{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:54:42Z","timestamp":1781794482587,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"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":[[2026,6,22]]},"DOI":"10.1145\/3787109.3816404","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:17:19Z","timestamp":1781792239000},"page":"220-225","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Shallow Enough? A Cross-Architecture Study of Ultra-Low-Depth Neural Networks for Edge Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4539-5681","authenticated-orcid":false,"given":"Chengwei","family":"Zhou","sequence":"first","affiliation":[{"name":"Case Western Reserve University, CLEVELAND, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4057-1286","authenticated-orcid":false,"given":"Haotian","family":"Yu","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, CLEVELAND, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8488-3008","authenticated-orcid":false,"given":"Shoma","family":"Yukawa","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, CLEVELAND, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2734-8935","authenticated-orcid":false,"given":"Deniz","family":"Najafi","sequence":"additional","affiliation":[{"name":"ECE, New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2289-6381","authenticated-orcid":false,"given":"Shaahin","family":"Angizi","sequence":"additional","affiliation":[{"name":"New Jersey Institute of Technology, Newark, NJ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5380-2619","authenticated-orcid":false,"given":"Gourav","family":"Datta","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, CLEVELAND, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_1_2_2","first-page":"1","volume-title":"IEEE International Symposium on Circuits and Systems (ISCAS)","author":"Agrawal Abhishek","year":"2019","unstructured":"Abhishek Agrawal and Kaushik Roy. 2019. Analog Computing using Approximate Memristors with Applications to Neural Networks. In IEEE International Symposium on Circuits and Systems (ISCAS). 1\u20135."},{"key":"e_1_3_3_1_3_2","unstructured":"Anwaar Anwar Aman Ayush and Aayush Prakash. 2021. Non-deep Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.07641 (2021)."},{"key":"e_1_3_3_1_4_2","unstructured":"Anwaar Anwar and Sung-Yeul Hwang. 2021. ParNet: Position Aware Circular Convolutions with Merges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.07641 (2021)."},{"key":"e_1_3_3_1_5_2","unstructured":"Apple Machine Learning Research. 2024. Deploying Attention-Based Vision Transformers to Apple Neural Engine. https:\/\/machinelearning.apple.com\/research\/vision-transformers."},{"key":"e_1_3_3_1_6_2","unstructured":"Daniel Bolya Cheng-Yang Fu Xiaoliang Dai Peizhao Zhang Christoph Feichtenhofer and Judy Hoffman. 2022. Token Merging: Your ViT But Faster. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.09461 (2022)."},{"key":"e_1_3_3_1_7_2","first-page":"12021","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chen Jierun","year":"2023","unstructured":"Jierun Chen, Shiu-hong Kao, Hao He, Weipeng Zhuo, Song Wen, Chul-Ho Lee, and S.-H.\u00a0Gary Chan. 2023. Run, Don\u2019t Walk: Chasing Higher FLOPs for Faster Neural Networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12021\u201312031."},{"key":"e_1_3_3_1_8_2","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"David Robert","year":"2021","unstructured":"Robert David, Jared Duke, Advait Jain, Vijay\u00a0Janapa Reddi, Nat Jeffries, Jian Li, Nick Kreber, Irene Natsev, Suyog Wang, Tom Warden, and Rocky Rhodes. 2021. TensorFlow Lite Micro: Embedded Machine Learning for TinyML Systems. In Proceedings of Machine Learning and Systems (MLSys)."},{"key":"e_1_3_3_1_9_2","first-page":"6849","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML)","author":"Fu Yonggan","year":"2022","unstructured":"Yonggan Fu, Haoran Yang, Jiayi Yuan, Meng Li, Cheng Wan, Raghuraman Krishnamoorthi, Vikas Chandra, and Yingyan Lin. 2022. DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks. In Proceedings of the 39th International Conference on Machine Learning (ICML). PMLR, 6849\u20136862."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_3_1_11_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1503.02531 (2015)."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_3_1_13_2","first-page":"5156","volume-title":"International Conference on Machine Learning (ICML)","author":"Katharopoulos Angelos","year":"2020","unstructured":"Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Fran\u00e7ois Fleuret. 2020. Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention. In International Conference on Machine Learning (ICML). 5156\u20135165."},{"key":"e_1_3_3_1_14_2","unstructured":"Seonghoon Kim et\u00a0al. 2024. Evaluating and Accelerating Vision Transformers on GPU-Based Embedded Edge AI Systems. The Journal of Supercomputing (2024)."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_1_16_2","first-page":"2001","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Lee Seokju","year":"2024","unstructured":"Seokju Lee, Seunghwan Kim, Jongse Lee, and Wonyong Sung. 2024. SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2001\u20132011."