting in large language models via MoE-style plugin","author":"Dou","year":"2023","journal-title":"arXiv:2312.09979"},{"key":"ref44","article-title":"Mixture of LoRA experts","author":"Wu","year":"2024","journal-title":"arXiv:2404.13628"},{"key":"ref45","article-title":"Dense training, sparse inference: Rethinking training of mixture-of-experts language models","author":"Pan","year":"2024","journal-title":"arXiv:2404.05567"},{"key":"ref46","article-title":"Learning factored representations in a deep mixture of experts","author":"Eigen","year":"2013","journal-title":"arXiv:1312.4314"},{"key":"ref47","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"key":"ref48","first-page":"5547","article-title":"GLaM: Efficient scaling of language models with mixture-of-experts","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Du"},{"key":"ref49","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv:2006.16668"},{"issue":"120","key":"ref50","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. NIPS","author":"Riquelme"},{"key":"ref52","article-title":"On expert estimation in hierarchical mixture of experts: Beyond softmax gating functions","author":"Nguyen","year":"2024","journal-title":"arXiv:2410.02935"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2023.08.156"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.34033"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095401"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/122"},{"key":"ref58","article-title":"Exploring sparse MoE in GANs for text-conditioned image synthesis","author":"Zhu","year":"2023","journal-title":"arXiv:2309.03904"},{"key":"ref59","first-page":"15692","article-title":"Variational mixture-of-experts autoencoders for multi-modal deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Shi"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01944-5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3078489"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3384058"},{"key":"ref63","article-title":"EDiff-I: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv:2211.01324"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_4"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_27"},{"key":"ref66","first-page":"22243","article-title":"Meta-DMoE: Adapting to domain shift by meta-distillation from mixture-of-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tao"},{"key":"ref67","article-title":"Uni-MoE: Scaling unified multimodal LLMs with mixture of experts","author":"Li","year":"2024","journal-title":"arXiv:2405.11273"},{"key":"ref68","article-title":"LLaMA-MoE v2: Exploring sparsity of LLaMA from perspective of mixture-of-experts with post-training","author":"Qu","year":"2024","journal-title":"arXiv:2411.15708"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref70","article-title":"Efficient large scale language modeling with mixtures of experts","author":"Artetxe","year":"2021","journal-title":"arXiv:2112.10684"},{"key":"ref71","article-title":"Mixtures of experts unlock parameter scaling for deep RL","author":"Obando-Ceron","year":"2024","journal-title":"arXiv:2402.08609"},{"key":"ref72","article-title":"Double deep Q-learning in opponent modeling","author":"Tao","year":"2022","journal-title":"arXiv:2211.15384"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015933"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/11840541_33"},{"issue":"2","key":"ref75","first-page":"154","article-title":"A mixture-of-experts approach to production capacity planning for diverse demand patterns via deep reinforcement learning","volume":"10","author":"Danket","year":"2024","journal-title":"Eng. Access"},{"key":"ref76","article-title":"Comparing deterministic and soft policy gradients for optimizing Gaussian mixture actors","author":"Dey","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref77","article-title":"Probabilistic mixture-of-experts for efficient deep reinforcement learning","author":"Ren","year":"2021","journal-title":"arXiv:2104.09122"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448500"},{"key":"ref79","article-title":"Optimizing generative AI networking: A dual perspective with multi-agent systems and mixture of experts","author":"Zhang","year":"2024","journal-title":"arXiv:2405.12472"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA251051"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00709-2"},{"key":"ref82","first-page":"26242","article-title":"Learning expressive meta-representations with mixture of expert neural processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Wang"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3271445"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119951"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1186\/s10033-024-01158-7"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104369"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366531"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2024.101270"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3459037"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/IS.2002.1044260"},{"key":"ref91","article-title":"Meta-reinforcement learning with mixture of experts for generalizable multi access in heterogeneous wireless networks","author":"Liu","year":"2024","journal-title":"arXiv:2412.03850"},{"key":"ref92","article-title":"Optimizing 6G integrated sensing and communications (ISAC) via expert networks","author":"Wang","year":"2024","journal-title":"arXiv:2406.00408"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715410"},{"key":"ref94","article-title":"Theory of mixture-of-experts for mobile edge computing","author":"Li","year":"2024","journal-title":"arXiv:2412.15690"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.3233\/KES-2006-10302"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322198"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2025.3570469"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-SoC62099.2024.10767787"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/IMS37962.2022.9865530"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TMTT.2023.3341616"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154235"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9882279"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC61514.2024.10592370"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2022-Spring54318.2022.9860682"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671507"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2024.3523318"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323651"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901084"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13112077"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3379270"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1708953"},{"key":"ref112","article-title":"Enhancing physical layer communication security through generative AI with mixture of experts","author":"Zhao","year":"2024","journal-title":"arXiv:2405.04198"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"issue":"140","key":"ref114","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref115","article-title":"TeleQnA: