{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:38:07Z","timestamp":1781887087827,"version":"3.54.5"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BE2023019-1"],"award-info":[{"award-number":["BE2023019-1"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. I"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsi.2025.3610210","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T17:56:28Z","timestamp":1759168588000},"page":"1245-1258","source":"Crossref","is-referenced-by-count":1,"title":["TEA-SPS: A Tiny and Efficient Architecture for Softmax With Parallelism and Sparsity Adaptability"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4143-0575","authenticated-orcid":false,"given":"Zhanhao","family":"Cui","sequence":"first","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Ma","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0964-3507","authenticated-orcid":false,"given":"Zhengyu","family":"Mei","sequence":"additional","affiliation":[{"name":"Wireless Terminal Architecture and Design Department, HS, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7181-8278","authenticated-orcid":false,"given":"Hongbing","family":"Pan","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9981-0588","authenticated-orcid":false,"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref5","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref6","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"},{"key":"ref7","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref9","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv:2106.08295"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20870-7_7"},{"key":"ref11","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Martins"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1223"},{"key":"ref13","first-page":"75067","article-title":"Quantizable transformers: Removing outliers by helping attention heads do nothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bondarenko"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS.2018.8605654"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3175534"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC.2016.7905501"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-94691-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.3002564"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3299874.3317988"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3120495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3665314.3670816"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS56072.2025.11044130"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3329039"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213521"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3386779"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3265710"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830277"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3081572"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3004602"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3133931"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181655"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref35","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv:2004.09602"},{"key":"ref36","first-page":"5506","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref37","article-title":"AdaSplash: Adaptive sparse flash attention","author":"Gon\u00e7alves","year":"2025","journal-title":"arXiv:2502.12082"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14132718"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00093"}],"container-title":["IEEE Transactions on Circuits and Systems I: Regular Papers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8919\/11368669\/11184336.pdf?arnumber=11184336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T19:54:36Z","timestamp":1774641276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11184336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsi.2025.3610210","relation":{},"ISSN":["1549-8328","1558-0806"],"issn-type":[{"value":"1549-8328","type":"print"},{"value":"1558-0806","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}