{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T04:05:01Z","timestamp":1747973101546,"version":"3.41.0"},"reference-count":33,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10993271","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":0,"title":["MCTA: A Multi-Stage Co-Optimized Transformer Accelerator with Energy-Efficient Dynamic Sparse Optimization"],"prefix":"10.23919","author":[{"given":"Heng","family":"Liu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Ming","family":"Han","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Jin","family":"Wu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Jian","family":"Dong","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.19"},{"key":"ref2","article-title":"Rethinking attention with performers","volume-title":"International Conference on Learning Representations","author":"Choromanski","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071081"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.292"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"ref11","first-page":"2","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Devlin","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3208206"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"ref16","article-title":"Cacti 6.0: A tool to model large caches","author":"Muralimanohar","year":"2009","journal-title":"HP laboratories"},{"key":"ref17","article-title":"Random feature attention","volume-title":"International Conference on Learning Representations","author":"Peng","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3397189"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref21","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"issue":"8","key":"ref22","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558119"},{"key":"ref25","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref26","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref29","article-title":"Vision transformer with attention map hallucination and ffn compaction","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acldemos.30"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","start":{"date-parts":[[2025,3,31]]},"location":"Lyon, France","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\/10993271.pdf?arnumber=10993271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:34:45Z","timestamp":1747892085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10993271","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}