{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:12Z","timestamp":1782546432954,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801487.3801830","type":"proceedings-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:05:47Z","timestamp":1782543947000},"page":"160-168","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["LSFAF: A Layer-Sharing and FPGA-Accelerated Framework for Fast Collaborative Inference in Edge Scenarios"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5181-9150","authenticated-orcid":false,"given":"Bin","family":"Zheng","sequence":"first","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6259-0896","authenticated-orcid":false,"given":"Yujie","family":"Peng","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3565-7510","authenticated-orcid":false,"given":"Zhenkai","family":"Sun","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-2673","authenticated-orcid":false,"given":"Jianxin","family":"Wang","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-8738","authenticated-orcid":false,"given":"Jin","family":"Wang","sequence":"additional","affiliation":[{"name":"Changsha University of Science and Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"9355","volume-title":"Advances in Neural Information Processing Systems","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu, Zhi Tian, Yuqing Wang, Bo Zhang, Haibing Ren, Xiaolin Wei, Huaxia Xia, and Chunhua Shen. 2021. Twins: Revisiting the Design of Spatial Attention in Vision Transformers. In Advances in Neural Information Processing Systems , M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.), Vol.\u00a034. Curran Associates, Inc., 9355\u20139366. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/4e0928de075538c593fbdabb0c5ef2c3-Paper.pdf"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Peiyan Dong Jinming Zhuang Zhuoping Yang Shixin Ji Yanyu Li Dongkuan Xu Heng Huang Jingtong Hu Alex\u00a0K. Jones Yiyu Shi Yanzhi Wang and Peipei Zhou. 2024. EQ-ViT: Algorithm-Hardware Co-Design for End-to-End Acceleration of Real-Time Vision Transformer Inference on Versal ACAP Architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43 11 (2024) 3949\u20133960. 10.1109\/TCAD.2024.3443692","DOI":"10.1109\/TCAD.2024.3443692"},{"key":"e_1_3_3_1_4_2","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676681"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00110"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Yiping Kang Johann Hauswald Cao Gao Austin Rovinski Trevor Mudge Jason Mars and Lingjia Tang. 2017. Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge. SIGARCH Comput. Archit. News 45 1 (April 2017) 615\u2013629. 10.1145\/3093337.3037698","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_3_1_9_2","unstructured":"Alex Krizhevsky Geoffrey Hinton et\u00a0al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0940"},{"key":"e_1_3_3_1_12_2","unstructured":"Zhuojin Li Marco Paolieri and Leana Golubchik. 2025. A Study on Inference Latency for Vision Transformers on Mobile Devices. arxiv:https:\/\/arXiv.org\/abs\/2510.25166\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2510.25166"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS63083.2025.00036"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC58850.2023.00039"},{"key":"e_1_3_3_1_16_2","unstructured":"Sachin Mehta and Mohammad Rastegari. 2021. MobileViT: Light-weight General-purpose and Mobile-friendly Vision Transformer. CoRR abs\/2110.02178 (2021). arXiv:https:\/\/arXiv.org\/abs\/2110.02178https:\/\/arxiv.org\/abs\/2110.02178"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Jun Na Handuo Zhang Jiaxin Lian and Bin Zhang. 2022. Partitioning DNNs for Optimizing Distributed Inference Performance on Cooperative Edge Devices: A Genetic Algorithm Approach. Applied Sciences 12 20 (2022). 10.3390\/app122010619","DOI":"10.3390\/app122010619"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS46773.2023.10181988"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"e_1_3_3_1_22_2","unstructured":"PyTorch Team. [n. d.]. torch.profiler \u2014 PyTorch Documentation. https:\/\/docs.pytorch.org\/docs\/stable\/profiler.html. Last updated: 2025-06-13 accessed: 2026-01-20."},{"key":"e_1_3_3_1_23_2","first-page":"12116","volume-title":"Advances in Neural Information Processing Systems","author":"Raghu Maithra","year":"2021","unstructured":"Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, and Alexey Dosovitskiy. 2021. Do Vision Transformers See Like Convolutional Neural Networks?. In Advances in Neural Information Processing Systems , M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.), Vol.\u00a034. Curran Associates, Inc., 12116\u201312128. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/652cf38361a209088302ba2b8b7f51e0-Paper.pdf"},{"key":"e_1_3_3_1_24_2","first-page":"13937","volume-title":"Advances in Neural Information Processing Systems","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification. In Advances in Neural Information Processing Systems , M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.), Vol.\u00a034. Curran Associates, Inc., 13937\u201313949. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/747d3443e319a22747fbb873e8b2f9f2-Paper.pdf"},{"key":"e_1_3_3_1_25_2","series-title":"Proceedings of Machine Learning Research","first-page":"10347","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herve Jegou. 2021. Training data-efficient image transformers & distillation through attention. In Proceedings of the 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0139), Marina Meila and Tong Zhang (Eds.). PMLR, 10347\u201310357. https:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"e_1_3_3_1_26_2","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141\u00a0ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Guanyu Xu Zhiwei Hao Yong Luo Han Hu Jianping An and Shiwen Mao. 2024. DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices. IEEE Transactions on Mobile Computing 23 5 (2024) 5917\u20135932. 10.1109\/TMC.2023.3315138","DOI":"10.1109\/TMC.2023.3315138"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Sifan Zhao Tongtong Liu Hai Jin and Dezhong Yao. 2025. SPViT: Accelerate Vision Transformer Inference on Mobile Devices via Adaptive Splitting and Offloading. IEEE Transactions on Mobile Computing 24 10 (2025) 9303\u20139318.","DOI":"10.1109\/TMC.2025.3562721"}],"event":{"name":"CF '26: Proceedings of the 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801487.3801830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:12:57Z","timestamp":1782544377000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801487.3801830"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":28,"alternative-id":["10.1145\/3801487.3801830","10.1145\/3801487"],"URL":"https:\/\/doi.org\/10.1145\/3801487.3801830","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}