{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T22:17:09Z","timestamp":1779920229159,"version":"3.53.1"},"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":5,"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Deng","sequence":"additional","affiliation":[{"name":"Tianjin University,School of Future Technology,Tianjin,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro","family":"Reviriego","sequence":"additional","affiliation":[{"name":"Universidad Politécnica de Madrid,Departamento de Ingeniería de Sistemas Telemáticos,Madrid"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Information and Communication Engineering,Chengdu,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrizio","family":"Lombardi","sequence":"additional","affiliation":[{"name":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"OpenAI, Introducing ChatGPT","year":"2022"},{"key":"ref2","article-title":"EdgeMoE: Fast On-Device Inference of MoE-based Large Language Models","author":"Yi","year":"2023"},{"key":"ref3","article-title":"Pushing Large Language Models to the 6G Edge: Vision, Challenges, and Opportunities","author":"Lin","year":"2023"},{"key":"ref4","article-title":"A Survey on Model Compression for Large Language Models","author":"Zhu","year":"2023"},{"key":"ref5","article-title":"LLM-Pruner: On the Structural Pruning of Large Language Models","author":"Ma","year":"2023","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018"},{"key":"ref7","article-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","article-title":"GPT-4 Technical Report","year":"2023"},{"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"},{"key":"ref16","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"NAACL 2019","author":"Devlin"},{"key":"ref17","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"Lan","year":"2019"},{"key":"ref18","article-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Well-read Students Learn Better: On the importance of Pre-trained Compact Models","author":"Turc","year":"2019"},{"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)","location":"Singapore, Singapore","start":{"date-parts":[[2024,5,19]]},"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]]}}}