{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:20:08Z","timestamp":1782969608347,"version":"3.54.5"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2442271"],"award-info":[{"award-number":["2442271"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10993217","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["NORA: Noise-Optimized Rescaling of LLMs on Analog Compute-in-Memory Accelerators"],"prefix":"10.23919","author":[{"given":"Yayue","family":"Hou","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute,Troy,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsinyu","family":"Tsai","sequence":"additional","affiliation":[{"name":"IBM Research,San Jose,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaoutar","family":"El Maghraoui","sequence":"additional","affiliation":[{"name":"IBM Research,Yorktown Heights,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tayfun","family":"Gokmen","sequence":"additional","affiliation":[{"name":"IBM Research,Yorktown Heights,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey W.","family":"Burr","sequence":"additional","affiliation":[{"name":"IBM Research,San Jose,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute,Troy,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 3 model card","volume-title":"AI@Meta","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589062"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2023.3329449"},{"key":"ref4","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":"ref5","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"The Pile: An 800gb dataset of diverse text for language modeling","author":"Gao","year":"2020","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00538"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1145\/3307650.3322237","article-title":"Floatpim: In-memory acceleration of deep neural network training with high precision","volume-title":"Proceedings of the 46th International Symposium on Computer Architecture","author":"Imani","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2022.3221390"},{"key":"ref10","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-16108-9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3140414"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-023-01010-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1063\/5.0168089"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6463\/ab7794"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"175","DOI":"10.18653\/v1\/2021.emnlp-demo.21","article-title":"Datasets: A community library for natural language processing","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Lhoest","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3344524"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00065"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3337777"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31405-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401558"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9371990"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.18653\/v1\/P16-1144","article-title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Paperno","year":"2016"},{"key":"ref25","volume-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19573.2019.8993491"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458494"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40770-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref30","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"38","DOI":"10.18653\/v1\/2020.emnlp-demos.6","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf","year":"2020"},{"key":"ref32","article-title":"Memory is all you need: An overview of compute-in-memory architectures for acceler-ating large language model inference","author":"Wolters","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao","year":"2023"},{"key":"ref34","first-page":"1","article-title":"Retransformer: Reram-based processing-in-memory architecture for transformer acceleration","volume-title":"Proceedings of the 39th International Conference on Computer-Aided Design","author":"Yang","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00059"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00348"},{"key":"ref37","article-title":"Opt: Open pretrained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","location":"Lyon, France","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10993217.pdf?arnumber=10993217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:34:43Z","timestamp":1747892083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":37,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10993217","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}