{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T17:56:57Z","timestamp":1786211817482,"version":"3.56.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"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":[[2023,10,28]]},"DOI":"10.1109\/iccad57390.2023.10323651","type":"proceedings-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T18:58:45Z","timestamp":1701370725000},"page":"01-09","source":"Crossref","is-referenced-by-count":52,"title":["Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-Level Sparsity via Mixture-of-Experts"],"prefix":"10.1109","author":[{"given":"Rishov","family":"Sarkar","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanxue","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwen","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS54282.2022.9869924"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref6","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00332"},{"key":"ref9","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","author":"He","year":"2021","journal-title":"FastMoE: A fast mixture-of-expert training system"},{"key":"ref11","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_37"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/app112210713"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00027"},{"key":"ref16","article-title":"M3vit: Mixture-of-experts vision transformer for efficient multi-task learning with model-accelerator co-design","volume-title":"36th Annual Conference on Neural Information Processing System (NeurIPS 2022)","author":"Liang","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00197"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.433"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102299"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED51717.2021.9424344"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461739"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"ref26","author":"Sun","year":"2022","journal-title":"VAQF: Fully automatic software-hardware co-design framework for low-bit vision transformer"},{"key":"ref27","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International Conference on Machine Learning","volume":"139","author":"Touvron","year":"2021"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3477002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00423"}],"event":{"name":"2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","location":"San Francisco, CA, USA","start":{"date-parts":[[2023,10,28]]},"end":{"date-parts":[[2023,11,2]]}},"container-title":["2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10323590\/10323543\/10323651.pdf?arnumber=10323651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:43:49Z","timestamp":1710380629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10323651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccad57390.2023.10323651","relation":{},"subject":[],"published":{"date-parts":[[2023,10,28]]}}}