{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:32:49Z","timestamp":1779334369950,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"CoCoSys, one of seven centers in JUMP 2"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcad.2024.3445263","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T17:22:17Z","timestamp":1723828937000},"page":"4081-4092","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Batched Inference in Conditional Neural Networks"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-5478","authenticated-orcid":false,"given":"Surya","family":"Selvam","sequence":"first","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2847-4721","authenticated-orcid":false,"given":"Amrit","family":"Nagarajan","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Raghunathan","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref7","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref8","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref10","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref11","volume-title":"Siri","year":"2024"},{"key":"ref12","volume-title":"ChatGPT.","year":"2022"},{"key":"ref13","volume-title":"Google translate.","year":"2024"},{"key":"ref14","volume-title":"DeepL translator.","year":"2024"},{"key":"ref15","volume-title":"Google photos","year":"2024"},{"key":"ref16","volume-title":"Recognizing text in images","year":"2024"},{"key":"ref17","volume-title":"Voice Consumer Index","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3372882"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CODESISSS.2015.7331375"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00919"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3246792"},{"key":"ref29","first-page":"1886","article-title":"Channel gating neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hua"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00939"},{"key":"ref31","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","author":"He","year":"2020","journal-title":"arXiv:2006.03654"},{"key":"ref32","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv:1701.06538"},{"key":"ref33","first-page":"8080","article-title":"Hydranets: Specialized dynamic architectures for efficient inference","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Mullapudi"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58285-2_3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3056031"},{"key":"ref37","first-page":"1","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"},{"key":"ref39","first-page":"17456","article-title":"Confident adaptive language modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuster"},{"key":"ref40","first-page":"18330","article-title":"BERT loses patience: Fast and robust inference with early exit","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3256796"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref45","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref46","article-title":"Early-exit convolutional neural networks","author":"Demir","year":"2019"},{"key":"ref47","first-page":"493","article-title":"LazyBatching: An SLA-aware Batching system for cloud machine learning inference","volume-title":"Proc. IEEE Int. Symp. High-Perform. Comput. Archit. (HPCA)","author":"Choi"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097075"},{"key":"ref49","article-title":"Fluid Batching: Exit-aware preemptive serving of early-exit neural networks on edge NPUs","author":"Kouris","year":"2022","journal-title":"arXiv:2209.13443"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480095"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26042"},{"key":"ref52","first-page":"14","article-title":"ACRoBat: Optimizing auto-batching of dynamic deep learning at compile time","volume-title":"Proc. Mach. Learn. Syst.","author":"Fegade"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/43\/10745760\/10638141-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/10745760\/10638141.pdf?arnumber=10638141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:28:04Z","timestamp":1732667284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10638141\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3445263","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}