{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T10:37:04Z","timestamp":1785926224895,"version":"3.56.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"8058","license":[{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T00:00:00Z","timestamp":1744156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2025,4,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The complexity of neural circuits makes it challenging to decipher the brain\u2019s algorithms of intelligence. Recent breakthroughs in deep learning have produced models that accurately simulate brain activity, enhancing our understanding of the brain\u2019s computational objectives and neural coding. However, it is difficult for such models to generalize beyond their training distribution, limiting their utility. The emergence of foundation models\n                    <jats:sup>1<\/jats:sup>\n                    trained on vast datasets has introduced a new artificial intelligence paradigm with remarkable generalization capabilities. Here we collected large amounts of neural activity from visual cortices of multiple mice and trained a foundation model to accurately predict neuronal responses to arbitrary natural videos. This model generalized to new mice with minimal training and successfully predicted responses across various new stimulus domains, such as coherent motion and noise patterns. Beyond neural response prediction, the model also accurately predicted anatomical cell types, dendritic features and neuronal connectivity within the MICrONS functional connectomics dataset\n                    <jats:sup>2<\/jats:sup>\n                    . Our work is a crucial step towards building foundation models of the brain. As neuroscience accumulates larger, multimodal datasets, foundation models will reveal statistical regularities, enable rapid adaptation to new tasks and accelerate research.\n                  <\/jats:p>","DOI":"10.1038\/s41586-025-08829-y","type":"journal-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T11:04:00Z","timestamp":1744196640000},"page":"470-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":77,"title":["Foundation model of neural activity predicts response to new stimulus types"],"prefix":"10.1038","volume":"640","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1084-7059","authenticated-orcid":false,"given":"Eric Y.","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul G.","family":"Fahey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8610-5182","authenticated-orcid":false,"given":"Zhuokun","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stelios","family":"Papadopoulos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kayla","family":"Ponder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0993-7145","authenticated-orcid":false,"given":"Marissa A.","family":"Weis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andersen","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taliah","family":"Muhammad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saumil","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dat","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiakun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-3853","authenticated-orcid":false,"given":"Casey M.","family":"Schneider-Mizell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"MICrONS Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuno Ma\u00e7arico","family":"da Costa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8697-6797","authenticated-orcid":false,"given":"R. Clay","family":"Reid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0280-7022","authenticated-orcid":false,"given":"Forrest","family":"Collman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2001-4568","authenticated-orcid":false,"given":"Nuno Ma\u00e7arico","family":"da Costa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katrin","family":"Franke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2392-5105","authenticated-orcid":false,"given":"Alexander S.","family":"Ecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4364-8846","authenticated-orcid":false,"given":"Jacob","family":"Reimer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6376-329X","authenticated-orcid":false,"given":"Xaq","family":"Pitkow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabian H.","family":"Sinz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4305-6376","authenticated-orcid":false,"given":"Andreas S.","family":"Tolias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"8829_CR1","doi-asserted-by":"publisher","unstructured":"Bommasani, R. et al. On the opportunities and risks of foundation models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2108.07258 (2021).","DOI":"10.48550\/arXiv.2108.07258"},{"key":"8829_CR2","doi-asserted-by":"publisher","unstructured":"The MICrONS Consortium. Functional connectomics spanning multiple areas of mouse visual cortex. Nature https:\/\/doi.org\/10.1038\/s41586-025-08790-w (2025).","DOI":"10.1038\/s41586-025-08790-w"},{"key":"8829_CR3","doi-asserted-by":"publisher","first-page":"e1003963","DOI":"10.1371\/journal.pcbi.1003963","volume":"10","author":"CF Cadieu","year":"2014","unstructured":"Cadieu, C. F. et al. Deep neural networks rival the representation of primate IT cortex for core visual object recognition. PLoS Comput. Biol. 10, e1003963 (2014).","journal-title":"PLoS Comput. Biol."},{"key":"8829_CR4","unstructured":"Batty, E. et al. Multilayer network models of primate retinal ganglion cells. In Proc. 5th International Conference for Learning Representations (ICLR, 2017)."},{"key":"8829_CR5","first-page":"1369","volume":"29","author":"LT McIntosh","year":"2016","unstructured":"McIntosh, L. T., Maheswaranathan, N., Nayebi, A., Ganguli, S. & Baccus, S. A. Deep learning models of the retinal response to natural scenes. Adv. Neural Inf. Process. Syst. 29, 1369\u20131377 (2016).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8829_CR6","unstructured":"Klindt, D. A., Ecker, A. S., Euler, T. & Bethge, M. Neural system identification for large populations separating what and where. In Proc. 31st International Conference on Neural Information Processing Systems 3509\u20133519 (ACM, 2017)."},{"key":"8829_CR7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1167\/19.4.29","volume":"19","author":"WF Kindel","year":"2019","unstructured":"Kindel, W. F., Christensen, E. D. & Zylberberg, J. Using deep learning to probe the neural code for images in primary visual cortex. JOV 19, 29 (2019).","journal-title":"JOV"},{"key":"8829_CR8","doi-asserted-by":"publisher","first-page":"e1006897","DOI":"10.1371\/journal.pcbi.1006897","volume":"15","author":"SA Cadena","year":"2019","unstructured":"Cadena, S. A. et al. Deep convolutional models improve predictions of macaque v1 responses to natural images. PLoS Computat. Biol. 15, e1006897 (2019).","journal-title":"PLoS Computat. Biol."},{"key":"8829_CR9","first-page":"15801","volume":"34","author":"M Bashiri","year":"2021","unstructured":"Bashiri, M. et al. A flow-based latent state generative model of neural population responses to natural images. Adv. Neural Inf. Process. Syst. 34, 15801\u201315815 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8829_CR10","doi-asserted-by":"publisher","first-page":"8619","DOI":"10.1073\/pnas.1403112111","volume":"111","author":"DLK Yamins","year":"2014","unstructured":"Yamins, D. L. K. et al. Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proc. Natl Acad. Sci. USA 111, 8619\u20138624 (2014).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"8829_CR11","first-page":"25164","volume":"34","author":"S Bakhtiari","year":"2021","unstructured":"Bakhtiari, S., Mineault, P., Lillicrap, T., Pack, C. & Richards, B. The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning. Adv. Neural Inf. Process. Syst. 34, 25164\u201325178 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8829_CR12","first-page":"32574","volume":"36","author":"P Pierzchlewicz","year":"2024","unstructured":"Pierzchlewicz, P. et al. Energy guided diffusion for generating neurally exciting images. Adv. Neural Inf. Process. Syst. 36, 32574\u201332601 (2024).