{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T08:54:06Z","timestamp":1781513646411,"version":"3.54.1"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Albert-Ludwigs-Universit\u00e4t Freiburg im Breisgau"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Large Language Models (LLMs) exhibit In-Context Learning (ICL), which enables the model to perform new tasks conditioning only on the examples provided in the context without updating the model\u2019s weights. While ICL offers fast adaptation across natural language tasks and domains, its emergence is less straightforward for modalities beyond text. In this work, we systematically uncover properties present in LLMs that support the emergence of ICL for autoregressive models and various modalities by promoting the learning of the mechanisms needed for ICL. We identify exact token repetitions in the training data sequences as an important factor for ICL. Such repetitions further improve stability and reduce transiency in ICL performance. We analyse in detail the training dynamics of such data sequences and explain how token repetitions enhance the ICL learning mechanisms. Moreover, we emphasise the importance of the training task difficulty for the emergence of ICL. Finally, by applying our novel insights on ICL emergence, we unlock ICL capabilities across various visual datasets used for few-shot classification, and confirm the generalisability of our insights to much harder real-world examples of large-scale object classification, and a more challenging EEG classification task. Code is available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/jelenab98\/unlocking_icl\" ext-link-type=\"uri\">https:\/\/github.com\/jelenab98\/unlocking_icl<\/jats:ext-link>\n                  <\/jats:p>","DOI":"10.1007\/s11263-026-02913-0","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T08:10:15Z","timestamp":1781511015000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unlocking In-Context Learning for Natural Datasets Across Modalities"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2835-4168","authenticated-orcid":false,"given":"Jelena","family":"Bratuli\u0107","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudhanshu","family":"Mittal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David T.","family":"Hoffmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"B\u00f6hm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin Tibor","family":"Schirrmeister","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tonio","family":"Ball","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Rupprecht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"2913_CR1","doi-asserted-by":"crossref","unstructured":"Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., Ring, R., Rutherford, E., Cabi, S., Han, T., Gong, Z., Samangooei, S., Monteiro, M., Menick, J., Borgeaud, S., Brock, A., Nematzadeh, A., Sharifzadeh, S., Binkowski, M., Barreira, R., Vinyals, O., Zisserman, A., & Simonyan, K. (2022). Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=EbMuimAbPbs","DOI":"10.52202\/068431-1723"},{"key":"2913_CR2","unstructured":"Aky\u00fcrek, E., Schuurmans, D., Andreas, J., Ma, T., & Zhou, D. (2023). What learning algorithm is in-context learning? investigations with linear models. In: The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=0g0X4H8yN4I"},{"key":"2913_CR3","doi-asserted-by":"crossref","unstructured":"Al-Saegh, A., Dawwd, S., & Abdul-Jabbar, J. (2021). Cutcat: An augmentation method for eeg classification. Neural Networks, 141, https:\/\/doi.org\/10.1016\/j.neunet.2021.05.032","DOI":"10.1016\/j.neunet.2021.05.032"},{"key":"2913_CR4","unstructured":"Agarwal, R., Singh, A., Zhang, L.M., Bohnet, B., Rosias, L., Chan, S.C.Y., Zhang, B., Anand, A., Abbas, Z., Nova, A., Co-Reyes, J.D., Chu, E., Behbahani, F., Faust, A., & Larochelle, H. (2024). Many-shot in-context learning. