{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T14:20:24Z","timestamp":1776090024934,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":102,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642628","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:38:25Z","timestamp":1715416705000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-844X","authenticated-orcid":false,"given":"Fred","family":"Hohman","sequence":"first","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5676-4592","authenticated-orcid":false,"given":"Chaoqun","family":"Wang","sequence":"additional","affiliation":[{"name":"Apple, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7693-8148","authenticated-orcid":false,"given":"Jinmook","family":"Lee","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6510-0908","authenticated-orcid":false,"given":"Jochen","family":"G\u00f6rtler","sequence":"additional","affiliation":[{"name":"Independent Researcher, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3110-1053","authenticated-orcid":false,"given":"Dominik","family":"Moritz","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2072-0625","authenticated-orcid":false,"given":"Jeffrey P","family":"Bigham","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0302-795X","authenticated-orcid":false,"given":"Zhile","family":"Ren","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8341-756X","authenticated-orcid":false,"given":"Cecile","family":"Foret","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1520-9283","authenticated-orcid":false,"given":"Qi","family":"Shan","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6591-7162","authenticated-orcid":false,"given":"Xiaoyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","first-page":"1086","article-title":"Fairsight: Visual analytics for fairness in decision making","volume":"26","author":"Ahn Yongsu","year":"2019","unstructured":"Yongsu Ahn and Yu-Ru Lin. 2019. Fairsight: Visual analytics for fairness in decision making. IEEE Transactions on Visualization and Computer Graphics 26, 1 (2019), 1086\u20131095.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/icse-seip.2019.00042"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702509"},{"key":"e_1_3_3_3_4_1","volume-title":"On-device panoptic segmentation for camera using transformers. Machine Learning Research","year":"2021","unstructured":"Apple. 2021. On-device panoptic segmentation for camera using transformers. Machine Learning Research (2021). https:\/\/machinelearning.apple.com\/research\/panoptic-segmentation"},{"key":"e_1_3_3_3_5_1","volume-title":"Deploying transformers on the Apple Neural Engine. Machine Learning Research","year":"2022","unstructured":"Apple. 2022. Deploying transformers on the Apple Neural Engine. Machine Learning Research (2022). https:\/\/machinelearning.apple.com\/research\/neural-engine-transformers"},{"key":"e_1_3_3_3_6_1","volume-title":"A multi-task neural architecture for on-device scene analysis. Machine Learning Research","year":"2022","unstructured":"Apple. 2022. A multi-task neural architecture for on-device scene analysis. Machine Learning Research (2022). https:\/\/machinelearning.apple.com\/research\/on-device-scene-analysis"},{"key":"e_1_3_3_3_7_1","unstructured":"Apple. 2023. Optimizing models - Core ML Tools overview. https:\/\/coremltools.readme.io\/docs"},{"key":"e_1_3_3_3_8_1","volume-title":"Benchmarking tinyml systems: Challenges and direction. arXiv preprint arXiv:2003.04821","author":"Banbury R","year":"2020","unstructured":"Colby\u00a0R Banbury, Vijay\u00a0Janapa Reddi, Max Lam, William Fu, Amin Fazel, Jeremy Holleman, Xinyuan Huang, Robert Hurtado, David Kanter, Anton Lokhmotov, 2020. Benchmarking tinyml systems: Challenges and direction. arXiv preprint arXiv:2003.04821 (2020)."},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502102"},{"key":"e_1_3_3_3_10_1","volume-title":"DendroMap: Visual exploration of large-scale image datasets for machine learning with treemaps","author":"Bertucci Donald","year":"2022","unstructured":"Donald Bertucci, Md\u00a0Montaser Hamid, Yashwanthi Anand, Anita Ruangrotsakun, Delyar Tabatabai, Melissa Perez, and Minsuk Kahng. 