{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T05:25:56Z","timestamp":1794374756782,"version":"4.9.0"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["467045002"],"award-info":[{"award-number":["467045002"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.neunet.2025.108407","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T07:12:53Z","timestamp":1765782773000},"page":"108407","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Object-centric proto-symbolic behavioural reasoning from pixels"],"prefix":"10.1016","volume":"197","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9216-6531","authenticated-orcid":false,"given":"Ruben","family":"van Bergen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8354-0368","authenticated-orcid":false,"given":"Justus","family":"H\u00fcbotter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1365-8721","authenticated-orcid":false,"given":"Alma","family":"Lago","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9154-0798","authenticated-orcid":false,"given":"Pablo","family":"Lanillos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108407_bib0001","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., Hausman, K. et al. (2022). Do as i can, not as i say: Grounding language in robotic affordances. arXiv preprint arXiv: 2204.01691."},{"key":"10.1016\/j.neunet.2025.108407_bib0002","series-title":"ICLR 2022 workshop on the elements of reasoning: Objects, structure and causality","article-title":"Object-centric compositional imagination for visual abstract reasoning","author":"Assouel","year":"2022"},{"key":"10.1016\/j.neunet.2025.108407_bib0003","unstructured":"Assran, M., Bardes, A., Fan, D., Garrido, Q., Howes, R., Muckley, M., Rizvi, A., Roberts, C., Sinha, K., Zholus, A. et al. (2025). V-jepa 2: Self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv: 2506.09985."},{"key":"10.1016\/j.neunet.2025.108407_bib0004","first-page":"4509","article-title":"Interaction networks for learning about objects, relations and physics","volume":"29","author":"Battaglia","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"45","key":"10.1016\/j.neunet.2025.108407_bib0005","doi-asserted-by":"crossref","first-page":"18327","DOI":"10.1073\/pnas.1306572110","article-title":"Simulation as an engine of physical scene understanding","volume":"110","author":"Battaglia","year":"2013","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2025.108407_bib0006","series-title":"Active inference: Third international workshop, IWAI 2022, Grenoble, France, September 19, 2022, Revised Selected Papers","first-page":"50","article-title":"Object-based active inference","author":"van Bergen","year":"2023"},{"key":"10.1016\/j.neunet.2025.108407_bib0007","series-title":"2022 International conference on robotics and automation (ICRA)","first-page":"5389","article-title":"Free energy principle for state and input estimation of a quadcopter flying in wind","author":"Bos","year":"2022"},{"issue":"1","key":"10.1016\/j.neunet.2025.108407_bib0008","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1075\/is.8.1.06cow","article-title":"How human infants deal with symbol grounding","volume":"8","author":"Cowley","year":"2007","journal-title":"Interaction Studies"},{"key":"10.1016\/j.neunet.2025.108407_bib0009","unstructured":"Daniel, T., & Tamar, A. (2022). Unsupervised image representation learning with deep latent particles. arXiv preprint arXiv: 2205.15821."},{"key":"10.1016\/j.neunet.2025.108407_bib0010","series-title":"Conference on robot learning","first-page":"1755","article-title":"Learning multi-object dynamics with compositional neural radiance fields","author":"Driess","year":"2023"},{"key":"10.1016\/j.neunet.2025.108407_bib0011","unstructured":"Driess, D., Xia, F., Sajjadi, M. S. M., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T. et al. (2023b). Palm-e: An embodied multimodal language model. arXiv preprint arXiv: 2303.03378."},{"key":"10.1016\/j.neunet.2025.108407_bib0012","first-page":"28940","article-title":"Savi++: Towards end-to-end object-centric learning from real-world videos","volume":"35","author":"Elsayed","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0013","first-page":"3233","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","volume":"29","author":"Eslami","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0014","first-page":"11662","article-title":"Deep active inference agents using monte-carlo methods","volume":"33","author":"Fountas","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.neunet.2025.108407_bib0015","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The free-energy principle: A unified brain theory?","volume":"11","author":"Friston","year":"2010","journal-title":"Nature Reviews Neuroscience"},{"key":"10.1016\/j.neunet.2025.108407_bib0016","unstructured":"Garrido, Q., Assran, M., Ballas, N., Bardes, A., Najman, L., & LeCun, Y. (2024). Learning and leveraging world models in visual representation learning. arXiv preprint arXiv: 2403.00504."},{"issue":"7999","key":"10.1016\/j.neunet.2025.108407_bib0017","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1038\/d41586-024-00288-1","article-title":"This AI learnt language by seeing the world through a baby\u2019s eyes","volume":"626","author":"Gibney","year":"2024","journal-title":"Nature"},{"issue":"2266","key":"10.1016\/j.neunet.2025.108407_bib0018","article-title":"Inductive biases for deep learning of higher-level cognition","volume":"478","author":"Goyal","year":"2022","journal-title":"Proceedings of the Royal Society A"},{"key":"10.1016\/j.neunet.2025.108407_bib0019","series-title":"International conference on machine learning","first-page":"2424","article-title":"Multi-object representation learning with iterative variational inference","author":"Greff","year":"2019"},{"key":"10.1016\/j.neunet.2025.108407_bib0020","unstructured":"Greff, K., Van Steenkiste, S., & Schmidhuber, J. (2020). On the binding problem in artificial neural networks. arXiv preprint arXiv: 2012.05208."