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=AB6XpMzvqH"},{"key":"2913_CR5","unstructured":"Aky\u00fcrek, E., Wang, B., Kim, Y., & Andreas, J. (2024). Context Language Learning: Architectures and Algorithms"},{"key":"2913_CR6","doi-asserted-by":"crossref","unstructured":"Bai, Y., Chen, F., Wang, H., Xiong, C., & Mei, S. (2023). Transformers as statisticians: Provable in-context learning with in-context algorithm selection. Advances in Neural Information Processing Systems","DOI":"10.52202\/075280-2498"},{"key":"2913_CR7","doi-asserted-by":"crossref","unstructured":"Bar, A., Gandelsman, Y., Darrell, T., Globerson, A., & Efros, A. A. (2022). Visual prompting via image inpainting. Advances in Neural Information Processing Systems","DOI":"10.52202\/068431-1813"},{"key":"2913_CR8","doi-asserted-by":"crossref","unstructured":"Bai, Y., Geng, X., Mangalam, K., Bar, A., Yuille, A. L., Darrell, T., Malik, J., & Efros, A. A. (2024). Sequential modeling enables scalable learning for large vision models. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"2913_CR9","unstructured":"Bertinetto, L., Henriques, J.F., Torr, P., & Vedaldi, A. (2019). Meta-learning with differentiable closed-form solvers. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=HyxnZh0ct7"},{"key":"2913_CR10","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., & Amodei, D. (2020). Language models are few-shot learners. In: Advances in Neural Information Processing Systems"},{"key":"2913_CR11","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., & Manning, C.D. (2019). What does BERT look at? an analysis of BERT\u2019s attention. In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. https:\/\/aclanthology.org\/W19-4828\/","DOI":"10.18653\/v1\/W19-4828"},{"key":"2913_CR12","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014). Describing textures in the wild. Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2014.461"},{"key":"2913_CR13","doi-asserted-by":"publisher","unstructured":"Camaret\u00a0Ndir, T., Reisert, M., & Schirrmeister, R. (2026). Scaling In-Context Segmentation with Hierarchical Supervision. https:\/\/doi.org\/10.48550\/arXiv.2604.12752","DOI":"10.48550\/arXiv.2604.12752"},{"key":"2913_CR14","doi-asserted-by":"crossref","unstructured":"Chan, S., Santoro, A., Lampinen, A., Wang, J., Singh, A., Richemond, P., McClelland, J., & Hill, F. (2022). Data distributional properties drive emergent in-context learning in transformers. In: Advances in Neural Information Processing Systems","DOI":"10.52202\/068431-1371"},{"key":"2913_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhao, C., Yu, Z., McKeown, K., & He, H. (2024). Parallel Structures in Pre-training Data Yield In-Context Learning. arXiv:https:\/\/arxiv.org\/abs\/2402.12530","DOI":"10.18653\/v1\/2024.acl-long.465"},{"key":"2913_CR16","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"11","key":"2913_CR17","doi-asserted-by":"publisher","first-page":"2411","DOI":"10.1109\/TNSRE.2020.3027004","volume":"28","author":"L Duan","year":"2020","unstructured":"Duan, L., Li, J., Ji, H., Pang, Z., Zheng, X., Lu, R., Li, M., & Zhuang, J. (2020). Zero-shot learning for eeg classification in motor imagery-based bci system. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(11), 2411\u20132419.","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"2913_CR18","doi-asserted-by":"crossref","unstructured":"Dai, D., Sun, Y., Dong, L., Hao, Y., Ma, S., Sui, Z., & Wei, F. (2023). Why can GPT learn in-context? language models secretly perform gradient descent as meta-optimizers. Findings of the Association for Computational Linguistics: ACL 2023","DOI":"10.18653\/v1\/2023.findings-acl.247"},{"key":"2913_CR19","doi-asserted-by":"crossref","unstructured":"Elhelo, A., & Geva, M. (2025). Inferring Functionality of Attention Heads from their Parameters. arXiv:https:\/\/arxiv.org\/abs\/2412.11965","DOI":"10.18653\/v1\/2025.acl-long.866"},{"key":"2913_CR20","doi-asserted-by":"crossref","unstructured":"Edelman, E., Tsilivis, N., Edelman, B.L., Malach, E., & Goel, S. (2024). The evolution of statistical induction heads: In-context learning markov chains. In: Advances in Neural Information Processing Systems","DOI":"10.52202\/079017-2050"},{"key":"2913_CR21","unstructured":"Finn, C., Abbeel, P., & Levine, S. (2017). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning"},{"key":"2913_CR22","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Conference on Computer Vision and Pattern Recognition Workshop"},{"key":"2913_CR23","unstructured":"Foundation, W. Wikimedia Downloads. https:\/\/dumps.wikimedia.org"},{"key":"2913_CR24","doi-asserted-by":"publisher","unstructured":"Ferber, D., W\u00f6lflein, G., Wiest, I., Ligero, M., Sainath, S., Laleh, N., Nahhas, O., M\u00fcller-Franzes, G., J\u00e4ger, D., Truhn, D., & Kather, J. (2024). In-context learning enables multimodal large language models to classify cancer pathology images. Nature Communications, 15, https:\/\/doi.org\/10.1038\/s41467-024-51465-9","DOI":"10.1038\/s41467-024-51465-9"},{"issue":"23","key":"2913_CR25","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger, A. L., Amaral, L. A. N., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., Mietus, J. E., Moody, G. B., Peng, C.-K., & Stanley, H. E. (2000). Physiobank, physiotoolkit, and physionet. Circulation, 101(23), 215\u2013220. https:\/\/doi.org\/10.1161\/01.CIR.101.23.e215","journal-title":"Circulation"},{"key":"2913_CR26","unstructured":"Gokaslan, A., Cohen, V., Pavlick, E., & Tellex, S. (2019). OpenWebText Corpus. http:\/\/Skylion007.github.io\/OpenWebTextCorpus"},{"key":"2913_CR27","doi-asserted-by":"crossref","unstructured":"Gu, Y., Dong, L., Wei, F., & Huang, M. (2023). Pre-Training to Learn in Context. arXiv:https:\/\/arxiv.org\/abs\/2305.09137","DOI":"10.18653\/v1\/2023.acl-long.267"},{"key":"2913_CR28","doi-asserted-by":"crossref","unstructured":"Garg, S., Tsipras, D., Liang, P. S., & Valiant, G. (2022). What can transformers learn in-context? a case study of simple function classes. Advances in Neural Information Processing Systems","DOI":"10.52202\/068431-2217"},{"key":"2913_CR29","unstructured":"Huang, B., Mitra, C., Arbelle, A., Karlinsky, L., Darrell, T., & Herzig, R. (2024). Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning. arXiv:https:\/\/arxiv.org\/abs\/2406.15334"},{"key":"2913_CR30","unstructured":"Hollmann, N., M\u00fcller, S., Eggensperger, K., & Hutter, F. (2023). Tabpfn: A transformer that solves small tabular classification problems in a second. International Conference on Learning Representations (p. 2023)"},{"key":"2913_CR31","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08328-6","author":"N Hollmann","year":"2025","unstructured":"Hollmann, N., M\u00fcller, S., Purucker, L., Krishnakumar, A., K\u00f6rfer, M., Hoo, S. B., Schirrmeister, R. T., & Hutter, F. (2025). Accurate predictions on small data with a tabular foundation model. Nature. https:\/\/doi.org\/10.1038\/s41586-024-08328-6","journal-title":"Nature"},{"key":"2913_CR32","doi-asserted-by":"crossref","unstructured":"Han, X., Simig, D., Mihaylov, T., Tsvetkov, Y., Celikyilmaz, A., & Wang, T. (2023). Understanding in-context learning via supportive pretraining data. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","DOI":"10.18653\/v1\/2023.acl-long.708"},{"key":"2913_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2016.90"},{"key":"2913_CR34","unstructured":"Jiang, W.-B., Zhao, L.-M., & Lu, B.-L. (2024). Large brain model for learning generic representations with tremendous eeg data in bci arXiv:2405.18765 arXiv preprint."},{"key":"2913_CR35","unstructured":"Kingma, D. P., Ba, J., & Adam. (2014). A method for stochastic optimization arXiv:1412.6980 arXiv preprint."},{"key":"2913_CR36","unstructured":"Lindsey, J., Gurnee, W., Ameisen, E., Chen, B., Pearce, A., Turner, N.L., Citro, C., Abrahams, D., Carter, S., Hosmer, B., Marcus, J., Sklar, M., Templeton, A., Bricken, T., McDougall, C., Cunningham, H., Henighan, T., Jermyn, A., Jones, A., Persic, A., Qi, Z., Thompson, T.B., Zimmerman, S., Rivoire, K., Conerly, T., Olah, C., & Batson, J. (2025). On the biology of a large language model. Transformer Circuits Thread"},{"key":"2913_CR37","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. International Conference on Learning Representations"},{"key":"2913_CR38","unstructured":"Liu, Y., Ma, Y., Zhou, W., Zhu, G., Zheng, N., & Brainclip. (2023). Bridging brain and visual-linguistic representation via clip for generic natural visual stimulus decoding arXiv:2302.12971 arxiv 2023. arXiv preprint."