{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:51:38Z","timestamp":1774558298628,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B250205031"],"award-info":[{"award-number":["B250205031"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of China","award":["2022YFC3005401"],"award-info":[{"award-number":["2022YFC3005401"]}]},{"name":"Technology Talent and Platform Program of Yunnan Province","award":["202405AK340002"],"award-info":[{"award-number":["202405AK340002"]}]},{"name":"Technology Project of Huaneng Group","award":["HNKJ24-H167"],"award-info":[{"award-number":["HNKJ24-H167"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572171"],"award-info":[{"award-number":["62572171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High Performance Computing Platform, Hohai University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tce.2025.3642866","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:45:23Z","timestamp":1765478723000},"page":"2122-2134","source":"Crossref","is-referenced-by-count":0,"title":["Efficient LLM Deployment in Consumer Electronics Applications via Resource-Aware and Salience-Guided Quantization"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8291-4437","authenticated-orcid":false,"given":"Tianfu","family":"Pang","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9884-8100","authenticated-orcid":false,"given":"Yingchi","family":"Mao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5477-0244","authenticated-orcid":false,"given":"Zhenxiang","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1181-0339","authenticated-orcid":false,"given":"Rongzhi","family":"Qi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6946-5254","authenticated-orcid":false,"given":"Benteng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4196-3041","authenticated-orcid":false,"given":"Xiaoming","family":"He","sequence":"additional","affiliation":[{"name":"College of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3472-1717","authenticated-orcid":false,"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"Center for Networked Computing, Temple University, Philadelphia, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","author":"Le Scao","year":"2022","journal-title":"arXiv:2211.05100"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2025.3544675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400703"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.fa.2024-0024.202407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-020-00956-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2018.01.007"},{"key":"ref7","first-page":"371","article-title":"Understanding large-language model (LLM)-powered human\u2013robot interaction","volume-title":"Proc. ACM\/IEEE Int. Conf. Human\u2013Robot Interact.","author":"Kim"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LLM4Code66737.2025.00028"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ECAI65401.2025.11095547"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref12","article-title":"OPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Frantar"},{"key":"ref13","first-page":"4396","article-title":"QuIP: 2-bit quantization of large language models with guarantees","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"36","author":"Chee"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26084"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.3009475"},{"key":"ref19","first-page":"1","article-title":"LLM-MQ: Mixed-precision quantization for efficient llm deployment","volume-title":"Proc. The Efficient Natural Lang. Speech Process. Workshop NeurIPS","volume":"9","author":"Li"},{"key":"ref20","first-page":"5733","article-title":"SpQR: A sparse-quantized representation for near-lossless LLM weight compression","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Dettmers"},{"key":"ref21","article-title":"PB-LLM: Partially binarized large language models","author":"Shang","year":"2023","journal-title":"arXiv:2310.00034"},{"key":"ref22","first-page":"48630","article-title":"QuIP#: Even better LLM quantization with Hadamard incoherence and lattice codebooks","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Tseng"},{"key":"ref23","first-page":"12284","article-title":"Extreme compression of large language models via additive quantization","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Egiazarian"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.133"},{"key":"ref25","article-title":"QuantMoE-bench: Examining post-training quantization for mixture-of-experts","author":"Li","year":"2024","journal-title":"arXiv:2406.08155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref28","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proc. Mach. Learn. Syst.","author":"Zhao"},{"key":"ref29","first-page":"23901","article-title":"SqueezeLLM: Dense-and-sparse quantization","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/DATE64628.2025.10993129"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0323"},{"key":"ref32","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Frantar"},{"key":"ref33","first-page":"70","article-title":"Matrix inversion using Cholesky decomposition","volume-title":"Proc. Signal Processing, Algorithms, Archit., Arrangements, Appl. (SPA)","author":"Krishnamoorthy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12000"},{"key":"ref35","first-page":"12360","article-title":"Root mean square layer normalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-1534-8_6"},{"key":"ref37","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref38","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref39","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv:1803.05457"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6399"},{"key":"ref43","article-title":"NVIDIA Jetson AGX orin series","author":"Karumbunathan","year":"2022"},{"key":"ref44","article-title":"Embedded ai performances of Nvidia\u2019s Jetson orin SoC series","volume-title":"Proc. 17th Colloque Nat. Du GDR SOC2","author":"Archet"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11456295\/11298178.pdf?arnumber=11298178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:50:05Z","timestamp":1774554605000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3642866","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}