{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:44:31Z","timestamp":1773377071792,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003977","name":"ISRAEL SCIENCE FOUNDATION (ISF)","doi-asserted-by":"publisher","award":["1641\/21"],"award-info":[{"award-number":["1641\/21"]}],"id":[{"id":"10.13039\/501100003977","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/isit63088.2025.11195282","type":"proceedings-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:48:08Z","timestamp":1760982488000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["High-Rate Nested-Lattice Quantized Matrix Multiplication with Small Lookup Tables"],"prefix":"10.1109","author":[{"given":"Iris","family":"Kaplan","sequence":"first","affiliation":[{"name":"Hebrew University of Jerusalem,Computer Science and Engineering,Jerusalem,Israel"}]},{"given":"Or","family":"Ordentlich","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem,Computer Science and Engineering,Jerusalem,Israel"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Compressing deep convolutional networks using vector quantization","author":"Gong","year":"2014","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref3","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","first-page":"27 168","article-title":"Zeroquant: Efficient and affordable post-training quantization for largescale transformers","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","first-page":"38 087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning. PMLR","author":"Xiao","year":"2023"},{"key":"ref6","article-title":"The era of 1-bit llms: All large language models are in 1.58 bits","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Quip#: Even better 1 lm quantization with hadamard incoherence and lattice codebooks","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Qtip: Quantization with trellises and incoherence processing","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Quarot: Outlier-free 4-bit inference in rotated llms","author":"Ashkboos","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Dynamic network surgery for efficient dnns","volume":"29","author":"Guo","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Frantar","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/isit63088.2025.11195544"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1983.1056761"},{"key":"ref14","article-title":"NestQuant: Nested lattice quantization for matrix products and LLMs","author":"Savkin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/18.75242"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/78.258085"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/76.499834"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2002.806235"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638777"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3626-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.124"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098195"},{"key":"ref25","first-page":"992","article-title":"Multiplying matrices without multiplying","volume-title":"International Conference on Machine Learning. PMLR","author":"Blalock","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139045520"}],"event":{"name":"2025 IEEE International Symposium on Information Theory (ISIT)","location":"Ann Arbor, MI, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,27]]}},"container-title":["2025 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11195206\/11195207\/11195282.pdf?arnumber=11195282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:30:29Z","timestamp":1773347429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/isit63088.2025.11195282","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}