{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T16:53:33Z","timestamp":1776704013125,"version":"3.51.2"},"reference-count":104,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"8","funder":[{"DOI":"10.13039\/501100003693","name":"Korea Institute of Science and Technology","doi-asserted-by":"publisher","award":["2E33811-25-077"],"award-info":[{"award-number":["2E33811-25-077"]}],"id":[{"id":"10.13039\/501100003693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2022-NR069243"],"award-info":[{"award-number":["RS-2022-NR069243"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-00557748"],"award-info":[{"award-number":["RS-2025-00557748"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS2023-00220077"],"award-info":[{"award-number":["RS2023-00220077"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00451891"],"award-info":[{"award-number":["RS-2024-00451891"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00439520"],"award-info":[{"award-number":["RS-2024-00439520"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00407271"],"award-info":[{"award-number":["RS-2024-00407271"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00451891"],"award-info":[{"award-number":["RS-2024-00451891"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-00520264"],"award-info":[{"award-number":["RS-2025-00520264"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Adv."],"published-print":{"date-parts":[[2026,2,20]]},"abstract":"<jats:p>\n                    The ability of multitasking (MT) learning in neuro-inspired artificial intelligence (AI) systems offers promise for energy-efficient deployment in robotics, health care, and autonomous vehicles. Here, an MT learning framework is established using a dual-output electroluminescent synaptic device array based on a mixed-dimensional stacked configuration with Cs\n                    <jats:sub>\n                      1\u2212\n                      <jats:italic toggle=\"yes\">x<\/jats:italic>\n                    <\/jats:sub>\n                    FA\n                    <jats:italic toggle=\"yes\">\n                      <jats:sub>x<\/jats:sub>\n                    <\/jats:italic>\n                    PbBr\n                    <jats:sub>3<\/jats:sub>\n                    (0.00\u00a0\u2264\u00a0\n                    <jats:italic toggle=\"yes\">x<\/jats:italic>\n                    \u00a0\u2264\u00a00.15) quantum dots. The device concurrently processes postsynaptic current (PSC) and postsynaptic electroluminescence (PSEL) signals, demonstrating stable and adjustable long-term plasticity with ~1000 individual states, along with spike rate-dependent plasticity and paired-pulse facilitation. By synthesizing the update behavior of both PSC and PSEL pathways, the MT framework simultaneously executes classification-regression and classification-image reconstruction tasks. This approach achieves computational speed improvements of up to 47.09 and 29.17% while reducing energy consumption by up to 8.2- and 32.4-fold compared to a combined single-tasking framework and graphics processing unit\u2013based hardware accelerators, respectively. This innovative method emphasizes the potential of dual-output electroluminescent artificial synapse for MT learning applications.\n                  <\/jats:p>","DOI":"10.1126\/sciadv.ady8518","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:58:58Z","timestamp":1771613938000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Electroluminescent perovskite QD\u2013based neural networks for energy-efficient and accelerate multitasking learning"],"prefix":"10.1126","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5816-1988","authenticated-orcid":true,"given":"Young Ran","family":"Park","sequence":"first","affiliation":[{"name":"KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6059-0530","authenticated-orcid":true,"given":"Gunuk","family":"Wang","sequence":"additional","affiliation":[{"name":"KU-KIST Graduate School of Converging Science and Technology, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea."},{"name":"Department of Integrative Energy Engineering, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea."},{"name":"Post-Silicon Semiconductor Institute, Korea Institute of Science and Technology, Seoul 02792, Republic of Korea."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature03010"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/nn826"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1209236"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-014-0713-3"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_01435"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci12111592"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adp2356"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-024-01277-y"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3329937"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2948"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-024-00751-z"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3410306"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCASAI.2024.3453809"},{"key":"e_1_3_2_15_2","unstructured":"H.-A. Rashid A. Sarkar A. Gangopadhyay M. Rahnemoonfar T. Mohsenin TinyVQA: Compact multimodal deep neural network for visual question answering on resource-constrained devices. arXiv:2404.03574 [cs.CV] (2024)."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2022.3215718"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3138092"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2021.3089132"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2020.3027760"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"R. Kubendran W. Wan S. Joshi H.