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"8829_CR13","doi-asserted-by":"publisher","first-page":"eaav9436","DOI":"10.1126\/science.aav9436","volume":"364","author":"P Bashivan","year":"2019","unstructured":"Bashivan, P., Kar, K. & DiCarlo, J. J. Neural population control via deep image synthesis. Science 364, eaav9436 (2019).","journal-title":"Science"},{"key":"8829_CR14","doi-asserted-by":"publisher","first-page":"999\u20131009.e10","DOI":"10.1016\/j.cell.2019.04.005","volume":"177","author":"CR Ponce","year":"2019","unstructured":"Ponce, C. R. et al. Evolving images for visual neurons using a deep generative network reveals coding principles and neuronal preferences. Cell 177, 999\u20131009.e10 (2019).","journal-title":"Cell"},{"key":"8829_CR15","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1038\/s41586-022-05270-3","volume":"610","author":"K Franke","year":"2022","unstructured":"Franke, K. et al. State-dependent pupil dilation rapidly shifts visual feature selectivity. Nature 610, 128\u2013134 (2022).","journal-title":"Nature"},{"key":"8829_CR16","doi-asserted-by":"publisher","first-page":"2060","DOI":"10.1038\/s41593-019-0517-x","volume":"22","author":"EY Walker","year":"2019","unstructured":"Walker, E. Y. et al. Inception loops discover what excites neurons most using deep predictive models. Nat. Neurosci. 22, 2060\u20132065 (2019).","journal-title":"Nat. Neurosci."},{"key":"8829_CR17","doi-asserted-by":"publisher","unstructured":"Hendrycks, D. & Dietterich, T. G. Benchmarking neural network robustness to common corruptions and perturbations. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1903.12261 (2019).","DOI":"10.48550\/arXiv.1903.12261"},{"key":"8829_CR18","doi-asserted-by":"crossref","unstructured":"Sinz, F. et al. Stimulus domain transfer in recurrent models for large scale cortical population prediction on video. In Proc. 32nd International Conference on Neural Information Processing Systems 7199\u20137210 (ACM, 2018).","DOI":"10.1101\/452672"},{"key":"8829_CR19","doi-asserted-by":"publisher","first-page":"4745","DOI":"10.1523\/JNEUROSCI.12-12-04745.1992","volume":"12","author":"KH Britten","year":"1992","unstructured":"Britten, K. H., Shadlen, M. N., Newsome, W. T. & Movshon, J. A. The analysis of visual motion: a comparison of neuronal and psychophysical performance. J. Neurosci. 12, 4745\u20134765 (1992).","journal-title":"J. Neurosci."},{"key":"8829_CR20","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1038\/346174a0","volume":"346","author":"CD Salzman","year":"1990","unstructured":"Salzman, C. D., Britten, K. H. & Newsome, W. T. Cortical microstimulation influences perceptual judgements of motion direction. Nature 346, 174\u2013177 (1990).","journal-title":"Nature"},{"key":"8829_CR21","doi-asserted-by":"publisher","first-page":"eaaw5202","DOI":"10.1126\/science.aaw5202","volume":"365","author":"JH Marshel","year":"2019","unstructured":"Marshel, J. H. et al. Cortical layer-specific critical dynamics triggering perception. Science 365, eaaw5202 (2019).","journal-title":"Science"},{"key":"8829_CR22","unstructured":"Brown, T. B. et al. Language models are few-shot learners. In Advances in Neural Information Processing Systems (eds. Larochelle, H. et al.) vol. 33, 1877\u20131901 (Curran Associates, 2020)."},{"key":"8829_CR23","unstructured":"Radford, A. et al. Learning transferable visual models from natural language supervision. In Proc. 38th International Conference on Machine Learning (eds. Meila, M. & Zhang, T.) vol. 139, 8748\u20138763 (PMLR, 2021)."},{"key":"8829_CR24","doi-asserted-by":"publisher","unstructured":"Ding, Z. et al. Functional connectomics reveals general wiring rule in mouse visual cortex. Nature https:\/\/doi.org\/10.1038\/s41586-025-08840-3 (2025).","DOI":"10.1038\/s41586-025-08840-3"},{"key":"8829_CR25","unstructured":"Weis, M. A. et al. An unsupervised map of excitatory neurons\u2019 dendritic morphology in the mouse visual cortex. Nat. Commun. (in the press)."},{"key":"8829_CR26","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.neuron.2014.09.033","volume":"84","author":"J Reimer","year":"2014","unstructured":"Reimer, J. et al. Pupil fluctuations track fast switching of cortical states during quiet wakefulness. Neuron 84, 355\u2013362 (2014).","journal-title":"Neuron"},{"key":"8829_CR27","doi-asserted-by":"publisher","first-page":"10","DOI":"10.3389\/fncom.2016.00010","volume":"10","author":"O Schoppe","year":"2016","unstructured":"Schoppe, O., Harper, N. S., Willmore, B. D. B., King, A. J. & Schnupp, J. W. H. Measuring the performance of neural models. Front. Comput. Neurosci. 