2022. DendroMap: Visual exploration of large-scale image datasets for machine learning with treemaps. IEEE Transactions on Visualization and Computer Graphics (2022)."},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3379393"},{"key":"e_1_3_3_3_12_1","volume-title":"Conducting in-depth interviews: A guide for designing and conducting in-depth interviews for evaluation input. Vol.\u00a02","author":"Boyce Carolyn","unstructured":"Carolyn Boyce and Palena Neale. 2006. Conducting in-depth interviews: A guide for designing and conducting in-depth interviews for evaluation input. Vol.\u00a02. Pathfinder International Watertown, MA."},{"key":"e_1_3_3_3_13_1","volume-title":"The role of interactive visualization in explaining (large) NLP models: From data to inference. arXiv preprint arXiv:2301.04528","author":"Brath Richard","year":"2023","unstructured":"Richard Brath, Daniel Keim, Johannes Knittel, Shimei Pan, Pia Sommerauer, and Hendrik Strobelt. 2023. The role of interactive visualization in explaining (large) NLP models: From data to inference. arXiv preprint arXiv:2301.04528 (2023)."},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.124"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/VAST47406.2019.8986948"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581268"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2765695"},{"key":"e_1_3_3_3_18_1","volume-title":"International Conference on Learning Representations. https:\/\/arxiv.org\/abs\/2108","author":"Cho Minsik","year":"2022","unstructured":"Minsik Cho, Keivan\u00a0A. Vahid, Saurabh Adya, and Mohammad Rastegari. 2022. Differentiable k-means clustering layer for neural network compression. In International Conference on Learning Representations. https:\/\/arxiv.org\/abs\/2108.12659"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/VAST.2010.5652443"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1456650.1456652"},{"key":"e_1_3_3_3_22_1","volume-title":"LEGION: visually compare modeling techniques for regression. In 2020 Visualization in Data Science","author":"Das Subhajit","unstructured":"Subhajit Das and Alex Endert. 2020. LEGION: visually compare modeling techniques for regression. In 2020 Visualization in Data Science. IEEE, 12\u201321."},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2020.2976475"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450494"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR.2018.8707381"},{"key":"e_1_3_3_3_26_1","unstructured":"Farah Fahim Benjamin Hawks Christian Herwig James Hirschauer Sergo Jindariani Nhan Tran Luca\u00a0P Carloni Giuseppe Di\u00a0Guglielmo Philip Harris Jeffrey Krupa 2021. hls4ml: An open-source codesign workflow to empower scientific low-power machine learning devices. (2021). arXiv:2103.05579"},{"key":"e_1_3_3_3_27_1","volume-title":"A survey of quantization methods for efficient neural network inference. arXiv","author":"Gholami Amir","year":"2021","unstructured":"Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael\u00a0W Mahoney, and Kurt Keutzer. 2021. A survey of quantization methods for efficient neural network inference. arXiv (2021). arXiv:2103.13630"},{"key":"e_1_3_3_3_28_1","volume-title":"Artificial intelligence. Our World in Data","author":"Giattino Charlie","year":"2022","unstructured":"Charlie Giattino, Edouard Mathieu, Veronika Samborska, Julia Broden, and Max Roser. 2022. Artificial intelligence. Our World in Data (2022). https:\/\/ourworldindata.org\/artificial-intelligence."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781849208574.n4"},{"key":"e_1_3_3_3_30_1","unstructured":"Github. 2021. Copilot. https:\/\/github.com\/features\/copilot"},{"key":"e_1_3_3_3_31_1","unstructured":"Google. 