-S. P. Wong G. Cauwenberghs \u201cA 1.52 pJ\/spike reconfigurable multimodal integrate-and-fire neuron array transceiver \u201d in International Conference on Neuromorphic Systems 2020 (Association for Computing Machinery 2020) pp. 1\u20134.","DOI":"10.1145\/3407197.3407209"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2019.2945114"},{"key":"e_1_3_2_22_2","unstructured":"H. Jiang H. Ard\u00f6 V. \u00d6wall \u201cHardware accelerator design for video segmentation with multi-modal background modelling \u201d in 2005 IEEE International Symposium on Circuits and Systems (ISCAS) (IEEE 2005) pp. 1142\u20131145."},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3716872","article-title":"Dynamic power management through multi-agent deep reinforcement learning for heterogeneous systems","volume":"22","author":"Wang Y.","year":"2025","unstructured":"Y. Wang, W. Zhang, M. Hao, W. Kong, Y. Wen, Dynamic power management through multi-agent deep reinforcement learning for heterogeneous systems. ACM Trans. Archit. Code Optim. 22, 1\u201323 (2025).","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"S. Wiggins Y. Meng M. A. Iyer V. Prasanna \u201cA heterogeneous acceleration system for attention-based multi-agent reinforcement learning \u201d in 2024 34th International Conference on Field-Programmable Logic and Applications (FPL) (IEEE 2024) pp. 236\u2013242.","DOI":"10.1109\/FPL64840.2024.00040"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi7566"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3291048"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831228"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-6526(07)03024-6"},{"key":"e_1_3_2_29_2","unstructured":"J. Ferber G. Weiss Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence (Addison-Wesley Reading 1999) vol. 1."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-51641-x"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.107749"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aax8177"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3064352"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-1942-4"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"J. Kim J. Kim Y. Park \u201cNavigator: Dynamic multi-kernel scheduling to improve GPU performance \u201d in 2020 57th ACM\/IEEE Design Automation Conference (DAC) (IEEE 2020) pp. 1\u20136.","DOI":"10.1109\/DAC18072.2020.9218711"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-018-0092-2"},{"key":"e_1_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Y. Zhu A. Samajdar M. Mattina P. Whatmough Euphrates: Algorithm-SoC co-design for low-power mobile continuous vision. arXiv:1803.11232 [cs.CV] (2018).","DOI":"10.1109\/ISCA.2018.00052"},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"D. Strigl K. Kofler S. Podlipnig \u201cPerformance and scalability of GPU-based convolutional neural networks \u201d in 2010 18th Euromicro International Conference on Parallel Distributed and Network-Based Processing (PDP) (IEEE 2010) pp. 317\u2013324.","DOI":"10.1109\/PDP.2010.43"},{"key":"e_1_3_2_39_2","doi-asserted-by":"crossref","unstructured":"M. Horowitz \u201c1.1 Computing's energy problem (and what we can do about it) \u201d in 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC) (IEEE 2014) pp. 10\u201314.","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-86785-3"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-68541-1"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-36583-0"},{"key":"e_1_3_2_43_2","first-page":"3614","article-title":"Multi-task learning for dense prediction tasks: A survey","volume":"44","author":"Vandenhende S.","year":"2022","unstructured":"S. Vandenhende, S. Georgoulis, W. Van Gansbeke, M. Proesmans, D. X. Dai, L. Van Gool, Multi-task learning for dense prediction tasks: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3614\u20133633 (2022).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Q. Zheng J. Deng Z. Zhu Y. Li S. Zafeiriou \u201cDecoupled multi-task learning with cyclical self-regulation for face parsing \u201d in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2022) pp. 4146\u20134155.","DOI":"10.1109\/CVPR52688.2022.00412"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104037"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adk1525"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2024.109435"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adp0174"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adh9889"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05759-5"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nanoen.2018.10.018"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202409933"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.201806646"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.1c01482"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.2c02995"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202305857"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-47641-6"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-46246-3"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202315584"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.matt.2024.06.050"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1021\/acs.nanolett.4c04444"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41377-024-01516-z"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202307971"},{"key":"e_1_3_2_65_2","unstructured":"Z. F. Zhang Y. Song H. R. Qi \u201cUTKFace Dataset \u201d GitHub Repository 01 April 2024; https:\/\/susanqq.github.io\/UTKFace\/."