{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:15:31Z","timestamp":1766060131640,"version":"3.48.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,1]]},"DOI":"10.1109\/pimrc62392.2025.11275395","type":"proceedings-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T18:33:25Z","timestamp":1765564405000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Collaborative Multi-Device Edge Inference for Vision-Language Models with Speculative Decoding"],"prefix":"10.1109","author":[{"given":"Luteng","family":"Qiao","sequence":"first","affiliation":[{"name":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China,201210"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Shao","sequence":"additional","affiliation":[{"name":"China Telecom,Institute of Artificial Intelligence (TeleAI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China,201210"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanming","family":"Shi","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,School of Information Science and Technology,Shanghai,China,201210"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"China Telecom,Institute of Artificial Intelligence (TeleAI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaled B.","family":"Letaief","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of ECE,Hong Kong,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3509739"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2024.10582827"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126076"},{"key":"ref4","first-page":"21702","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Ma"},{"key":"ref5","first-page":"88981","article-title":"Compressing large language models using low rank and low precision decomposition","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Saha"},{"key":"ref6","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst","author":"Lin"},{"key":"ref7","first-page":"98297","article-title":"DDK: Distilling domain knowledge for efficient large language models","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Liu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11161391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3531128"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.002.2200468"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400761"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3541208"},{"key":"ref14","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Leviathan"},{"article-title":"Specdec++: Boosting speculative decoding via adaptive candidate lengths","year":"2024","author":"Huang","key":"ref15"},{"article-title":"Dynamic speculation lookahead accelerates speculative decoding of large language models","year":"2024","author":"Mamou","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3294494"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560538"},{"key":"ref19","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inform. Process. Syst. (NeurIPS)","author":"Liu"},{"article-title":"Aladdin: Joint placement and scaling for SLO-aware LLM serving","year":"2024","author":"Nie","key":"ref20"}],"event":{"name":"2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","start":{"date-parts":[[2025,9,1]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,4]]}},"container-title":["2025 IEEE 36th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11274530\/11274549\/11275395.pdf?arnumber=11275395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:11:34Z","timestamp":1766059894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11275395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/pimrc62392.2025.11275395","relation":{},"subject":[],"published":{"date-parts":[[2025,9,1]]}}}