2019. QKeras. https:\/\/github.com\/google\/qkeras"},{"key":"e_1_3_3_3_32_1","volume-title":"Why on-device machine learning?Google Developers (Accessed","author":"Accessed","year":"2022","unstructured":"Google. Accessed 2022. Why on-device machine learning?Google Developers (Accessed 2022). https:\/\/developers.google.com\/learn\/topics\/on-device-ml\/learn-more"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030350"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3424660"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501823"},{"key":"e_1_3_3_3_37_1","unstructured":"Song Han Huizi Mao and William\u00a0J Dally. 2016. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. (2016)."},{"key":"e_1_3_3_3_38_1","volume-title":"MLX: Efficient and flexible machine learning on Apple silicon. https:\/\/github.com\/ml-explore","author":"Hannun Awni","year":"2023","unstructured":"Awni Hannun, Jagrit Digani, Angelos Katharopoulos, and Ronan Collobert. 2023. MLX: Efficient and flexible machine learning on Apple silicon. https:\/\/github.com\/ml-explore"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300500"},{"key":"e_1_3_3_3_40_1","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler Torsten","year":"2021","unstructured":"Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, and Alexandra Peste. 2021. Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. Journal of Machine Learning Research 22, 241 (2021), 1\u2013124.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2843369"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642109"},{"key":"e_1_3_3_3_43_1","volume-title":"exbert: A visual analysis tool to explore learned representations in transformers models. arXiv preprint arXiv:1910.05276","author":"Hoover Benjamin","year":"2019","unstructured":"Benjamin Hoover, Hendrik Strobelt, and Sebastian Gehrmann. 2019. exbert: A visual analysis tool to explore learned representations in transformers models. arXiv preprint arXiv:1910.05276 (2019)."},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_3_45_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv abs\/1704.04861","author":"Howard G","year":"2017","unstructured":"Andrew\u00a0G 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 abs\/1704.04861 (2017). arXiv:1704.04861"},{"key":"e_1_3_3_3_46_1","unstructured":"Google Inc.2021. Know Your Data. https:\/\/knowyourdata.withgoogle.com\/"},{"key":"e_1_3_3_3_47_1","unstructured":"Intel. 2020. Neural Compressor. https:\/\/github.com\/intel\/neural-compressor"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939502.2939503"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300322"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415842"},{"key":"e_1_3_3_3_51_1","volume-title":"Jupyter Notebooks-a publishing format for reproducible computational workflows.Elpub 2016","author":"Kluyver Thomas","year":"2016","unstructured":"Thomas Kluyver, Benjamin Ragan-Kelley, Fernando P\u00e9rez, Brian\u00a0E Granger, Matthias Bussonnier, Jonathan Frederic, Kyle Kelley, Jessica\u00a0B Hamrick, Jason Grout, Sylvain Corlay, 2016. Jupyter Notebooks-a publishing format for reproducible computational workflows.Elpub 2016 (2016), 87\u201390."},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-022-00150-6"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3030461"},{"key":"e_1_3_3_3_54_1","volume-title":"Learning IoT in edge: Deep learning for the nternet of Things with edge computing","author":"Li He","year":"2018","unstructured":"He Li, Kaoru Ota, and Mianxiong Dong. 2018. Learning IoT in edge: Deep learning for the nternet of Things with edge computing. IEEE network 32, 1 (2018), 96\u2013101."},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2020.2986024"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3028888"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578938"},{"key":"e_1_3_3_3_58_1","unstructured":"Microsoft. 2021. Neural network intelligence. https:\/\/github.com\/microsoft\/nni"},{"key":"e_1_3_3_3_59_1","unstructured":"Microsoft. 2023. Visual studio code. https:\/\/code.visualstudio.com\/"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3469029"},{"key":"e_1_3_3_3_61_1","unstructured":"NVIDIA. 