},{"issue":"6266","key":"2913_CR39","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"BM Lake","year":"2015","unstructured":"Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015). Human-level concept learning through probabilistic program induction. Science, 350(6266), 1332\u20131338.","journal-title":"Science"},{"key":"2913_CR40","unstructured":"Lauren\u00e7on, H., Saulnier, L., Tronchon, L., Bekman, S., Singh, A., Lozhkov, A., Wang, T., Karamcheti, S., Rush, A.M., Kiela, D., Cord, M.,& Sanh, V. (2023). OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents. arXiv:https:\/\/arxiv.org\/abs\/2306.16527"},{"key":"2913_CR41","doi-asserted-by":"crossref","unstructured":"Liu, J., Shen, D., Zhang, Y., Dolan, B., Carin, L., & Chen, W. (2022). What makes good in-context examples for GPT-3? In: Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"2913_CR42","doi-asserted-by":"crossref","unstructured":"Li, L., & Wei, B. (2025). A two-stage eeg zero-shot classification algorithm guided by class reconstruction. Available at SSRN, 5177120.","DOI":"10.2139\/ssrn.5177120"},{"key":"2913_CR43","unstructured":"Levine, Y., Wies, N., Jannai, D., Navon, D., Hoshen, Y., & Shashua, A. (2022). The inductive bias of in-context learning: Rethinking pretraining example design. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=lnEaqbTJIRz"},{"key":"2913_CR44","doi-asserted-by":"crossref","unstructured":"Long, Q., Wang, W., & Pan, S. (2023). Adapt in contexts: Retrieval-augmented domain adaptation via in-context learning. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2023.emnlp-main.402"},{"key":"2913_CR45","unstructured":"Liu, S., Ye, H., Xing, L., & Zou, J. (2024). In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering. arXiv:https:\/\/arxiv.org\/abs\/2311.06668"},{"key":"2913_CR46","doi-asserted-by":"crossref","unstructured":"Min, S., Lewis, M., Zettlemoyer, L., & Hajishirzi, H. (2022). MetaICL: Learning to learn in context. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","DOI":"10.18653\/v1\/2022.naacl-main.201"},{"key":"2913_CR47","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., & Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in Neural Information Processing Systems"},{"key":"2913_CR48","unstructured":"Olsson, C., Elhage, N., Nanda, N., Joseph, N., DasSarma, N., Henighan, T., Mann, B., Askell, A., Bai, Y., Chen, A., Conerly, T., Drain, D., Ganguli, D., Hatfield-Dodds, Z., Hernandez, D., Johnston, S., Jones, A., Kernion, J., Lovitt, L., Ndousse, K., Amodei, D., Brown, T., Clark, J., Kaplan, J., McCandlish, S., & Olah, C. (2022). In-context learning and induction heads. Transformer Circuits Thread. https:\/\/transformer-circuits.pub\/2022\/in-context-learning-and-induction-heads\/index.html"},{"key":"2913_CR49","doi-asserted-by":"crossref","unstructured":"Peng, Y., Hao, C., Yang, X., Peng, J., Hu, X., & Geng, X. (2024). LIVE: Learnable In-Context Vector for Visual Question Answering. arXiv:https:\/\/arxiv.org\/abs\/2406.13185","DOI":"10.52202\/079017-0312"},{"key":"2913_CR50","unstructured":"Pawelczyk, M., Neel, S., & Lakkaraju, H. (2024). In-Context Unlearning: Language Models as Few Shot Unlearners. arXiv:https:\/\/arxiv.org\/abs\/2310.07579"},{"key":"2913_CR51","unstructured":"Patil, S., Schirrmeister, R. T., Hutter, F., & Ball, T. (2024). Coordconformer: Heterogenous EEG datasets decoding using transformers. ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling"},{"key":"2913_CR52","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., & Manning, C. (2014). GloVe: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). https:\/\/aclanthology.org\/D14-1162\/","DOI":"10.3115\/v1\/D14-1162"},{"key":"2913_CR53","doi-asserted-by":"crossref","unstructured":"Press, O., Zhang, M., Min, S., Schmidt, L., Smith, N., & Lewis, M. (2023). Measuring and narrowing the compositionality gap in language models. Findings of the Association for Computational Linguistics: EMNLP 2023","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"2913_CR54","unstructured":"Reddy, G. (2024). The mechanistic basis of data dependence and abrupt learning in an in-context classification task. In: The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=aN4Jf6Cx69"},{"key":"2913_CR55","doi-asserted-by":"crossref","unstructured":"Rubin, O., Herzig, J., & Berant, J. (2022). Learning to retrieve prompts for in-context learning. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"2913_CR56","doi-asserted-by":"crossref","unstructured":"Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023). In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics","DOI":"10.1162\/tacl_a_00605"},{"key":"2913_CR57","doi-asserted-by":"crossref","unstructured":"Razeghi, Y., Logan, I. V., Gardner, R. L., Singh, M., & S. (2022). Impact of pretraining term frequencies on few-shot numerical reasoning. Findings of the Association for Computational Linguistics: EMNLP 2022","DOI":"10.18653\/v1\/2022.findings-emnlp.59"},{"issue":"140","key":"2913_CR58","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1\u201367.","journal-title":"Journal of Machine Learning Research"},{"key":"2913_CR59","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI blog,"},{"key":"2913_CR60","unstructured":"Singh, A.K., Chan, S.C.Y., Moskovitz, T., Grant, E., Saxe, A.M., & Hill, F. (2023). The transient nature of emergent in-context learning in transformers. In: Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=Of0GBzow8P"},{"key":"2913_CR61","doi-asserted-by":"publisher","first-page":"2147","DOI":"10.1109\/TIP.2025.3554410","volume":"34","author":"Y Sun","year":"2025","unstructured":"Sun, Y., Chen, Q., Wang, J., Wang, J., & Li, Z. (2025). Exploring effective factors for improving visual in-context learning. IEEE Transactions on Image Processing, 34, 2147\u20132160. https:\/\/doi.org\/10.1109\/TIP.2025.3554410","journal-title":"IEEE Transactions on Image Processing"},{"key":"2913_CR62","doi-asserted-by":"crossref","unstructured":"Sun, Q., Cui, Y., Zhang, X., Zhang, F., Yu, Q., Luo, Z., Wang, Y., Rao, Y., Liu, J., Huang, T., & Wang, X. (2023). Generative multimodal models are in-context learners","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"2913_CR63","unstructured":"Song, Y., Liu, B., Li, X., Shi, N., Wang, Y., & Gao, X. (2023). Decoding natural images from eeg for object recognition arXiv:2308.13234 arXiv preprint."},{"key":"2913_CR64","doi-asserted-by":"crossref","unstructured":"Suo, W., Lai, L., Sun, M., Zhang, H., Wang, P., & Zhang, Y. (2024). Visual prompt selection for in-context learning segmentation. https:\/\/api.semanticscholar.org\/CorpusID:271213205","DOI":"10.1007\/978-3-031-72952-2_2"},{"key":"2913_CR65","unstructured":"Singh, A. K., Moskovitz, T., Hill, F., Chan, S. C., & Saxe, A. M. (2024). What needs to go right for an induction head? a mechanistic study of in-context learning circuits and their formation arXiv:2404.07129 arXiv preprint."},{"key":"2913_CR66","doi-asserted-by":"publisher","unstructured":"Serina, L., Putelli, L., Gerevini, A.E., & Serina, I. (2023). Synonyms, antonyms and factual knowledge in bert heads. Future Internet 15(7). https:\/\/doi.org\/10.3390\/fi15070230","DOI":"10.3390\/fi15070230"},{"issue":"11","key":"2913_CR67","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","volume":"38","author":"RT Schirrmeister","year":"2017","unstructured":"Schirrmeister, R. T., Springenberg, J. T., Fiederer, L. D. J., Glasstetter, M., Eggensperger, K., Tangermann, M., Hutter, F., Burgard, W., & Ball, T. (2017). Deep learning with convolutional neural networks for eeg decoding and visualization. Human Brain Mapping, 38(11), 5391\u20135420.","journal-title":"Human Brain Mapping"},{"key":"2913_CR68","volume-title":"Prototypical networks for few-shot learning","author":"J Snell","year":"2017","unstructured":"Snell, J., Swersky, K., & Zemel, R. (2017). Prototypical networks for few-shot learning. Syst: Adv. Neural Inf. Process."