{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T03:58:27Z","timestamp":1775015907020,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["Lamarr Institute"],"award-info":[{"award-number":["Lamarr Institute"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["6GEM"],"award-info":[{"award-number":["6GEM"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["Lamarr Institute"],"award-info":[{"award-number":["Lamarr Institute"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100016378","name":"Technische Universit\u00e4t Dortmund","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100016378","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Real-Time Syst"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>We propose two complementary research directions, \u201cTime for ML\u201d and \u201cML for Time\u201d, that we believe to be critical for the deployment of machine-learning (ML) applications in time-sensitive applications. \u201cTime for ML\u201d refers to ML systems that are aware of and can adapt to dynamic time constraints regarding their execution, while \u201cML for Time\u201d refers to ML systems that are aware of and can deal with data\u2019s temporal aspects, such as misalignment. We believe these two directions are complementary and can be combined to provide more robust and reliable machine learning systems.<\/jats:p>","DOI":"10.1007\/s11241-025-09449-5","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:37:57Z","timestamp":1750235877000},"page":"311-319","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Timely ML"],"prefix":"10.1007","volume":"61","author":[{"given":"Daniel","family":"Kuhse","sequence":"first","affiliation":[]},{"given":"Harun","family":"Teper","sequence":"additional","affiliation":[]},{"given":"Christian","family":"Hakert","sequence":"additional","affiliation":[]},{"given":"Jian-Jia","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"9449_CR1","volume-title":"Classification and regression trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman J, Olshen RA, Stone CJ (1984) Classification and regression trees. CRC Press, Boca Raton"},{"key":"9449_CR2","unstructured":"Cai H, Gan C, Wang T, Zhang Z, Han S (2019) Once-for-all: Train one network and specialize it for efficient deployment. Preprint at arXiv:1908.09791"},{"key":"9449_CR3","doi-asserted-by":"crossref","unstructured":"Coulom R (2006) Efficient selectivity and backup operators in Monte\u2013Carlo tree search. In: International Conference on Computers and Games, pp. 72\u201383 . Springer","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"9449_CR4","doi-asserted-by":"crossref","unstructured":"Davare A, Zhu Q, Di\u00a0Natale M, Pinello C, Kanajan S, Sangiovanni-Vincentelli A (2007) Period optimization for hard real-time distributed automotive systems. In: Proceedings of the 44th Annual Design Automation Conference. DAC \u201907, pp. 278\u2013283. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/1278480.1278553"},{"key":"9449_CR5","doi-asserted-by":"crossref","unstructured":"Elhoushi M, Shrivastava A, Liskovich D, Hosmer B, Wasti B, Lai L, Mahmoud A, Acun B, Agarwal S, Roman A, et al.: Layer skip: enabling early exit inference and self-speculative decoding. Preprint at arXiv:2404.16710 (2024)","DOI":"10.18653\/v1\/2024.acl-long.681"},{"key":"9449_CR6","unstructured":"Feiertag N, Richter K, Nordlander JE, J\u00f6nsson J.