2023. NVIDIA deep learning TensorRT documentation. https:\/\/docs.nvidia.com\/deeplearning\/tensorrt\/developer-guide\/index.html#optimize-performance"},{"key":"e_1_3_3_3_62_1","unstructured":"OpenAI. 2021. OpenAI Codex. https:\/\/openai.com\/blog\/openai-codex"},{"key":"e_1_3_3_3_63_1","volume-title":"GPT-4 technical report. arXiv","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. GPT-4 technical report. arXiv (2023). arXiv:2303.08774"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357160"},{"key":"e_1_3_3_3_65_1","volume-title":"Model compression via distillation and quantization. arXiv","author":"Polino Antonio","year":"2018","unstructured":"Antonio Polino, Razvan Pascanu, and Dan Alistarh. 2018. Model compression via distillation and quantization. arXiv (2018). arXiv:1802.05668"},{"key":"e_1_3_3_3_66_1","unstructured":"PyTorch. 2018. Quantization. https:\/\/pytorch.org\/docs\/stable\/quantization.html"},{"key":"e_1_3_3_3_67_1","unstructured":"PyTorch. 2019. Sparisty. https:\/\/pytorch.org\/docs\/stable\/sparse.html"},{"key":"e_1_3_3_3_68_1","unstructured":"PyTorch. 2023. PyTorch Examples. https:\/\/pytorch.org\/tutorials\/"},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL.2017.7991618"},{"key":"e_1_3_3_3_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2598828"},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","unstructured":"Lutz Roeder. 2017. Netron visualizer for neural network deep learning and machine learning models. https:\/\/doi.org\/10.5281\/zenodo.5854962","DOI":"10.5281\/zenodo.5854962"},{"key":"e_1_3_3_3_72_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention. Springer, 234\u2013241."},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"e_1_3_3_3_74_1","volume-title":"Organizational culture. Vol.\u00a045","author":"Schein H","unstructured":"Edgar\u00a0H Schein. 1990. Organizational culture. Vol.\u00a045. American Psychological Association."},{"key":"e_1_3_3_3_75_1","volume-title":"Machine learning: The high interest credit card of technical debt. Google","author":"Sculley David","year":"2014","unstructured":"David Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, and Michael Young. 2014. Machine learning: The high interest credit card of technical debt. Google (2014)."},{"key":"e_1_3_3_3_76_1","doi-asserted-by":"publisher","DOI":"10.3390\/make1010027"},{"key":"e_1_3_3_3_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/VL.1996.545307"},{"key":"e_1_3_3_3_78_1","unstructured":"Stanford. 2023. The AI index report: Measuring trends in artificial intelligence. https:\/\/aiindex.stanford.edu\/report\/"},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744158"},{"key":"e_1_3_3_3_80_1","first-page":"1146","article-title":"Interactive and visual prompt engineering for ad-hoc task adaptation with large language models","volume":"29","author":"Strobelt Hendrik","year":"2022","unstructured":"Hendrik Strobelt, Albert Webson, Victor Sanh, Benjamin Hoover, Johanna Beyer, Hanspeter Pfister, and Alexander\u00a0M Rush. 2022. Interactive and visual prompt engineering for ad-hoc task adaptation with large language models. IEEE Transactions on Visualization and Computer Graphics 29, 1 (2022), 1146\u20131156.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_3_3_81_1","volume-title":"International Conference on Machine Learning. PMLR, 6105\u20136114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning. PMLR, 6105\u20136114. arXiv:1905.11946"},{"key":"e_1_3_3_3_82_1","unstructured":"TensorFlow. 2018. Introducing the Model Optimization Toolkit for TensorFlow. https:\/\/blog.tensorflow.org\/2018\/09\/introducing-model-optimization-toolkit.html"},{"key":"e_1_3_3_3_83_1","unstructured":"TensorFlow. 2020. Quantization aware training with TensorFlow Model Optimization Toolkit - performance with accuracy. https:\/\/blog.tensorflow.org\/2020\/04\/quantization-aware-training-with-tensorflow-model-optimization-toolkit.html"},{"key":"e_1_3_3_3_84_1","doi-asserted-by":"publisher","DOI":"10.1177\/1098214005283748"},{"key":"e_1_3_3_3_85_1","unstructured":"Edward\u00a0R Tufte. 