{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:52:42Z","timestamp":1763704362343,"version":"3.45.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014553","name":"Samsung Advanced Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014553","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240777","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":0,"title":["Mamba-X: An End-to-End Vision Mamba Accelerator for Edge Computing Devices"],"prefix":"10.1109","author":[{"given":"Dongho","family":"Yoon","sequence":"first","affiliation":[{"name":"KAIST"}]},{"given":"Gungyu","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Jaewon","family":"Chang","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Yunjae","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Dongjae","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST"}]},{"given":"Minsoo","family":"Rhu","sequence":"additional","affiliation":[{"name":"KAIST"}]}],"member":"263","reference":[{"article-title":"Attention is All You Need","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Vaswani","key":"ref1"},{"article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Dosovitskiy","key":"ref2"},{"article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford","key":"ref3"},{"article-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","year":"2024","author":"Gu","key":"ref4"},{"article-title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Zhu","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3645107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9041955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00094"},{"article-title":"Efficiently Modeling Long Sequences with Structured State Spaces","year":"2022","author":"Gu","key":"ref9"},{"article-title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","year":"2023","author":"Fu","key":"ref10"},{"article-title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Gu","key":"ref11"},{"article-title":"Efficiently Scaling Transformer Inference","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"Pope","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1973.5009159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.30"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522352"},{"year":"2025","key":"ref18","article-title":"NVIDIA Nsight Compute"},{"year":"2022","key":"ref19","article-title":"NVIDIA CUB Library"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/mc.1982.1653825"},{"article-title":"Systolic Arrays (for VLSI)","volume-title":"Sparse Matrix Proceedings","author":"Kung","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530505"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247855"},{"year":"2025","key":"ref25","article-title":"NVIDIA Automatic Mixed Precision for Deep Learning"},{"year":"2018","key":"ref26","article-title":"Jetson AGX Xavier Series"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.vlsi.2017.02.002"},{"article-title":"High-Bandwidth Memory and Processing-in-Memory in the Era of Generative AI","volume-title":"Proceedings of the International Solid State Circuits Conference (ISSCC)","author":"Sohn","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2024.3422492"},{"article-title":"VMamba: Visual State Space Model","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Liu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00106"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676798"},{"article-title":"Post-Training Quantization for Vision Transformer","volume-title":"Proceedings of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Liu","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071081"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","start":{"date-parts":[[2025,10,26]]},"location":"Munich, Germany","end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240777.pdf?arnumber=11240777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:44:16Z","timestamp":1763703856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240777","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}