{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T06:10:30Z","timestamp":1778220630444,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471121"],"award-info":[{"award-number":["62471121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenyang Science and Technology Plan Fund","award":["23-503-6-17"],"award-info":[{"award-number":["23-503-6-17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tmc.2026.3650838","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:57Z","timestamp":1767638517000},"page":"8747-8763","source":"Crossref","is-referenced-by-count":0,"title":["Joint Optimization of Dynamic Batching and Adaptive Partitioning for Distributed LLMs Inference in Mobile Edge Computing"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3247-0846","authenticated-orcid":false,"given":"Tong","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8424-8542","authenticated-orcid":false,"given":"Yuanguo","family":"Bi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6921-7369","authenticated-orcid":false,"given":"Guangjie","family":"Han","sequence":"additional","affiliation":[{"name":"Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University, Changzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4374-2314","authenticated-orcid":false,"given":"Tianao","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4338-7252","authenticated-orcid":false,"given":"Lexi","family":"Xu","sequence":"additional","affiliation":[{"name":"Research Institute, China United Network Communications Corporation, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1820-6141","authenticated-orcid":false,"given":"Qiang","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5829-6850","authenticated-orcid":false,"given":"Liang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shenyang Aerospace University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3456549"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3430063"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3527641"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044632"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707215"},{"key":"ref7","article-title":"Samsung bans ChatGPT, AI chatbots after data leak blunder","author":"Sea","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3125949"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3195664"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SWC62898.2024.00113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400764"},{"key":"ref12","article-title":"Efficient distributed LLM inference with dynamic partitioning","author":"Ong","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3183098"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3381952"},{"key":"ref15","first-page":"12312","article-title":"Distributed inference and fine-tuning of large language models over the Internet","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Borzunov","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3627535.3638480"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3546466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ton.2025.3649068"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3497923"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3420755"},{"key":"ref22","article-title":"PrivateLoRA for efficient privacy preserving LLM","author":"Wang","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3440581"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400468"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3438995"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref28","article-title":"$\\wedge$\u2227-Split: A privacy-preserving split computing framework for cloud-powered generative AI","author":"Ohta","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3610856"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2025.3645168"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3430103"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3357874"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3466848"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3376550"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3192882"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3463429"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2013.418"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref41","first-page":"1","article-title":"High-Dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3082898"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3114193"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshp64532.2024.11100350"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11511860\/11328882.pdf?arnumber=11328882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:16:38Z","timestamp":1778217398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11328882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2026.3650838","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}