A benchmark dataset to assess large language models telecommunications knowledge","author":"Maatouk","year":"2023","journal-title":"arXiv:2310.15051"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref120","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Schuhmann"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2797022"},{"key":"ref123","article-title":"DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications","author":"Alkhateeb","year":"2019","journal-title":"arXiv:1902.06435"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1177\/03611981231185768"},{"key":"ref125","article-title":"A survey of resource-efficient LLM and multimodal foundation models","author":"Xu","year":"2024","journal-title":"arXiv:2401.08092"},{"key":"ref126","first-page":"9564","article-title":"Multimodal contrastive learning with LIMoE: The language-image mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Mustafa"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3401159"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3236003"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3532342"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2987014"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.aeue.2020.153372"},{"key":"ref132","first-page":"29335","article-title":"DSelect-k: Differentiable selection in the mixture of experts with applications to multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Hazimeh"},{"key":"ref133","article-title":"Bayesian hierarchical mixtures of experts","author":"Bishop","year":"2012","journal-title":"arXiv:1212.2447"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-007-9043-z"},{"key":"ref135","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref136","article-title":"Skywork-MoE: A deep dive into training techniques for mixture-of-experts language models","author":"Wei","year":"2024","journal-title":"arXiv:2406.06563"},{"key":"ref137","article-title":"Residual mixture of experts","author":"Wu","year":"2022","journal-title":"arXiv:2204.09636"},{"key":"ref138","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhou"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.319"},{"key":"ref140","first-page":"18332","article-title":"DeepSpeed-MoE: Advancing mixture-of-experts inference and training to power next-generation AI scale","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rajbhandari"},{"key":"ref141","article-title":"ST-MoE: Designing stable and transferable sparse expert models","author":"Zoph","year":"2022","journal-title":"arXiv:2202.08906"},{"key":"ref142","article-title":"Mixture-of-experts meets instruction tuning: A winning combination for large language models","author":"Shen","year":"2023","journal-title":"arXiv:2305.14705"},{"key":"ref143","article-title":"LLaVA-MoD: Making LLaVA tiny via MoE knowledge distillation","author":"Shu","year":"2024","journal-title":"arXiv:2408.15881"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3594102"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.525"},{"key":"ref147","article-title":"Multi-generator generative adversarial nets","author":"Hoang","year":"2017","journal-title":"arXiv:1708.02556"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436728"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00977"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29245"},{"key":"ref151","article-title":"Staleness-centric optimizations for parallel diffusion MoE inference","author":"Luo","year":"2024","journal-title":"arXiv:2411.16786"},{"key":"ref152","article-title":"Mobile V-MoEs: Scaling down vision transformers via sparse mixture-of-experts","author":"Daxberger","year":"2023","journal-title":"arXiv:2309.04354"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105287"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC60668.2024.10694106"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC60668.2024.10694591"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3535554"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref160","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref161","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref163","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref164","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1145\/3665348.3665372"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401238"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126485"},{"key":"ref168","article-title":"Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model","author":"Cui","year":"2023","journal-title":"arXiv:2306.16092"},{"key":"ref169","article-title":"Mixture of experts in a mixture of RL settings","author":"Willi","year":"2024","journal-title":"arXiv:2406.18420"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968149"},{"key":"ref171","article-title":"A mixture-of-expert approach to RL-based dialogue management","author":"Chow","year":"2022","journal-title":"arXiv:2206.00059"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2025.3597910"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3240707"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.3390\/s23187709"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118397"},{"issue":"107","key":"ref176","first-page":"1","article-title":"Beyond english-centric multilingual machine translation","volume":"22","author":"Fan","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref177","article-title":"Alt-MoE: Multimodal alignment via alternating optimization of multi-directional moe with unimodal models","author":"Lei","year":"2024","journal-title":"arXiv:2409.05929"},{"key":"ref178","article-title":"MoE-AMC: Enhancing automatic modulation classification performance using mixture-of-experts","author":"Gao","year":"2023","journal-title":"arXiv:2312.02298"},{"key":"ref179","article-title":"MoVA: Adapting mixture of vision experts to multimodal context","author":"Zong","year":"2024","journal-title":"arXiv:2404.13046"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.3390\/app11052040"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3336310"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3185249"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3054649"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3303490"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.3390\/rs9050459"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2495297"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088632"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI52147.2023.10371877"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3239080"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2022.10005214"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.011.2200198"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3207967"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3327596"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2024.3387707"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3211005"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3335233"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3432871"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2953172"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500604"},{"key":"ref200","article-title":"EdgeMoE: Empowering sparse large language models on mobile devices","author":"Yi","year":"2023","journal-title":"arXiv:2308.14352"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685076"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14112188"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3454328"},{"key":"ref205","article-title":"PWC-MoE: Privacy-aware wireless collaborative mixture of experts","author":"Su","year":"2025","journal-title":"arXiv:2505.08719"},{"key":"ref206","article-title":"Split federated learning for UAV-enabled integrated sensing, computation, and communication","author":"Hou","year":"2025","journal-title":"arXiv:2504.01443"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3306773"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3280359"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3395388"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3371501"},{"key":"ref211","article-title":"When MoE meets blockchain: A trustworthy distributed framework of large models","author":"Zhu","year":"2025","journal-title":"arXiv:2509.12141"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3446585"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-85181-0_21"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3523181"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2025.3550055"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2023.3260443"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2320074"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2005.1465135"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2016.7752732"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-009-0288-5"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41136-6_11"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-017-0376-0"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3101364"},{"key":"ref224","article-title":"Sionna: An open-source library for next-generation physical layer research","author":"Hoydis","year":"2022","journal-title":"arXiv:2203.11854"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2023.3266379"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3495719"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.016.2300547"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.007.2300582"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3058999"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3347580"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3422241"},{"key":"ref232","article-title":"Interpretable mixture of experts for time series prediction under recurrent and non-recurrent conditions","author":"Ke","year":"2024","journal-title":"arXiv:2409.03282"},{"key":"ref233","article-title":"Generalizing motion planners with mixture of experts for autonomous driving","author":"Sun","year":"2024","journal-title":"arXiv:2410.15774"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3356554"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2018.2874555"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1145\/3588964"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3422309"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3541078"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2023.3346824"},{"key":"ref240","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":"ref241","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774692"},{"key":"ref242","article-title":"EPS-MoE: Expert pipeline scheduler for cost-efficient MoE inference","author":"Qian","year":"2024","journal-title":"arXiv:2410.12247"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.23"},{"key":"ref244","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv:2401.04088"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.40895"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3438379"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2916209"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2939742"},{"key":"ref250","article-title":"5G-NIDD: A comprehensive network intrusion detection dataset generated over 5G wireless network","author":"Samarakoon","year":"2022","journal-title":"arXiv:2212.01298"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3531577"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3400011"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1145\/3666025.3699355"},{"key":"ref254","article-title":"Mixture compressor for mixture-of-experts LLMs gains more","author":"Huang","year":"2024","journal-title":"arXiv:2410.06270"},{"key":"ref255","article-title":"Expert-token resonance MoE: Bidirectional routing with efficiency affinity-driven active selection","author":"Li","year":"2024","journal-title":"arXiv:2406.00023"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.540"},{"key":"ref258","article-title":"SM3Det: A unified model for multi-modal remote sensing object detection","author":"Li","year":"2024","journal-title":"arXiv:2412.20665"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02549"},{"key":"ref260","first-page":"41693","article-title":"RAPHAEL: Text-to-image generation via large mixture of diffusion paths","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xue"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832196"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/FNWF58287.2023.10520606"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3035277"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Spring48590.2020.9128579"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104313"},{"key":"ref266","article-title":"Enhancing wireless networks for IoT with large vision models: Foundations and applications","author":"Xu","year":"2025","journal-title":"arXiv:2508.00583"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-248"},{"key":"ref268","article-title":"Efficient and robust quantization-aware training via adaptive coreset selection","author":"Huang","year":"2023","journal-title":"arXiv:2306.07215"},{"key":"ref269","article-title":"QKD: Quantization-aware knowledge distillation","author":"Kim","year":"2019","journal-title":"arXiv:1911.12491"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops67674.2025.11162260"},{"key":"ref271","article-title":"Mixture-of-experts meets in-context reinforcement learning","author":"Wu","year":"2025","journal-title":"arXiv:2506.05426"},{"key":"ref272","article-title":"Dynamic mixture of experts: An auto-tuning approach for efficient transformer models","author":"Guo","year":"2024","journal-title":"arXiv:2405.14297"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900252"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11321210\/11284842.pdf?arnumber=11284842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:05:48Z","timestamp":1768255548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11284842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":273,"URL":"https:\/\/doi.org\/10.1109\/comst.2025.3641591","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}