10, 10 (2016).","journal-title":"Front. Comput. Neurosci."},{"key":"8829_CR28","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41586-020-03171-x","volume":"592","author":"JH Siegle","year":"2021","unstructured":"Siegle, J. H. et al. Survey of spiking in the mouse visual system reveals functional hierarchy. Nature 592, 86\u201392 (2021).","journal-title":"Nature"},{"key":"8829_CR29","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1038\/s41593-021-00914-5","volume":"24","author":"PM Goltstein","year":"2021","unstructured":"Goltstein, P. M., Reinert, S., Bonhoeffer, T. & H\u00fcbener, M. Mouse visual cortex areas represent perceptual and semantic features of learned visual categories. Nat. Neurosci. 24, 1441\u20131451 (2021).","journal-title":"Nat. Neurosci."},{"key":"8829_CR30","doi-asserted-by":"publisher","unstructured":"Kaplan, J. et al. Scaling laws for neural language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2001.08361 (2020).","DOI":"10.48550\/arXiv.2001.08361"},{"key":"8829_CR31","doi-asserted-by":"publisher","first-page":"12587","DOI":"10.1523\/JNEUROSCI.1124-14.2014","volume":"34","author":"ME Garrett","year":"2014","unstructured":"Garrett, M. E., Nauhaus, I., Marshel, J. H. & Callaway, E. M. Topography and areal organization of mouse visual cortex. J. Neurosci. 34, 12587\u201312600 (2014).","journal-title":"J. Neurosci."},{"key":"8829_CR32","doi-asserted-by":"publisher","first-page":"e18372","DOI":"10.7554\/eLife.18372","volume":"6","author":"J Zhuang","year":"2017","unstructured":"Zhuang, J. et al. An extended retinotopic map of mouse cortex. eLife 6, e18372 (2017).","journal-title":"eLife"},{"key":"8829_CR33","doi-asserted-by":"publisher","unstructured":"Schneider-Mizell, C. M. et al. Inhibitory specificity from a connectomic census of mouse visual cortex. Nature https:\/\/doi.org\/10.1038\/10.1038\/s41586-024-07780-8 (2025).","DOI":"10.1038\/10.1038\/s41586-024-07780-8"},{"key":"8829_CR34","doi-asserted-by":"crossref","unstructured":"Lurz, K.-K. et al. Generalization in data-driven models of primary visual cortex. In 9th International Conference on Learning Representations (ICLR, 2021).","DOI":"10.1101\/2020.10.05.326256"},{"key":"8829_CR35","unstructured":"Ding, Z. et al. Bipartite invariance in mouse primary visual cortex. Nat. Neurosci. (in the press)."},{"key":"8829_CR36","doi-asserted-by":"publisher","unstructured":"Fu, J. et al. Pattern completion and disruption characterize contextual modulation in mouse visual cortex. Preprint at bioRxiv https:\/\/doi.org\/10.1101\/2023.03.13.532473 (2023).","DOI":"10.1101\/2023.03.13.532473"},{"key":"8829_CR37","first-page":"1014","volume":"83","author":"MJ Lindstrom","year":"1988","unstructured":"Lindstrom, M. J. & Bates, D. M. Newton\u2013Raphson and EM algorithms for linear mixed-effects models for repeated-measures data. J. Am. Stat. Assoc. 83, 1014 (1988).","journal-title":"J. Am. Stat. Assoc."},{"key":"8829_CR38","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1038\/nn.3707","volume":"17","author":"E Froudarakis","year":"2014","unstructured":"Froudarakis, E. et al. Population code in mouse V1 facilitates readout of natural scenes through increased sparseness. Nat. Neurosci. 17, 851\u2013857 (2014).","journal-title":"Nat. Neurosci."},{"key":"8829_CR39","doi-asserted-by":"publisher","first-page":"e14472","DOI":"10.7554\/eLife.14472","volume":"5","author":"NJ Sofroniew","year":"2016","unstructured":"Sofroniew, N. J., Flickinger, D., King, J. & Svoboda, K. A large field of view two-photon mesoscope with subcellular resolution for in vivo imaging. eLife 5, e14472 (2016).","journal-title":"eLife"},{"key":"8829_CR40","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1038\/s41593-018-0209-y","volume":"21","author":"A Mathis","year":"2018","unstructured":"Mathis, A. et al. DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nat. Neurosci. 21, 1281\u20131289 (2018).","journal-title":"Nat. Neurosci."