},{"key":"e_1_3_3_1_17_2","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Li Hongkang","year":"2023","unstructured":"Hongkang Li, Meng Wang, Sijia Liu, and Pin-Yu Chen. 2023. A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity. In The Eleventh International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_18_2","first-page":"1478","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"Li Jiashi","year":"2022","unstructured":"Jiashi Li, Xin Xia, Wei Li, Huixia Li, Xing Wang, Xuefeng Xiao, Rui Wang, Min Zheng, and Xin Pan. 2022. Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol.\u00a036. 1478\u20131486."},{"key":"e_1_3_3_1_19_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Lin Ji","year":"2020","unstructured":"Ji Lin, Wei-Ming Chen, Yujun Lin, John Cohn, Chuang Gan, and Song Han. 2020. MCUNet: Tiny Deep Learning on IoT Devices. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_20_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong\u00a0Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_21_2","first-page":"24101","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Liu Woosuk","year":"2022","unstructured":"Woosuk Liu, Zhenyu Zhou, Zhili Zhuang, Bing Xiao, Jian Chen, and Ion Stoica. 2022. A Fast Post-Training Pruning Framework for Transformers. In Advances in Neural Information Processing Systems (NeurIPS) , Vol.\u00a035. 24101\u201324116."},{"key":"e_1_3_3_1_22_2","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Lyu Yanyu","year":"2022","unstructured":"Yanyu Lyu, Guanzhong Jiang, Yiteng Lyu, and Meng Yang. 2022. EfficientFormer: Vision Transformers at MobileNet Speed. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_3_1_23_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Mehta Sachin","year":"2022","unstructured":"Sachin Mehta and Mohammad Rastegari. 2022. MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_24_2","unstructured":"NVIDIA. 2024. TensorRT SDK. https:\/\/developer.nvidia.com\/tensorrt."},{"key":"e_1_3_3_1_25_2","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et\u00a0al. 2023. DINOv2: Learning Robust Visual Features without Supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.07193 (2023)."},{"key":"e_1_3_3_1_26_2","unstructured":"Qualcomm. 2025. Snapdragon 8 Elite Hexagon Tensor Processor."},{"key":"e_1_3_3_1_27_2","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning Transferable Visual Models from Natural Language Supervision. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_1_28_2","first-page":"13937","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","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 (NeurIPS). 13937\u201313949."},{"key":"e_1_3_3_1_29_2","first-page":"12786","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Ryoo Michael\u00a0S.","year":"2021","unstructured":"Michael\u00a0S. Ryoo, AJ Piergiovanni, Anurag Arnab, Mostafa Dehghani, and Anelia Angelova. 2021. TokenLearner: Adaptive Space-Time Tokenization for Videos. In Advances in Neural Information Processing Systems (NeurIPS). 12786\u201312797."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_3_1_31_2","unstructured":"Utkarsh Saxena Shubham Negi and Kaushik Roy. 2021. ADC-less Compute-in-Memory Architectures for Deep Neural Networks. IEEE Transactions on Circuits and Systems I: Regular Papers 68 11 (2021) 4663\u20134674."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Yichen Shen Nicholas\u00a0C. Harris Scott Skirlo Mihika Prabhu Tom Baehr-Jones Michael Hochberg Xin Sun Shijie Zhao Hugo Larochelle Dirk Englund and Marin Solja\u010di\u0107. 2017. Deep Learning with Coherent Nanophotonic Circuits. Nature Photonics 11 7 (2017) 441\u2013446.","DOI":"10.1038\/nphoton.2017.93"},{"key":"e_1_3_3_1_34_2","first-page":"10347","volume-title":"International Conference on Machine Learning (ICML)","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training Data-Efficient Image Transformers & Distillation through Attention. In International Conference on Machine Learning (ICML). PMLR, 10347\u201310357."},{"key":"e_1_3_3_1_35_2","first-page":"5785","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Vasu Pavan Kumar\u00a0Anasosalu","year":"2023","unstructured":"Pavan Kumar\u00a0Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. 2023. FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 5785\u20135795."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"e_1_3_3_1_38_2","unstructured":"Chengwei Zhou Yang Ni Vipin Chaudhary and Gourav Datta. 2026. Training Wide Deploying Shallow: Structural Re-parameterization for Vision Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.xxxxx (2026)."}],"event":{"name":"GLSVLSI '26: Great Lakes Symposium on VLSI 2026","location":"Canandaigua , NY , USA","acronym":"GLSVLSI '26","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CEDA"]},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2026"],"original-title":[],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T14:21:30Z","timestamp":1781792490000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787109.3816404"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":37,"alternative-id":["10.1145\/3787109.3816404","10.1145\/3787109"],"URL":"https:\/\/doi.org\/10.1145\/3787109.3816404","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}