\u00c5.: A Compositional Framework for End-to-End Path Delay Calculation of Automotive Systems under Different Path Semantics. In: IEEE Real-Time Systems Symposium (2008)"},{"key":"9449_CR7","unstructured":"Geifman Y, El-Yaniv R (2019) Selectivenet: A deep neural network with an integrated reject option. In: International Conference on Machine Learning, pp. 2151\u20132159 . PMLR"},{"key":"9449_CR8","doi-asserted-by":"crossref","unstructured":"G\u00fcnzel M, Teper H, Br\u00fcggen Gvd, Chen J-J(2024) End-to-end latency of cause-effect chains: a tutorial. ACM Trans Embed Comput Syst 24(1)","DOI":"10.1145\/3703630"},{"key":"9449_CR9","doi-asserted-by":"crossref","unstructured":"Heo S, Cho S, Kim Y, Kim H (2020) Real-time object detection system with multi-path neural networks. In: 2020 IEEE real-time and embedded technology and applications symposium (RTAS), pp. 174\u2013187 . IEEE","DOI":"10.1109\/RTAS48715.2020.000-8"},{"issue":"11","key":"9449_CR10","doi-asserted-by":"publisher","first-page":"7436","DOI":"10.1109\/TPAMI.2021.3117837","volume":"44","author":"Y Han","year":"2021","unstructured":"Han Y, Huang G, Song S, Yang L, Wang H, Wang Y (2021) Dynamic neural networks: a survey. IEEE Trans Pattern Anal Mach Intell 44(11):7436\u20137456","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9449_CR11","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. Preprint at arXiv:1510.00149"},{"key":"9449_CR12","doi-asserted-by":"crossref","unstructured":"Huang G, Sun Y, Liu Z, Sedra D, Weinberger KQ (2016) Deep networks with stochastic depth. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, Proceedings, Part IV 14, pp. 646\u2013661 (2016). Springer","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"9449_CR13","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. Preprint at arXiv:1503.02531"},{"key":"9449_CR14","doi-asserted-by":"crossref","unstructured":"Jacob B, Kligys S, Chen B, Zhu M, Tang M, Howard A, Adam H, Kalenichenko D (2018) Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713","DOI":"10.1109\/CVPR.2018.00286"},{"issue":"5","key":"9449_CR15","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1093\/comjnl\/29.5.390","volume":"29","author":"M Joseph","year":"1986","unstructured":"Joseph M, Pandya P (1986) Finding response times in a real-time system. Comput J 29(5):390\u2013395","journal-title":"Comput J"},{"key":"9449_CR16","doi-asserted-by":"crossref","unstructured":"Kang W, Chung S, Kim JY, Lee Y, Lee K, Lee J, Shin KG, Chwa HS (2022) DNN-SAM: Split-and-merge DNN execution for real-time object detection. In: 2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium (RTAS), pp. 160\u2013172 . IEEE","DOI":"10.1109\/RTAS54340.2022.00021"},{"key":"9449_CR17","doi-asserted-by":"crossref","unstructured":"Kuhse D, Holscher N, Gunzel M, Teper H, Von Der\u00a0Bruggen G, Chen J-J, Lin C-C (2024).Sync or Sink? The Robustness of Sensor Fusion Against Temporal Misalignment. In: 2024 IEEE 30th Real-Time and Embedded Technology and Applications Symposium (RTAS), pp. 122\u2013134 . IEEE","DOI":"10.1109\/RTAS61025.2024.00018"},{"key":"9449_CR18","unstructured":"Kuhse D, Teper H, Buschj\u00e4ger S, Wang C-Y, Chen J-J (2025) You Only Look Once at Anytime (AnytimeYOLO): Analysis and Optimization of Early-Exits for Object-Detection. Preprint at arXiv:2503.17497"},{"key":"9449_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Fu X, Wigness M, David P, Yao S, Sha L, Abdelzaher T (2022) Self-cueing real-time attention scheduling in criticality-aware visual machine perception. In: 2022 IEEE 28th Real-Time and Embedded Technology and Applications Symposium (RTAS), pp. 173\u2013186 . IEEE","DOI":"10.1109\/RTAS54340.2022.00022"},{"key":"9449_CR20","unstructured":"Likhachev M, Gordon GJ, Thrun S (2003) ARA*: Anytime A* with provable bounds on sub-optimality. Adv Neural Inform Process Syst 16"},{"key":"9449_CR21","doi-asserted-by":"crossref","unstructured":"Laskaridis S, Kouris A, Lane ND (2021) Adaptive inference through early-exit networks: Design, challenges and directions. In: Proceedings of the 5th International Workshop on Embedded and Mobile Deep Learning, pp. 1\u20136","DOI":"10.1145\/3469116.3470012"},{"key":"9449_CR22","doi-asserted-by":"crossref","unstructured":"Lehoczky J, Sha L, Ding Y (1989) The rate monotonic scheduling algorithm: exact characterization and average case behavior. In: [1989] Proceedings. Real-Time Systems Symposium, pp. 166\u2013171","DOI":"10.1109\/REAL.1989.63567"},{"key":"9449_CR23","doi-asserted-by":"crossref","unstructured":"Liu