{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:05:02Z","timestamp":1764777902541,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1145\/3769102.3770612","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:00:41Z","timestamp":1764777641000},"page":"1-14","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Elastoformer: Enabling Dynamic Adaptivity via Elastic Model Transformation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6804-8908","authenticated-orcid":false,"given":"Sudaksh","family":"Kalra","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3590-0394","authenticated-orcid":false,"given":"Dolly","family":"Sapra","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Learning Representations.","author":"Bolya Daniel","year":"2023","unstructured":"Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, and Judy Hoffman. 2023. Token Merging: Your ViT but Faster. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","author":"Kudugunta Sneha","year":"2025","unstructured":"Devvrit, Sneha Kudugunta, Aditya Kusupati, Tim Dettmers, Kaifeng Chen, Inderjit Dhillon, Yulia Tsvetkov, Hannaneh Hajishirzi, Sham Kakade, Ali Farhadi, and Prateek Jain. 2025. MatFormer: nested transformer for elastic inference. In Proceedings of the 38th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS '24). Curran Associates Inc., Red Hook, NY, USA, Article 4461, 30 pages."},{"key":"e_1_3_2_1_4_1","volume-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR (2021)."},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"Neural architecture search: a survey","volume":"20","author":"Elsken Thomas","year":"2019","unstructured":"Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. 2019. Neural architecture search: a survey. J. Mach. Learn. Res. 20, 1 (Jan. 2019), 1997\u20132017.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEC50012.2020.00014"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483249"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1510.00149"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems -","volume":"1","author":"Han Song","unstructured":"Song Han, Jeff Pool, John Tran, and William J. Dally. 2015. Learning both weights and connections for efficient neural networks. In Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 1 (Montreal, Canada) (NIPS'15). MIT Press, Cambridge, MA, USA, 1135\u20131143."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861 [cs]. 10.48550\/arXiv.1704.04861","DOI":"10.48550\/arXiv.1704.04861"},{"key":"e_1_3_2_1_16_1","volume-title":"Weinberger","author":"Huang Gao","year":"2016","unstructured":"Gao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, and Kilian Q. Weinberger. 2016. Deep Networks with Stochastic Depth. In Computer Vision - ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 646\u2013661."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157557"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"e_1_3_2_1_19_1","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto. https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf Technical Report."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469116.3470012"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 3rd International Conference on Neural Information Processing Systems (NIPS'89)","author":"Cun Yann Le","unstructured":"Yann Le Cun, John S. Denker, and Sara A. Solla. 1989. Optimal brain damage. In Proceedings of the 3rd International Conference on Neural Information Processing Systems (NIPS'89). MIT Press, Cambridge, MA, USA, 598\u2013605."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Hao Li Asim Kadav Igor Durdanovic Hanan Samet and Hans Peter Graf. 2017. Pruning Filters for Efficient ConvNets. arXiv:1608.08710 [cs]. 10.48550\/arXiv.1608.08710","DOI":"10.48550\/arXiv.1608.08710"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488718"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila and Jan Kautz. 2017. Pruning Convolutional Neural Networks for Resource Efficient Inference. arXiv:1611.06440 [cs]. 10.48550\/arXiv.1611.06440","DOI":"10.48550\/arXiv.1611.06440"},{"key":"e_1_3_2_1_25_1","volume-title":"Jetson Orin Embedded Systems. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-orin\/ Accessed","author":"NVIDIA.","year":"2025","unstructured":"NVIDIA. 2025. Jetson Orin Embedded Systems. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-orin\/ Accessed: Jun. 16, 2025."},{"key":"e_1_3_2_1_26_1","volume-title":"Jetson Nano: Product Development. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-nano\/product-development\/. Accessed: 2025-06-27.","author":"NVIDIA Corporation","year":"2025","unstructured":"NVIDIA Corporation. 2025. Jetson Nano: Product Development. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-nano\/product-development\/. Accessed: 2025-06-27."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning -","volume":"28","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu, Tomas Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 (Atlanta, GA, USA) (ICML'13). JMLR.org, III-1310\u2013III-1318."},{"key":"e_1_3_2_1_28_1","volume-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas K\u00f6pf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: an imperative style, high-performance deep learning library. Curran Associates Inc., Red Hook, NY, USA."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21)","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 Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 1068, 13 pages."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55789-8_61"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACET61898.2024.10730112"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs]. 10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10136943"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"10357","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 amp; distillation through attention. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 10347\u201310357. https:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Huan Wang Can Qin Yue Bai and Yun Fu. 2023. Why is the State of Neural Network Pruning so Confusing? On the Fairness Comparison Setup and Trainability in Network Pruning. arXiv:2301.05219 [cs]. 10.48550\/arXiv.2301.05219","DOI":"10.48550\/arXiv.2301.05219"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21)","author":"Wang Yulin","year":"2021","unstructured":"Yulin Wang, Rui Huang, Shiji Song, Zeyi Huang, and Gao Huang. 2021. Not all images are worth 16x16 words: dynamic transformers for efficient image recognition. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 915, 14 pages."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592529"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611762"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01779"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00189"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Jiahui Yu Linjie Yang Ning Xu Jianchao Yang and Thomas Huang. 2018. Slimmable Neural Networks. arXiv:1812.08928 [cs]. 10.48550\/arXiv.1812.08928","DOI":"10.48550\/arXiv.1812.08928"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","unstructured":"Hongyi Zhang Moustapha Cisse Yann N. Dauphin and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. arXiv:1710.09412 [cs]. 10.48550\/arXiv.1710.09412","DOI":"10.48550\/arXiv.1710.09412"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Mingjian Zhu Yehui Tang and Kai Han. 2021. Vision Transformer Pruning. arXiv:2104.08500 [cs]. 10.48550\/arXiv.2104.08500","DOI":"10.48550\/arXiv.2104.08500"}],"event":{"name":"SEC '25: Tenth ACM\/IEEE Symposium on Edge Computing","location":"the Hilton Arlington National Landing Arlington VA USA","acronym":"SEC '25","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","IEEE Computer Society"]},"container-title":["Proceedings of the Tenth ACM\/IEEE Symposium on Edge Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769102.3770612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T16:01:11Z","timestamp":1764777671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769102.3770612"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":48,"alternative-id":["10.1145\/3769102.3770612","10.1145\/3769102"],"URL":"https:\/\/doi.org\/10.1145\/3769102.3770612","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"2025-12-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}