{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:49:43Z","timestamp":1783183783725,"version":"3.54.6"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U21B2030"],"award-info":[{"award-number":["U21B2030"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U24B6015"],"award-info":[{"award-number":["U24B6015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["92264204"],"award-info":[{"award-number":["92264204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Solid-State Circuits"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/jssc.2025.3556008","type":"journal-article","created":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T13:37:18Z","timestamp":1744724238000},"page":"4140-4153","source":"Crossref","is-referenced-by-count":10,"title":["Hybrid SRAM\/ROM Compute-in-Memory Architecture for High Task-Level Energy Efficiency in Transformer Models With 8928-kb\/mm\u00b2 Density in 28nm CMOS"],"prefix":"10.1109","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1315-9806","authenticated-orcid":false,"given":"Guodong","family":"Yin","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1408-5194","authenticated-orcid":false,"given":"Yiming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5076-4645","authenticated-orcid":false,"given":"Mingyen","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2939-9564","authenticated-orcid":false,"given":"Xirui","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Ke","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9994-8736","authenticated-orcid":false,"given":"Wenjun","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhonghao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6021-3265","authenticated-orcid":false,"given":"Mufeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-7400","authenticated-orcid":false,"given":"Jinshan","family":"Yue","sequence":"additional","affiliation":[{"name":"Laboratory of Microelectronics Device and Integrated Technology, Institute of Microelectronics, Chinese Academy of Sciences (CAS), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-353X","authenticated-orcid":false,"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8692-1860","authenticated-orcid":false,"given":"Hongyang","family":"Jia","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-2309","authenticated-orcid":false,"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8051-3345","authenticated-orcid":false,"given":"Xueqing","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, LFET\/BNRist\/SKLSNC, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731681"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067289"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365932"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3387995"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3326955"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ESSCIRC59616.2023.10268726"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067305"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731545"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3324954"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.2987714"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref12","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref13","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref15","article-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","author":"Aghajanyan","year":"2020","journal-title":"arXiv:2012.13255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3064189"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662419"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2776302"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662392"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3211290"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CICC53496.2022.9772821"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3232601"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/4.50301"},{"key":"ref24","first-page":"9895","article-title":"Sparse is enough in scaling transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaszczur"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365788"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.2992886"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731754"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454556"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067352"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062985"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185253"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067555"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2899730"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3339887"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.23919\/VLSITechnologyandCir57934.2023.10185439"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref38","article-title":"GPT understands, too","author":"Liu","year":"2021","journal-title":"arXiv:2103.10385"},{"key":"ref39","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref40","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"36","author":"Dettmers"},{"key":"ref41","article-title":"QuickLLaMA: Query-aware inference acceleration for large language models","author":"Li","year":"2024","journal-title":"arXiv:2406.07528"},{"key":"ref42","article-title":"ThinK: Thinner key cache by query-driven pruning","author":"Xu","year":"2024","journal-title":"arXiv:2407.21018"},{"key":"ref43","first-page":"34661","article-title":"H2O: Heavy-hitter Oracle for efficient generative inference of large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref44","article-title":"SnapKV: LLM knows what you are looking for before generation","author":"Li","year":"2024","journal-title":"arXiv:2404.14469"}],"container-title":["IEEE Journal of Solid-State Circuits"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4\/11230034\/10965590.pdf?arnumber=10965590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T05:46:10Z","timestamp":1762407970000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10965590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":44,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/jssc.2025.3556008","relation":{},"ISSN":["0018-9200","1558-173X"],"issn-type":[{"value":"0018-9200","type":"print"},{"value":"1558-173X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}