},{"key":"e_1_3_2_66_2","doi-asserted-by":"crossref","unstructured":"Z. Zhang Y. Song H. Qi \u201cAge progression\/regression by conditional adversarial autoencoder \u201d in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2017) pp. 4352\u20134360.","DOI":"10.1109\/CVPR.2017.463"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-71666-8"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1039\/D0TC05514J"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1002\/jsid.2012"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.3390\/mi16020207"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1364\/OL.555035"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41377-024-01639-3"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1002\/admt.202200632"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202000115"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1049\/cds2.12141"},{"key":"e_1_3_2_76_2","unstructured":"Micron \u201cGraphics memory - GDDR6X \u201d Micron Technology 01 July 2024; www.micron.com\/products\/memory\/graphics-memory\/gddr6x."},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"e_1_3_2_78_2","first-page":"1","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han S.","year":"2015","unstructured":"S. Han, J. Pool, J. Tran, W. Dally, Learning both weights and connections for efficient neural network. Adv. Neural Inf. Process. Syst. 28, 1\u20139 (2015).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.orgel.2014.12.030"},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25016-5"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1039\/C5EE01265A"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201805454"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.physiol.64.092501.114547"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2859757"},{"key":"e_1_3_2_85_2","doi-asserted-by":"crossref","unstructured":"A. Shafiee A. Nag N. Muralimanohar R. Balasubramonian J. P. Strachan M. Hu R. S. Williams V. Srikumar \u201cISAAC: A convolutional neural network accelerator with in-situ analog arithmetic in crossbars \u201d in 2016 ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) (ACM 2016) pp. 14\u201326.","DOI":"10.1109\/ISCA.2016.12"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2003.813296"},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1364\/OE.389889"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2885531"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1364\/OE.478852"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2023.3291704"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2015.2494060"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41566-025-01633-0"},{"key":"e_1_3_2_93_2","doi-asserted-by":"crossref","unstructured":"Y. Liu N. Qi X. Xu W. Li L. Wang M. Chen Q. Cheng J. Shi L. Liu J. Liu X. Xiao N. Wu \u201cA 50Gb\/s PAM-4 optical receiver with Si-photonic PD and linear TIA in 40nm CMOS \u201d in 2020 IEEE International Symposium on Circuits and Systems (ISCAS) (IEEE 2020) pp. 1\u20134.","DOI":"10.1109\/ISCAS45731.2020.9180413"},{"key":"e_1_3_2_94_2","doi-asserted-by":"crossref","unstructured":"D. Wu D. Wang D. Chen J. Yan Z. Dang J. Feng S. Chen P. Feng H. Zhang Y. Fu L. Wang X. Hu X. Xiao \u201cA 128 Gbit\/s 3D-integrated silicon photonics receiver with 1.5 pJ\/bit power consumption \u201d in 2022 Asia Communications and Photonics Conference (ACP) (IEEE 2022) pp. 1509\u20131513.","DOI":"10.1109\/ACP55869.2022.10088619"},{"key":"e_1_3_2_95_2","unstructured":"Texas Instruments \u201cAnalog front-end reference design for imaging using time-interleaved SAR ADCs with 73-dB SNR 7.5 MSPS \u201d Texas Instruments 05 July 2025; www.ti.com\/lit\/pdf\/tidud58."},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad1818"},{"key":"e_1_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1021\/nl0342491"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.915114"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510413"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018966222807"},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(93)80052-J"},{"key":"e_1_3_2_102_2","doi-asserted-by":"crossref","unstructured":"O. Zavalnyi G. Zhao Y. Savchenko W. Xiao \u201cExperimental evaluation of metaheuristic optimization of gradients as an alternative to backpropagation \u201d in 2018 IEEE 4th International Conference on Computer and Communications (ICCC) (IEEE 2018) pp. 2095\u20132099.","DOI":"10.1109\/CompComm.2018.8780709"},{"key":"e_1_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1021\/acsaelm.2c00663"},{"key":"e_1_3_2_104_2","unstructured":"T. Standley A. Zamir D. Chen L. Guibas J. Malik S. Savarese \u201cWhich tasks should be learned together in multi-task learning? \u201d in Proceedings of the 37th International Conference on Machine Learning (PMLR 2020) vol. 119 pp. 9120\u20139132."},{"key":"e_1_3_2_105_2","doi-asserted-by":"crossref","unstructured":"S. Verma V. Chen D. Mei \u201cAn audio-centric multi-task learning framework for streaming ads targeting on Spotify \u201d in Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (Association for Computing Machinery 2025) pp. 4945\u20134955.","DOI":"10.1145\/3711896.3737190"}],"container-title":["Science Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/sciadv.ady8518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T16:02:50Z","timestamp":1776700970000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/sciadv.ady8518"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,20]]},"references-count":104,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,2,20]]}},"alternative-id":["10.1126\/sciadv.ady8518"],"URL":"https:\/\/doi.org\/10.1126\/sciadv.ady8518","relation":{},"ISSN":["2375-2548"],"issn-type":[{"value":"2375-2548","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,20]]},"assertion":[{"value":"2025-05-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eady8518"}}