{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:00:50Z","timestamp":1781157650454,"version":"3.54.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Yangtze River Delta Science and Technology Innovation Community Joint Fundamental Research Project","award":["2024CSJZN0504"],"award-info":[{"award-number":["2024CSJZN0504"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tc.2026.3689022","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:47:08Z","timestamp":1777578428000},"page":"2604-2617","source":"Crossref","is-referenced-by-count":0,"title":["Low Bit-Width LLM Acceleration via Symmetric Lookup Format and Compute-in-Decoding Paradigm"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1510-1341","authenticated-orcid":false,"given":"Zihan","family":"Zou","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9253-5736","authenticated-orcid":false,"given":"Xinyang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1261-8543","authenticated-orcid":false,"given":"Jiaming","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2239-7350","authenticated-orcid":false,"given":"Bo","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7661-6165","authenticated-orcid":false,"given":"Xinming","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3331-1562","authenticated-orcid":false,"given":"Shikuang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1312-422X","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3853-2398","authenticated-orcid":false,"given":"Xilong","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9794-8049","authenticated-orcid":false,"given":"Hao","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0894-1054","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0196"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.498"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00047"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001177"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2025.3628193"},{"key":"ref8","first-page":"2924","article-title":"BooLQ: Exploring the surprising difficulty of natural yes\/no questions","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Clark","year":"2019"},{"key":"ref9","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref10","first-page":"873","article-title":"VS-Quant: Per-vector scaled quantization for accurate low-precision neural network inference","volume-title":"Proc. Mach. Learn. Syst.","volume":"3","author":"Dai","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref12","article-title":"Learning from students: Applying t-distributions to explore accurate and efficient formats for LLMs","author":"Dotzel","year":"2024"},{"key":"ref13","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/isscc49657.2024.10454308"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00064"},{"key":"ref18","article-title":"An investigation of FP8 across accelerators for LLM inference","author":"Kim","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2025.3558300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2973991"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2786"},{"key":"ref24","article-title":"SpinQuant: LLM quantization with learned rotations","author":"Liu","year":"2024"},{"key":"ref25","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref26","article-title":"Lut tensor core: Lookup table enables efficient low-bit LLM inference acceleration","author":"Mo","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1144"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00085"},{"key":"ref29","article-title":"LUT-GEMM: Quantized matrix multiplication based on LUTs for efficient inference in large-scale generative language models","author":"Park","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00079"},{"issue":"140","key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00127"},{"key":"ref34","article-title":"OmniQuant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00062"},{"key":"ref36","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/9355053924"},{"key":"ref38","article-title":"T-MAC: CPU renaissance via table lookup for low-bit LLM deployment on edge","author":"Wei","year":"2024"},{"key":"ref39","article-title":"COAT: Compressing optimizer states and activation for memory-efficient FP8 training","author":"Xi","year":"2024"},{"key":"ref40","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656221"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0782"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11557416\/11501947.pdf?arnumber=11501947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T05:35:23Z","timestamp":1781156123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11501947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":43,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tc.2026.3689022","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}