{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:10:51Z","timestamp":1759335051598,"version":"build-2065373602"},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"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":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1109\/icc52391.2025.11161094","type":"proceedings-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:34:55Z","timestamp":1758908095000},"page":"6285-6290","source":"Crossref","is-referenced-by-count":0,"title":["Joint Caching and Inference for Large Language Models in Wireless Networks"],"prefix":"10.1109","author":[{"given":"Bingjie","family":"Zhu","sequence":"first","affiliation":[{"name":"Xidian University,The State Key Laboratory of Integrated Services Networks,Xi'an,China,710071"}]},{"given":"Zhixiong","family":"Chen","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,U.K."}]},{"given":"Liqiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xidian University,The State Key Laboratory of Integrated Services Networks,Xi'an,China,710071"}]},{"given":"Hyundong","family":"Shin","sequence":"additional","affiliation":[{"name":"Kyung Hee University, Yongin-si,Gyeonggido,Republic of Korea,17104"}]},{"given":"Arumugam","family":"Nallanathan","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,London,U.K."}]}],"member":"263","reference":[{"key":"ref1","article-title":"Taming throughput-latency tradeoff in llm inference with sarathi-serve","author":"Agrawal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Trimcaching: Parameter-sharing edge caching for ai model downloading","author":"Qu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Perllm: Personalized inference scheduling with edge-cloud collaboration for diverse 1 lm services","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3527641"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3338153"},{"key":"ref7","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3359009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013927"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3200109"}],"event":{"name":"ICC 2025 - IEEE International Conference on Communications","start":{"date-parts":[[2025,6,8]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2025,6,12]]}},"container-title":["ICC 2025 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11160703\/11160705\/11161094.pdf?arnumber=11161094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T05:25:16Z","timestamp":1759296316000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11161094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/icc52391.2025.11161094","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]}}}