},{"key":"2913_CR69","unstructured":"Thie\u00dfen, F., D\u2019Souza, J., & Stocker, M. (2023). Probing large language models for scientific synonyms. In: SEMANTICS Workshops. https:\/\/api.semanticscholar.org\/CorpusID:265068593"},{"key":"2913_CR70","doi-asserted-by":"crossref","unstructured":"Tangermann, M., M\u00fcller, K.-R., Aertsen, A., Birbaumer, N., Braun, C., Brunner, C., Leeb, R., Mehring, C., Miller, K. J., Mueller-Putz, G., Nolte, G., Pfurtscheller, G., Preissl, H., Schalk, G., Schl\u00f6gl, A., Vidaurre, C., Waldert, S., & Blankertz, B. (2012). Review of the bci competition iv. Frontiers in Neuroscience, 6, https:\/\/doi.org\/10.3389\/fnins.2012.00055","DOI":"10.3389\/fnins.2012.00055"},{"key":"2913_CR71","unstructured":"Oswald, V., Niklasson, J., Randazzo, E., Sacramento, E., Mordvintsev, J., Zhmoginov, A., Vladymyrov, A., & M. (2023). Transformers learn in-context by gradient descent. International Conference on Machine Learning"},{"key":"2913_CR72","doi-asserted-by":"crossref","unstructured":"Voronov, A., Wolf, L., & Ryabinin, M. (2024). Mind your format: Towards consistent evaluation of in. context learning improvements. arXiv [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.375"},{"key":"2913_CR73","doi-asserted-by":"crossref","unstructured":"Wies, N., Levine, Y., & Shashua, A. (2023). The learnability of in-context learning. Advances in Neural Information Processing Systems","DOI":"10.52202\/075280-1593"},{"key":"2913_CR74","doi-asserted-by":"publisher","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., & Huang, T. (2023). Images speak in images: A generalist painter for in-context visual learning. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6830\u20136839. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00660","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"2913_CR75","unstructured":"Yang, J., Ma, S., & Wei, F. (2023). Auto-icl: In-context learning without human supervision. arXiv preprint arXiv:2311.09263"},{"issue":"12","key":"2913_CR76","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0114853","volume":"9","author":"W Yi","year":"2014","unstructured":"Yi, W., Qiu, S., Wang, K., Qi, H., Zhang, L., Zhou, P., He, F., & Ming, D. (2014). Evaluation of eeg oscillatory patterns and cognitive process during simple and compound limb motor imagery. PLOS ONE, 9(12), 1\u201319. https:\/\/doi.org\/10.1371\/journal.pone.0114853","journal-title":"PLOS ONE"},{"key":"2913_CR77","unstructured":"Zhu, J.Y., Cano, C.G., Bermudez, D.V., & Drozdzal, M. (2024). InCoRo: In-Context Learning for Robotics Control with Feedback Loops. arXiv:https:\/\/arxiv.org\/abs\/2402.05188"},{"key":"2913_CR78","unstructured":"Zucchet, N., d\u2019Angelo, F., Lampinen, A.K., & Chan, S.C.Y. (2025). The emergence of sparse attention: impact of data distribution and benefits of repetition. In: Advances in Neural Information Processing Systems"},{"issue":"9","key":"2913_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0162657","volume":"11","author":"B Zhou","year":"2016","unstructured":"Zhou, B., Wu, X., Lv, Z., Zhang, L., & Guo, X. (2016). A fully automated trial selection method for optimization of motor imagery based brain-computer interface. PLOS ONE, 11(9), 1\u201320. https:\/\/doi.org\/10.1371\/journal.pone.0162657","journal-title":"PLOS ONE"},{"key":"2913_CR80","unstructured":"Zhang, Y., Zhou, K., & Liu, Z. (2023). What makes good examples for visual in-context learning? Advances in Neural Information Processing Systems"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02913-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02913-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02913-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T08:11:23Z","timestamp":1781511083000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02913-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":80,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["2913"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02913-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"21 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}}],"article-number":"317"}}