{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T06:51:01Z","timestamp":1781851861260,"version":"3.54.5"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,24]]},"DOI":"10.1109\/iscas66217.2026.11562390","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:06:41Z","timestamp":1781813201000},"page":"3236-3240","source":"Crossref","is-referenced-by-count":0,"title":["Efficient LLM Inference on ARM via Hardware-Aware Operator Co-design and Heuristic Mixed-Precision Search"],"prefix":"10.1109","author":[{"given":"Zhaode","family":"Wang","sequence":"first","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Yao","sequence":"additional","affiliation":[{"name":"Tsingmicro Intelligent Technology Co., Ltd,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shirui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Katholieke Universiteit (KU) Leuven,Department of Electrical Engineering,Leuven,Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxi","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiguang","family":"Wu","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Mao","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Genquan","family":"Han","sequence":"additional","affiliation":[{"name":"Xidian University,Hangzhou Institute of Technology,Hangzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref3","author":"Xu","year":"2024","journal-title":"On-device language models: A comprehensive review"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2025.3527641"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/ICS.2025.3571019"},{"issue":"120","key":"ref6","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0040"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/ICS.2025.3568404"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS64808.2025.11173152"},{"key":"ref11","article-title":"Lut-gemm: Quantized matrix multiplication based on luts for efficient inference in large-scale generative language models","volume-title":"International Conference on Learning Representations","author":"Park"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3486322"},{"key":"ref13","article-title":"AI at the Edge GigaOm Research Byte"},{"key":"ref14","first-page":"2158","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL)","author":"Zhiqing"},{"key":"ref15","first-page":"27 168","article-title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref16","article-title":"Arm A-profile A64 Instruction Set Architecture"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","author":"Yang","year":"2025","journal-title":"Qwen2.5 technical report"}],"event":{"name":"2026 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Shanghai, China","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11561899\/11561804\/11562390.pdf?arnumber=11562390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:54:57Z","timestamp":1781848497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11562390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/iscas66217.2026.11562390","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}