{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:24Z","timestamp":1780639224058,"version":"3.54.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"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":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539124","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["SATA: Sparsity-Aware Scheduling for Selective Token Attention"],"prefix":"10.23919","author":[{"given":"Zhenkun","family":"Fan","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology,Electrical and Computer Engineering Department,Atlanta,GA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zishen","family":"Wan","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Electrical and Computer Engineering Department,Atlanta,GA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Che-Kai","family":"Liu","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Electrical and Computer Engineering Department,Atlanta,GA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashwin Sanjay","family":"Lele","sequence":"additional","affiliation":[{"name":"TSMC Corporate Research,San Jose,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Win-San","family":"Khwa","sequence":"additional","affiliation":[{"name":"TSMC Corporate Research,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"TSMC Corporate Research,San Jose,CA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng-Fan","family":"Chang","sequence":"additional","affiliation":[{"name":"TSMC Corporate Research,Hsinchu,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arijit","family":"Raychowdhury","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,Electrical and Computer Engineering Department,Atlanta,GA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS64960.2025.00013"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref8","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/DAC63849.2025.11132610"},{"key":"ref10","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref11","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716016"},{"key":"ref14","article-title":"Slm-mux: Orchestrating small language models for reasoning","author":"Wang","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"ref16","article-title":"Full stack optimization of transformer inference: a survey","author":"Kim","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CODES-ISSS60120.2024.00012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref20","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fsci.2025.1611658"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3273992"},{"key":"ref26","article-title":"Explicit sparse transformer: Concentrated attention through explicit selection","author":"Zhao","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_17"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00571"},{"key":"ref29","article-title":"Tosa: Token selective attention for efficient vision transformers","author":"Singh","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3349004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3315060"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3305663"},{"key":"ref34","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":"ref35","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.183"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.659060"},{"key":"ref40","volume-title":"User manual of dnn+neurosim framework v2.0","author":"Xiaochen Peng","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS64960.2025.00026"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539124.pdf?arnumber=11539124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:06:42Z","timestamp":1780636002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":41,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539124","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}