{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:04:53Z","timestamp":1781280293608,"version":"3.54.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council through AoE","award":["AoE\/E-601\/22R"],"award-info":[{"award-number":["AoE\/E-601\/22R"]}]},{"name":"NSFC\/RGC Joint Research Scheme"},{"name":"Research Grants Council of the Hong Kong Special Administrative Region, China and National Natural Science Foundation of China","award":["N_HKUST656\/22"],"award-info":[{"award-number":["N_HKUST656\/22"]}]},{"name":"NSFC\/RGC Collaborative Research Scheme","award":["CRS_HKUST603\/22"],"award-info":[{"award-number":["CRS_HKUST603\/22"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/jstsp.2025.3581478","type":"journal-article","created":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T13:38:59Z","timestamp":1750340339000},"page":"1301-1317","source":"Crossref","is-referenced-by-count":6,"title":["Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7876-5764","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology (HKUST), Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4659-6941","authenticated-orcid":false,"given":"Hengtao","family":"He","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6316-8415","authenticated-orcid":false,"given":"Shenghui","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology (HKUST), Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5222-1898","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology (HKUST), Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2519-6401","authenticated-orcid":false,"given":"Khaled B.","family":"Letaief","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology (HKUST), Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11161391"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-023-02294-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02482"},{"key":"ref7","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300364"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2024.10582827"},{"key":"ref10","article-title":"WirelessAgent: Large language model agents for intelligent wireless networks","author":"Tong","year":"2024"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref12","article-title":"Fast distributed inference serving for large language models","author":"Wu","year":"2023"},{"key":"ref13","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","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3732941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126076"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3454086"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref20","article-title":"Adaptive layer splitting for wireless LLM inference in edge computing: A model-based reinforcement learning approach","author":"Chen","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436784"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3559116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3294703"},{"key":"ref25","article-title":"Model parallelism on distributed infrastructure: A literature review from theory to LLM case-studies","author":"Brakel","year":"2024"},{"key":"ref26","article-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"2019"},{"key":"ref27","article-title":"Towards low-bit communication for tensor parallel LLM inference","author":"Dong","year":"2024"},{"key":"ref28","article-title":"Communication compression for tensor parallel LLM inference","volume-title":"Proc. Workshop Mach. Learn. Compress.","author":"Hansen-Palmus","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2007.904785"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416116"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3165658"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3106115"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3012287"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2961673"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3352280"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090323"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3343086"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2025.3593802"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3310895"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3130111"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3501297"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3497998"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3306465"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3485678"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2272921"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2914046"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/0613006"},{"key":"ref49","article-title":"CVX: Matlab software for disciplined convex programming, version 2.2","author":"Grant","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.936019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2925601"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/978-3-642-11339-0","article-title":"Interior point methods for nonlinear optimization","volume-title":"Nonlinear Optimization","author":"Bomze","year":"2010"},{"key":"ref53","article-title":"Successive convex approximation: Analysis and applications","author":"Razaviyayn","year":"2014"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3322791"},{"key":"ref55","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref56","article-title":"Regularizing and optimizing lstm language models","author":"Merity","year":"2017"},{"key":"ref57","article-title":"Distributed llama","author":"Tadych","year":"2024"},{"key":"ref58","article-title":"Detecting language model attacks with perplexity","author":"Alon","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807213"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/BF01581643"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/11320985\/11045182.pdf?arnumber=11045182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T20:59:46Z","timestamp":1770929986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11045182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":61,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2025.3581478","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}