{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:25:55Z","timestamp":1770845155392,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11343559","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"2685-2690","source":"Crossref","is-referenced-by-count":0,"title":["Dynamically Reconfigurable NPU Acceleration for Knowledge Loading in LLM Retrieval-Augmented Generation"],"prefix":"10.1109","author":[{"given":"Peidong","family":"Lin","sequence":"first","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China,Shenzhen,China,518110"}]},{"given":"Jintao","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China,Shenzhen,China,518110"}]},{"given":"Hui","family":"Deng","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China,Shenzhen,China,518110"}]},{"given":"Shihong","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China,Shenzhen,China,518110"}]},{"given":"Shui","family":"Yu","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China,Shenzhen,China,518110"}]},{"given":"Yun","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China,Shenzhen,China,518110"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00530"},{"key":"ref4","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Borgeaud"},{"key":"ref5","article-title":"Piperag: Fast retrieval-augmented generation via algorithm-system co-design","author":"Jiang","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123301"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref8","article-title":"Efficiently programming large language models using sglang","author":"Zheng","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473859"},{"key":"ref10","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Yao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126966"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3697117"},{"key":"ref13","article-title":"Accelerating retrieval-augmented generation","volume-title":"J","author":"D"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASICON47005.2019.8983642"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3697701"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICTA60488.2023.10364281"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.389"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2018.8297291"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1145\/3669940.3707264","article-title":"Accelerating Retrieval-Augmented Generation","author":"Quinn","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181869"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2008.918214"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2951569"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PAAP54281.2021.9720451"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3466301"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/GEMIC.2019.8698143"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1086\/313274"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323899"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3340683"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2007.11"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref33","article-title":"A survey on large language models: Applications, challenges, limitations, and practical usage","author":"Hadi","year":"2023","journal-title":"Authorea Preprints"},{"key":"ref34","article-title":"Self-rag: Learning to retrieve, generate, and critique through self-reflection","author":"Asai","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICoDT255437.2022.9787395"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICNLP58431.2023.00062"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref38","article-title":"Efficient representation of local geometry for large scale object retrieval","volume-title":"IEEE Conference on Computer Vision & Pattern Recognition","author":"M"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-010-0303-2"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11343559.pdf?arnumber=11343559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:04Z","timestamp":1770843004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11343559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11343559","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}