{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:56:28Z","timestamp":1781675788909,"version":"3.54.5"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"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":[[2026,4,13]]},"DOI":"10.1109\/wcnc65185.2026.11555375","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:41:29Z","timestamp":1781638889000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive LLM Inference in 6G Vehicular Networks via Layer Pruning and Offloading"],"prefix":"10.1109","author":[{"given":"Yan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics,Nanjing,China,211106"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiru","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics,Nanjing,China,211106"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhua","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University,Shenyang,China,110819"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewen","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University,Shenyang,China,110819"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics,Nanjing,China,211106"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhu","family":"Han","sequence":"additional","affiliation":[{"name":"University of Houston,Houston,TX,USA,77004"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476209","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":"Narayanan"},{"key":"ref2","article-title":"Sheared llama: Accelerating language model pre-training via structured pruning","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Xia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1299"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2024-Spring62846.2024.10683673"},{"key":"ref5","article-title":"Streamlining redundant layers to compress large language models","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.262"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0950"},{"key":"ref8","article-title":"Slicegpt: Compress large language models by deleting rows and columns","volume-title":"The Twelfth International Conference on Learning Representations (ICLR)","author":"Ashkboos"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/a16090398"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref11","article-title":"Reducing transformer depth on demand with structured dropout","volume-title":"8th International Conference on Learning Representations (ICLR)","author":"Fan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096914"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3527155"},{"key":"ref14","article-title":"The unreasonable ineffectiveness of the deeper layers","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Gromov"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2400468"}],"event":{"name":"2026 IEEE Wireless Communications and Networking Conference (WCNC)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2026,4,13]]},"end":{"date-parts":[[2026,4,16]]}},"container-title":["2026 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11555037\/11555040\/11555375.pdf?arnumber=11555375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:30:08Z","timestamp":1781674208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11555375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/wcnc65185.2026.11555375","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]}}}