{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:43:41Z","timestamp":1777322621521,"version":"3.51.4"},"reference-count":18,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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 Internet Things J."],"published-print":{"date-parts":[[2026,5,1]]},"DOI":"10.1109\/jiot.2026.3659676","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:04:37Z","timestamp":1769807077000},"page":"19751-19754","source":"Crossref","is-referenced-by-count":0,"title":["Reliable and Efficient LLM Inference on Resource-Constrained Mobile Devices via Dynamic Scheduling"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0932-9553","authenticated-orcid":false,"given":"Aoxing","family":"Liang","sequence":"first","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengfan","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5073-5561","authenticated-orcid":false,"given":"Yunzhe","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8657-5064","authenticated-orcid":false,"given":"Hongzi","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref3","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3458185"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3614064"},{"key":"ref6","first-page":"703","article-title":"Shockwave: Fair and efficient cluster scheduling for dynamic adaptation in machine learning","volume-title":"Proc. 20th USENIX Symp. Networked Syst. Design Implement. (NSDI)","author":"Zheng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3449039"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-8"},{"key":"ref9","first-page":"27168","article-title":"ZeroQuant: Efficient and affordable post-training quantization for large-scale transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1569"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"ref12","article-title":"QA-LoRA: Quantization-aware low-rank adaptation of large language models","author":"Xu","year":"2023","journal-title":"arXiv:2309.14717"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3615732"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649391"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3442430"},{"key":"ref17","volume-title":"EXO: Run Your Own AI Cluster At Home With Everyday Devices","author":"Cheema","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11494393\/11368869.pdf?arnumber=11368869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:51:29Z","timestamp":1777319489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11368869\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,1]]},"references-count":18,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3659676","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,1]]}}}