S, Yao S, Fu X, Tabish R, Yu S, Bansal A, Yun H, Sha L, Abdelzaher T (2020) On removing algorithmic priority inversion from mission-critical machine inference pipelines. In: 2020 IEEE Real-Time Systems Symposium (RTSS), pp. 319\u2013332 . IEEE","DOI":"10.1109\/RTSS49844.2020.00037"},{"issue":"8","key":"9449_CR24","first-page":"1770","volume":"71","author":"S Liu","year":"2021","unstructured":"Liu S, Yao S, Fu X, Shao H, Tabish R, Yu S, Bansal A, Yun H, Sha L, Abdelzaher T (2021) Real-time task scheduling for machine perception in intelligent cyber-physical systems. IEEE Trans Comput 71(8):1770\u20131783","journal-title":"IEEE Trans Comput"},{"key":"9449_CR25","doi-asserted-by":"crossref","unstructured":"Rastegari M, Ordonez V, Redmon J, Farhadi A (2016) Xnor-net: Imagenet classification using binary convolutional neural networks. In: European Conference on Computer Vision, pp. 525\u2013542 . Springer","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"9449_CR26","doi-asserted-by":"crossref","unstructured":"Soyyigit A, Yao S, Yun H (2022) Anytime-Lidar: Deadline-aware 3D object detection. In: 2022 IEEE 28th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), pp. 31\u201340 . IEEE","DOI":"10.1109\/RTCSA55878.2022.00010"},{"issue":"11","key":"9449_CR27","doi-asserted-by":"publisher","first-page":"4045","DOI":"10.1109\/TCAD.2024.3443774","volume":"43","author":"A Soyyigit","year":"2024","unstructured":"Soyyigit A, Yao S, Yun H (2024) VALO: a versatile anytime framework for LiDAR-based object detection deep neural networks. IEEE Trans Comput Aided Des Integr Circuits Syst 43(11):4045\u20134056","journal-title":"IEEE Trans Comput Aided Des Integr Circuits Syst"},{"key":"9449_CR28","doi-asserted-by":"crossref","unstructured":"Teerapittayanon S, McDanel B, Kung H-T(2016) Branchynet: Fast inference via early exiting from deep neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 2464\u20132469 . IEEE","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"9449_CR29","doi-asserted-by":"crossref","unstructured":"Wu Z, Nagarajan T, Kumar A, Rennie S, Davis LS, Grauman K, Feris R (2018) Blockdrop: Dynamic inference paths in residual networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8817\u20138826","DOI":"10.1109\/CVPR.2018.00919"},{"key":"9449_CR30","doi-asserted-by":"crossref","unstructured":"Wang X, Yu F, Dou Z-Y, Darrell T, Gonzalez JE (2018) Skipnet: Learning dynamic routing in convolutional networks. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 409\u2013424","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"9449_CR31","doi-asserted-by":"crossref","unstructured":"Yao S, Hao Y, Zhao Y, Shao H, Liu D, Liu S, Wang T, Li J, Abdelzaher T (2020) Scheduling real-time deep learning services as imprecise computations. In: 2020 IEEE 26th International Conference on Embedded and Real-time Computing Systems and Applications (RTCSA), pp. 1\u201310 . IEEE","DOI":"10.1109\/RTCSA50079.2020.9203676"},{"issue":"3","key":"9449_CR32","first-page":"73","volume":"17","author":"S Zilberstein","year":"1996","unstructured":"Zilberstein S (1996) Using anytime algorithms in intelligent systems. AI Mag 17(3):73\u201373","journal-title":"AI Mag"}],"container-title":["Real-Time Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11241-025-09449-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11241-025-09449-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11241-025-09449-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T20:35:28Z","timestamp":1757190928000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11241-025-09449-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["9449"],"URL":"https:\/\/doi.org\/10.1007\/s11241-025-09449-5","relation":{},"ISSN":["0922-6443","1573-1383"],"issn-type":[{"value":"0922-6443","type":"print"},{"value":"1573-1383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"20 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}