{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:50:23Z","timestamp":1785603023208,"version":"3.56.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"crossref","award":["BK20243051"],"award-info":[{"award-number":["BK20243051"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["4254088"],"award-info":[{"award-number":["4254088"]}]},{"name":"Science and Technology Major Special Program of Jiangsu","award":["BG2024028"],"award-info":[{"award-number":["BG2024028"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tc.2025.3626150","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T17:57:14Z","timestamp":1761587834000},"page":"2660-2672","source":"Crossref","is-referenced-by-count":2,"title":["MATA: A Memory-Efficient Attention Accelerator for LLMs Exploiting Look-Back KV Cache Pruning"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0709-2438","authenticated-orcid":false,"given":"Zeyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences, C<sup>2<\/sup>DL, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7835-4739","authenticated-orcid":false,"given":"Gang","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, C<sup>2<\/sup>DL, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9675-4465","authenticated-orcid":false,"given":"Tielong","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, C<sup>2<\/sup>DL, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8623-5465","authenticated-orcid":false,"given":"Zitao","family":"Mo","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, C<sup>2<\/sup>DL, Institute of Automation, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2790-5884","authenticated-orcid":false,"given":"Xiaoyao","family":"Liang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1289-2758","authenticated-orcid":false,"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, C<sup>2<\/sup>DL, Institute of Automation, Beijing, 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":"10.18653\/v1\/P19-1285"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/567"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref12","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref13","article-title":"Full stack optimization of transformer inference","volume-title":"Proc. Archit. Syst. Support Transformer Models (ASSYST@ ISCA)","author":"Kim","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref15","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2279"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3531437.3539717"},{"key":"ref19","article-title":"Highlights of the high-bandwidth memory (HBM) standard","volume-title":"Proc. Memory Forum Workshop","volume":"3","author":"O\u2019Connor","year":"2014"},{"key":"ref20","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref24","article-title":"Compressive transformers for long-range sequence modelling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rae","year":"2019"},{"issue":"140","key":"ref25","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref27","article-title":"Stanford Alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref29","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref30","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616280"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref33","article-title":"Efficient streaming language models with attention sinks","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xiao","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17674"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527438"},{"key":"ref37","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00632"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1506"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11603879\/11218945.pdf?arnumber=11218945","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:03:49Z","timestamp":1783973029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11218945\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":39,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3626150","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":[[2026,8]]}}}