1986. The visual display of quantitative information. (1986)."},{"key":"e_1_3_3_3_86_1","volume-title":"An improved one millisecond mobile backbone. arXiv preprint arXiv:2206.04040","author":"Kumar\u00a0Anasosalu Vasu Pavan","year":"2022","unstructured":"Pavan Kumar\u00a0Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. 2022. An improved one millisecond mobile backbone. arXiv preprint arXiv:2206.04040 (2022)."},{"key":"e_1_3_3_3_87_1","volume-title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization. arXiv preprint arXiv:2303.14189","author":"Kumar\u00a0Anasosalu Vasu Pavan","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. arXiv preprint arXiv:2303.14189 (2023)."},{"key":"e_1_3_3_3_88_1","unstructured":"Pablo Villalobos Jaime Sevilla Tamay Besiroglu Lennart Heim Anson Ho and Marius Hobbhahn. 2022. Machine learning model sizes and the parameter gap. arxiv:2207.02852\u00a0[cs.LG]"},{"key":"e_1_3_3_3_89_1","volume-title":"Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers. O\u2019Reilly Media.","author":"Warden Pete","year":"2019","unstructured":"Pete Warden and Daniel Situnayake. 2019. Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers. O\u2019Reilly Media."},{"key":"e_1_3_3_3_90_1","unstructured":"Megan\u00a0Maher Welsh David Koski Miguel Sarabia Niv Sivakumar Ian Arawjo Aparna Joshi Moussa Doumbouya Luca Suau Xavierand\u00a0Zappella and Nicholas Apostoloff. 2023. Data and Network Introspection Kit. https:\/\/github.com\/apple\/dnikit"},{"key":"e_1_3_3_3_91_1","volume-title":"The what-if tool: Interactive probing of machine learning models","author":"Wexler James","year":"2019","unstructured":"James Wexler, Mahima Pushkarna, Tolga Bolukbasi, Martin Wattenberg, Fernanda Vi\u00e9gas, and Jimbo Wilson. 2019. The what-if tool: Interactive probing of machine learning models. IEEE transactions on visualization and computer graphics 26, 1 (2019), 56\u201365."},{"key":"e_1_3_3_3_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744878"},{"key":"e_1_3_3_3_93_1","volume-title":"International Conference on Machine Learning. PMLR, 5363\u20135372","author":"Wu Junru","year":"2018","unstructured":"Junru Wu, Yue Wang, Zhenyu Wu, Zhangyang Wang, Ashok Veeraraghavan, and Yingyan Lin. 2018. Deep k-means: Re-training and parameter sharing with harder cluster assignments for compressing deep convolutions. In International Conference on Machine Learning. PMLR, 5363\u20135372."},{"key":"e_1_3_3_3_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/3094243.3094262"},{"key":"e_1_3_3_3_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3165347"},{"key":"e_1_3_3_3_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/icicis46948.2019.9014733"},{"key":"e_1_3_3_3_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3392826"},{"key":"e_1_3_3_3_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00716"},{"key":"e_1_3_3_3_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2022.3153408"},{"key":"e_1_3_3_3_100_1","volume-title":"A survey of large language models. arXiv preprint arXiv:2303.18223","author":"Zhao Wayne\u00a0Xin","year":"2023","unstructured":"Wayne\u00a0Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."},{"key":"e_1_3_3_3_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2019.2918951"},{"key":"e_1_3_3_3_102_1","first-page":"27319","article-title":"Dynamic resolution network","volume":"34","author":"Zhu Mingjian","year":"2021","unstructured":"Mingjian Zhu, Kai Han, Enhua Wu, Qiulin Zhang, Ying Nie, Zhenzhong Lan, and Yunhe Wang. 2021. Dynamic resolution network. Advances in Neural Information Processing Systems 34 (2021), 27319\u201327330. arXiv:2106.02898","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642628","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:11Z","timestamp":1750290251000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":102,"alternative-id":["10.1145\/3613904.3642628","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642628","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}