},{"issue":"8","key":"10.1016\/j.neunet.2025.108407_bib0021","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.tics.2010.05.004","article-title":"Probabilistic models of cognition: Exploring representations and inductive biases","volume":"14","author":"Griffiths","year":"2010","journal-title":"Trends in Cognitive Sciences"},{"key":"10.1016\/j.neunet.2025.108407_bib0022","unstructured":"Gu, J., Kirmani, S., Wohlhart, P., Lu, Y., Arenas, M. G., Rao, K., Yu, W., Fu, C., Gopalakrishnan, K., Xu, Z. et al. (2023). Rt-trajectory: Robotic task generalization via hindsight trajectory sketches. arXiv preprint arXiv: 2311.01977."},{"key":"10.1016\/j.neunet.2025.108407_bib0023","first-page":"17518","article-title":"Sparsely changing latent states for prediction and planning in partially observable domains","volume":"34","author":"Gumbsch","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0024","series-title":"International conference on machine learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.neunet.2025.108407_bib0025","unstructured":"Haramati, D., Daniel, T., & Tamar, A. (2024). Entity-centric reinforcement learning for object manipulation from pixels. arXiv preprint arXiv: 2404.01220."},{"key":"10.1016\/j.neunet.2025.108407_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23212","article-title":"GeoVLN: Learning geometry-enhanced visual representation with slot attention for vision-and-language navigation","author":"Huo","year":"2023"},{"key":"10.1016\/j.neunet.2025.108407_bib0027","unstructured":"Jang, E., Gu, S., & Poole, B. (2016). Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv: 1611.01144."},{"key":"10.1016\/j.neunet.2025.108407_bib0028","unstructured":"Jiang, J., Deng, F., Singh, G., & Ahn, S. (2023). Object-centric slot diffusion. arXiv preprint arXiv: 2303.10834."},{"key":"10.1016\/j.neunet.2025.108407_bib0029","unstructured":"Jiang, J., Janghorbani, S., De Melo, G., & Ahn, S. (2019). SCALOR: Generative world models with scalable object representations. arXiv preprint arXiv: 1910.02384."},{"issue":"2","key":"10.1016\/j.neunet.2025.108407_bib0030","first-page":"102","article-title":"Contributions to the theory of optimal control","volume":"5","author":"Kalman","year":"1960","journal-title":"Bolet\u00edn de la Sociedad Matem\u00e1tica Mexicana"},{"key":"10.1016\/j.neunet.2025.108407_bib0031","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv: 1412.6980."},{"key":"10.1016\/j.neunet.2025.108407_bib0032","series-title":"International conference on learning representations","article-title":"Conditional object-centric learning from video","author":"Kipf","year":"2022"},{"key":"10.1016\/j.neunet.2025.108407_bib0033","series-title":"Optimal control theory: an introduction","author":"Kirk","year":"2004"},{"key":"10.1016\/j.neunet.2025.108407_bib0034","unstructured":"Lanillos, P., & van Gerven, M. (2021). Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception. arXiv preprint arXiv: 2105.04261."},{"key":"10.1016\/j.neunet.2025.108407_bib0035","unstructured":"Lanillos, P., Meo, C., Pezzato, C., Meera, A. A., Baioumy, M., Ohata, W., Tschantz, A., Millidge, B., Wisse, M., Buckley, C. L. et al. (2021). Active inference in robotics and artificial agents: Survey and challenges. arXiv preprint arXiv: 2112.01871."},{"key":"10.1016\/j.neunet.2025.108407_bib0036","series-title":"2019 International conference on robotics and automation (ICRA)","first-page":"1205","article-title":"Propagation networks for model-based control under partial observation","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2025.108407_bib0037","first-page":"11525","article-title":"Object-centric learning with slot attention","volume":"33","author":"Locatello","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0038","first-page":"5444","article-title":"Iterative amortized inference","volume":"8","author":"Marino","year":"2018","journal-title":"35th International Conference on Machine Learning, ICML 2018"},{"issue":"2","key":"10.1016\/j.neunet.2025.108407_bib0039","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1162\/neco_a_01354","article-title":"Whence the expected free energy?","volume":"33","author":"Millidge","year":"2021","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2025.108407_bib0040","series-title":"International conference on machine learning (ICML)","article-title":"Sold: Slot object-centric latent dynamics models for relational manipulation learning from pixels","author":"Mosbach","year":"2025"},{"key":"10.1016\/j.neunet.2025.108407_bib0041","series-title":"Active inference: the free energy principle in mind, brain, and behavior","author":"Parr","year":"2022"},{"key":"10.1016\/j.neunet.2025.108407_bib0042","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1038\/s41562-021-01194-6","article-title":"Capturing the objects of vision with neural networks","volume":"5","author":"Peters","year":"2021","journal-title":"Nature Human Behaviour"},{"key":"10.1016\/j.neunet.2025.108407_bib0043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11023-020-09540-9","article-title":"The computational origin of representation","volume":"31","author":"Piantadosi","year":"2021","journal-title":"Minds and Machines"},{"issue":"9","key":"10.1016\/j.neunet.2025.108407_bib0044","doi-asserted-by":"crossref","first-page":"1257","DOI":"10.1038\/s41562-022-01394-8","article-title":"Intuitive