{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T12:21:15Z","timestamp":1766578875465},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,19]],"date-time":"2024-05-19T00:00:00Z","timestamp":1716076800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,19]]},"DOI":"10.1109\/iscas58744.2024.10558275","type":"proceedings-article","created":{"date-parts":[[2024,7,2]],"date-time":"2024-07-02T17:22:52Z","timestamp":1719940972000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Reducing the Energy Dissipation of Large Language Models (LLMs) with Approximate Memories"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Gao","sequence":"first","affiliation":[{"name":"Tianjin University,School of Electrical and Information Engineering,Tianjin,China"}]},{"given":"Jie","family":"Deng","sequence":"additional","affiliation":[{"name":"Tianjin University,School of Future Technology,Tianjin,China"}]},{"given":"Pedro","family":"Reviriego","sequence":"additional","affiliation":[{"name":"Universidad Polit&#x00E9;cnica de Madrid,Departamento de Ingenier&#x00ED;a de Sistemas Telem&#x00E1;ticos,Madrid"}]},{"given":"Shanshan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}]},{"given":"Fabrizio","family":"Lombardi","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA"}]}],"member":"263","reference":[{"year":"2022","key":"ref1","article-title":"OpenAI, Introducing ChatGPT"},{"article-title":"EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models","year":"2023","author":"Yi","key":"ref2"},{"article-title":"Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities","year":"2023","author":"Lin","key":"ref3"},{"article-title":"A Survey on Model Compression for Large Language Models","year":"2023","author":"Zhu","key":"ref4"},{"key":"ref5","article-title":"LLM-Pruner: On the Structural Pruning of Large Language Models","author":"Ma","year":"2023","journal-title":"NeurIPS"},{"article-title":"Improving Language Understanding by Generative Pre-Training","year":"2018","author":"Radford","key":"ref6"},{"key":"ref7","article-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"year":"2023","key":"ref8","article-title":"GPT-4 Technical Report"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2975695"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MWSCAS.2007.4488788"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2015.2417540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.84"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2017.2750140"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3109559"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2962516"},{"article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"NAACL 2019","author":"Devlin","key":"ref16"},{"article-title":"Albert: A lite bert for self-supervised learning of language representations","year":"2019","author":"Lan","key":"ref17"},{"key":"ref18","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"NeurIPS"},{"article-title":"Well-read Students Learn Better: On the importance of Pre-trained Compact Models","year":"2019","author":"Turc","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7943-9_27"},{"key":"ref21","article-title":"Code for ALBERT"},{"key":"ref22","article-title":"Code for DistilBERT"},{"key":"ref23","article-title":"Code for Tiny BERT"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2015.2408332"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/2.917539"}],"event":{"name":"2024 IEEE International Symposium on Circuits and Systems (ISCAS)","start":{"date-parts":[[2024,5,19]]},"location":"Singapore, Singapore","end":{"date-parts":[[2024,5,22]]}},"container-title":["2024 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10557746\/10557828\/10558275.pdf?arnumber=10558275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T07:55:07Z","timestamp":1719993307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10558275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,19]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iscas58744.2024.10558275","relation":{},"subject":[],"published":{"date-parts":[[2024,5,19]]}}}