},{"key":"8829_CR41","doi-asserted-by":"publisher","first-page":"e38173","DOI":"10.7554\/eLife.38173","volume":"8","author":"A Giovannucci","year":"2019","unstructured":"Giovannucci, A. et al. CaImAn: an open source tool for scalable calcium imaging data analysis. eLife 8, e38173 (2019).","journal-title":"eLife"},{"key":"8829_CR42","doi-asserted-by":"crossref","unstructured":"Karpathy, A. et al. Large-scale video classification with convolutional neural networks. In 2014 IEEE Conference on Computer Vision and Pattern Recognition 1725\u20131732 (IEEE, 2014).","DOI":"10.1109\/CVPR.2014.223"},{"key":"8829_CR43","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/s00422-007-0182-0","volume":"97","author":"N Petkov","year":"2007","unstructured":"Petkov, N. & Subramanian, E. Motion detection, noise reduction, texture suppression and contour enhancement by spatiotemporal gabor filters with surround inhibition. Biol. Cybernet. 97, 423\u2013439 (2007).","journal-title":"Biol. Cybernet."},{"key":"8829_CR44","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1038\/81860","volume":"3","author":"MC Morrone","year":"2000","unstructured":"Morrone, M. C. et al. A cortical area that responds specifically to optic flow, revealed by fMRI. Nat. Neurosci. 3, 1322\u20131328 (2000).","journal-title":"Nat. Neurosci."},{"key":"8829_CR45","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"8829_CR46","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2261\u20132269 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"8829_CR47","doi-asserted-by":"publisher","unstructured":"Hendrycks, D. & Gimpel, K. Gaussian error linear units (GELUs). Preprint at https:\/\/doi.org\/10.48550\/arXiv.1606.08415 (2020).","DOI":"10.48550\/arXiv.1606.08415"},{"key":"8829_CR48","unstructured":"Shi, X. et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In Advances in Neural Information Processing Systems vol. 28 (eds Cortes, C. et al.) (Curran Associates, 2015)."},{"key":"8829_CR49","unstructured":"Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems (eds. Guyon, I. et al.) vol. 30 (Curran Associates, 2017)."},{"key":"8829_CR50","doi-asserted-by":"crossref","unstructured":"Wu, H. et al. CvT: Introducing convolutions to vision transformers. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) 22\u201331 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"8829_CR51","doi-asserted-by":"publisher","unstructured":"Kingma, D. P. & Welling, M. Auto-encoding variational Bayes. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1312.6114 (2013).","DOI":"10.48550\/arXiv.1312.6114"},{"key":"8829_CR52","first-page":"1139","volume":"28","author":"I Sutskever","year":"2013","unstructured":"Sutskever, I., Martens, J., Dahl, G. & Hinton, G. On the importance of initialization and momentum in deep learning. Proc. Mach. Learn. Res. 28, 1139\u20131147 (2013).","journal-title":"Proc. Mach. Learn. Res."},{"key":"8829_CR53","doi-asserted-by":"publisher","unstructured":"Loshchilov, I. & Hutter, F. SGDR: stochastic gradient descent with warm restarts. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1608.03983 (2016).","DOI":"10.48550\/arXiv.1608.03983"}],"updated-by":[{"DOI":"10.1038\/s41586-026-10457-z","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000}}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-08829-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-08829-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-08829-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T05:40:37Z","timestamp":1775713237000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-025-08829-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,9]]},"references-count":53,"journal-issue":{"issue":"8058","published-print":{"date-parts":[[2025,4,10]]}},"alternative-id":["8829"],"URL":"https:\/\/doi.org\/10.1038\/s41586-025-08829-y","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,9]]},"assertion":[{"value":"24 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2026","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41586-026-10457-z","URL":"https:\/\/doi.org\/10.1038\/s41586-026-10457-z","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.S.T. and J.R.\u00a0are co-founders of DataJoint Inc., in which they have financial interests. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}