physics learning in a deep-learning model inspired by developmental psychology","volume":"6","author":"Piloto","year":"2022","journal-title":"Nature Human Behaviour"},{"issue":"268","key":"10.1016\/j.neunet.2025.108407_bib0045","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"10.1016\/j.neunet.2025.108407_bib0046","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1007\/s10514-019-09882-z","article-title":"Attention-based active visual search for mobile robots","volume":"44","author":"Rasouli","year":"2020","journal-title":"Autonomous Robots"},{"key":"10.1016\/j.neunet.2025.108407_bib0047","first-page":"24170","article-title":"Curious exploration via structured world models yields zero-shot object manipulation","volume":"35","author":"Sancaktar","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0048","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv preprint arXiv: 1707.06347."},{"key":"10.1016\/j.neunet.2025.108407_bib0049","unstructured":"Sundaresan, P., Vuong, Q., Gu, J., Xu, P., Xiao, T., Kirmani, S., Yu, T., Stark, M., Jain, A., Hausman, K. et al. (2024). Rt-sketch: Goal-conditioned imitation learning from hand-drawn sketches. arXiv preprint arXiv: 2403.02709."},{"issue":"13","key":"10.1016\/j.neunet.2025.108407_bib0050","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1080\/01691864.2023.2225232","article-title":"World models and predictive coding for cognitive and developmental robotics: Frontiers and challenges","volume":"37","author":"Taniguchi","year":"2023","journal-title":"Advanced Robotics"},{"key":"10.1016\/j.neunet.2025.108407_bib0051","unstructured":"Traub, M., Otte, S., Menge, T., Karlbauer, M., Thuemmel, J., & Butz, M. V. (2022). Learning what and where: Disentangling location and identity tracking without supervision. arXiv preprint arXiv: 2205.13349."},{"key":"10.1016\/j.neunet.2025.108407_bib0052","series-title":"The eleventh international conference on learning representations","article-title":"Learning what and where: Disentangling location and identity tracking without supervision","author":"Traub","year":"2023"},{"issue":"4","key":"10.1016\/j.neunet.2025.108407_bib0053","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1162\/neco_a_01637","article-title":"Object-centric scene representations using active inference","volume":"36","author":"Van de Maele","year":"2024","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2025.108407_bib0054","series-title":"Active inference: First international workshop, IWAI 2020, co-located with ECML\/PKDD 2020, Ghent, Belgium, september 14, 2020, Proceedings 1","first-page":"61","article-title":"Deep active inference for partially observable mdps","author":"van der Himst","year":"2020"},{"key":"10.1016\/j.neunet.2025.108407_bib0055","series-title":"Conference on robot learning","first-page":"1439","article-title":"Entity abstraction in visual model-based reinforcement learning","author":"Veerapaneni","year":"2020"},{"key":"10.1016\/j.neunet.2025.108407_bib0056","series-title":"2023\u202fIEEE International conference on image processing (ICIP)","first-page":"570","article-title":"Object-centric video prediction via decoupling of object dynamics and interactions","author":"Villar-Corrales","year":"2023"},{"issue":"9","key":"10.1016\/j.neunet.2025.108407_bib0057","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1016\/j.neunet.2006.10.001","article-title":"Modeling attention to salient proto-objects","volume":"19","author":"Walther","year":"2006","journal-title":"Neural Networks"},{"issue":"2","key":"10.1016\/j.neunet.2025.108407_bib0058","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.1109\/TPAMI.2022.3165153","article-title":"PredRNN: A recurrent neural network for spatiotemporal predictive learning","volume":"45","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108407_bib0059","first-page":"4542","article-title":"Visual interaction networks: Learning a physics simulator from video","volume":"30","author":"Watters","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0060","article-title":"Systematic visual reasoning through object-centric relational abstraction","volume":"36","author":"Webb","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108407_bib0061","unstructured":"Xu, Y., Li, W., Vaezipoor, P., Sanner, S., & Khalil, E. B. (2023). Llms and the abstraction and reasoning corpus: successes, failures, and the importance of object-based representations. arXiv preprint arXiv: 2305.18354."},{"key":"10.1016\/j.neunet.2025.108407_bib0062","series-title":"International conference on learning representations","article-title":"Unsupervised discovery of object radiance fields","author":"Yu","year":"2022"},{"key":"10.1016\/j.neunet.2025.108407_bib0063","unstructured":"Zadaianchuk, A., Seitzer, M., & Martius, G. (2020). Self-supervised visual reinforcement learning with object-centric representations. arXiv preprint arXiv: 2011.14381."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025012882?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025012882?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:01:55Z","timestamp":1771876915000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025012882"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":63,"alternative-id":["S0893608025012882"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108407","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Object-centric proto-symbolic behavioural reasoning from pixels","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108407","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108407"}}