{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:36:39Z","timestamp":1773246999291,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["92464302"],"award-info":[{"award-number":["92464302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcsi.2025.3547732","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T13:49:25Z","timestamp":1741873765000},"page":"4077-4090","source":"Crossref","is-referenced-by-count":1,"title":["OFQ-LLM: Outlier-Flexing Quantization for Efficient Low-Bit Large Language Model Acceleration"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6944-2958","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of MicroNano Engineering Science, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1478-2202","authenticated-orcid":false,"given":"Siqi","family":"Cai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of MicroNano Engineering Science, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1244-7657","authenticated-orcid":false,"given":"Wenjie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6826-2670","authenticated-orcid":false,"given":"Dongxu","family":"Lyu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of MicroNano Engineering Science, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0486-6421","authenticated-orcid":false,"given":"Guanghui","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of MicroNano Engineering Science, School of Integrated Circuits, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv:2009.03300"},{"key":"ref2","article-title":"Evaluating quantized large language models","author":"Li","year":"2024","journal-title":"arXiv:2402.18158"},{"key":"ref3","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv:2001.08361"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref5","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref6","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref7","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref8","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref9","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref10","first-page":"30318","article-title":"GPT3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dettmers"},{"key":"ref11","article-title":"SqueezeLLM: Dense-and-Sparse quantization","author":"Kim","year":"2023","journal-title":"arXiv:2306.07629"},{"key":"ref12","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Lin"},{"key":"ref13","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Xiao"},{"key":"ref14","article-title":"RPTQ: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023","journal-title":"arXiv:2304.01089"},{"key":"ref15","first-page":"17402","article-title":"Outlier suppression: Pushing the limit of low-bit transformer language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Wei"},{"key":"ref16","article-title":"QLLM: Accurate and efficient low-bitwidth quantization for large language models","author":"Liu","year":"2023","journal-title":"arXiv:2310.08041"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.300"},{"key":"ref18","first-page":"196","article-title":"Atom: Low-bit quantization for efficient and accurate LLM serving","volume-title":"Proc. Mach. Learn. Syst.","volume":"6","author":"Zhao"},{"key":"ref19","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3350661"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref26","article-title":"UEyes: An eye-tracking dataset across user interface types","author":"Jiang","year":"2024","journal-title":"arXiv:2402.05202"},{"key":"ref27","article-title":"RepQuant: Towards accurate post-training quantization of large transformer models via scale reparameterization","author":"Li","year":"2024","journal-title":"arXiv:2402.05628"},{"key":"ref28","article-title":"OmniQuant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023","journal-title":"arXiv:2308.13137"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00082"},{"key":"ref30","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref31","article-title":"The RefinedWeb dataset for falcon LLM: Outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023","journal-title":"arXiv:2306.01116"},{"key":"ref32","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref33","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8919\/11099062\/10924797.pdf?arnumber=10924797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T05:08:01Z","timestamp":1753852081000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":35,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2025.3547732","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"value":"1549-8328","type":"print"},{"value":"1558-0806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}