{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:10:33Z","timestamp":1755925833989,"version":"3.44.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"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":[[2025,8,4]]},"DOI":"10.1109\/coins65080.2025.11125766","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:57:49Z","timestamp":1755907069000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Acceleration of Large Language Models with Emerging Compute and Communication Technology"],"prefix":"10.1109","author":[{"given":"Sharin Shahana K","family":"C","sequence":"first","affiliation":[{"name":"Indian Institute of Science,Dept. of CSA,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sumit K.","family":"Mandal","sequence":"additional","affiliation":[{"name":"Indian Institute of Science,Dept. of CSA,Bangalore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biresh Kumar","family":"Joardar","sequence":"additional","affiliation":[{"name":"University of Houston,Dept. of ECE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3199648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103722"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12118"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11030418"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191462"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02056-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43901-8_66"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3476999"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197500"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2889053"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3083684"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2022.3223630"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref15","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref16","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","article-title":"Linformer: Self-attention with Linear Complexity","author":"Wang","year":"2020","journal-title":"arXiv preprint arXiv:2006.04768"},{"key":"ref18","first-page":"16 344","article-title":"Flashattention: Fast and Memory-efficient Exact Attention with IO-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Generating Long Sequences with Sparse Transformers","author":"Child","year":"2019","journal-title":"arXiv preprint arXiv:1904.10509"},{"key":"ref20","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"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/felec.2022.847069"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3427421"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2016.2612647"},{"key":"ref25","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"Proceedings of NAACL-HLT","author":"Kenton"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"}],"event":{"name":"2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","location":"Madison, WI, USA","start":{"date-parts":[[2025,8,4]]},"end":{"date-parts":[[2025,8,6]]}},"container-title":["2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11125678\/11125719\/11125766.pdf?arnumber=11125766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T04:46:26Z","timestamp":1755924386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11125766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/coins65080.2025.11125766","relation":{},"subject":[],"published":{"date-parts":[[2025,8,4]]}}}