{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T06:06:20Z","timestamp":1782281180395,"version":"3.54.5"},"reference-count":68,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,11]]},"DOI":"10.1109\/iccps68698.2026.00024","type":"proceedings-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T19:43:46Z","timestamp":1782243826000},"page":"177-188","source":"Crossref","is-referenced-by-count":0,"title":["Physically Interpretable World Models via Weakly Supervised Representation Learning"],"prefix":"10.1109","author":[{"given":"Zhenjiang","family":"Mao","sequence":"first","affiliation":[{"name":"University of Florida,Gainesville,FL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mrinall Eashaan","family":"Umasudhan","sequence":"additional","affiliation":[{"name":"University of Florida,Gainesville,FL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Ruchkin","sequence":"additional","affiliation":[{"name":"University of Florida,Gainesville,FL,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint arXiv:1803.10122"},{"key":"ref2","article-title":"Transformers are sample-efficient world models","author":"Micheli","year":"2022","journal-title":"arXiv preprint arXiv:2209.00588"},{"key":"ref3","article-title":"Mastering diverse domains through world models","author":"Hafner","year":"2023","journal-title":"arXiv preprint arXiv:2301.04104"},{"key":"ref4","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Conference on Robot Learning","author":"Seo"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-4666-5888-2.ch705"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2514\/1.I011071"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19992-9_2"},{"key":"ref9","first-page":"1370","article-title":"How safe am i given what i see? calibrated prediction of safety chances for image-controlled autonomy","volume-title":"6th Annual Learning for Dynamics & Control Conference","author":"Mao"},{"key":"ref10","article-title":"Pixie: Fast and generalizable supervised learning of 3d physics from pixels","author":"Le","year":"2025","journal-title":"arXiv preprint arXiv:2508.17437"},{"key":"ref11","article-title":"Sold: Slot object-centric latent dynamics models for relational manipulation learning from pixels","author":"Mosbach","year":"2025"},{"key":"ref12","article-title":"Physically interpretable world models via weakly supervised representation learning: Extended version","author":"Mao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint arXiv:1509.02971"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref17","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Four principles for physically interpretable world models","author":"Peper","year":"2025","journal-title":"arXiv preprint arXiv:2503.02143"},{"key":"ref19","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv preprint arXiv:1606.01540"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR53236.2021.9659342"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2959476"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3450439.3451866"},{"key":"ref23","article-title":"Deep variational bayes filters: Unsupervised learning of state space models from raw data","author":"Karl","year":"2016","journal-title":"arXiv preprint arXiv:1605.06432"},{"issue":"18","key":"ref24","first-page":"710","article-title":"Sparse identification of nonlinear dynamics with control (sindyc)","volume-title":"IFAC-PapersOnLine","volume":"49","author":"Brunton"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859436"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560790"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160828"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_40"},{"key":"ref29","first-page":"606","article-title":"Interpretable self-aware neural networks for robust trajectory prediction","volume-title":"Conference on Robot Learning","author":"Itkina"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341712"},{"key":"ref31","first-page":"4717","article-title":"Towards generalizable and interpretable motion prediction: A deep variational bayes approach","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Lu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3576841.3585927"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS54341.2022.00007"},{"key":"ref34","article-title":"Convolutional 1stm network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv preprint arXiv:1803.01271"},{"key":"ref36","article-title":"Language-enhanced latent representations for out-of-distribution detection in autonomous driving","volume-title":"Robot Trust for Symbiotic Societies Workshop at IEEE ICRA","author":"Mao"},{"key":"ref37","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume":"3","author":"Higgins","year":"2017","journal-title":"ICLR (Poster)"},{"key":"ref38","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref39","article-title":"Isolating sources of disentanglement in variational autoencoders","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"ref41","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Supervised vector quantized variational autoencoder for learning interpretable global representations","author":"Xue","year":"2019","journal-title":"arXiv preprint arXiv:1909.11124"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_26"},{"key":"ref44","article-title":"Focus: Object-centric world models for robotics manipulation","author":"Ferraro","year":"2023","journal-title":"arXiv preprint arXiv:2307.02427"},{"key":"ref45","article-title":"Zero-shot safety prediction for autonomous robots with foundation world models","author":"Mao","year":"2024","journal-title":"arXiv preprint arXiv:2404.00462"},{"key":"ref46","article-title":"Spartan: A sparse transformer learning local causation","author":"Lei","year":"2024","journal-title":"arXiv preprint arXiv:2411.06890"},{"key":"ref47","article-title":"Bayesian neural networks with domain knowledge priors","author":"Sam","year":"2024","journal-title":"arXiv preprint arXiv:2402.13410"},{"key":"ref48","first-page":"3480","article-title":"Learning task informed abstractions","volume-title":"International Conference on Machine Learning","author":"Fu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5575"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3013"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-022-00281-6"},{"key":"ref53","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2020","journal-title":"arXiv preprint arXiv:2010.02193"},{"key":"ref54","first-page":"2226","article-title":"Day-dreamer: World models for physical robot learning","volume-title":"Conference on robot learning","author":"Wu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186812"},{"key":"ref56","first-page":"76","article-title":"Guaranteed conformance of neurosymbolic models to natural constraints","volume-title":"Learning for Dynamics and Control Conference","author":"Sridhar"},{"key":"ref57","article-title":"How to learn and generalize from three minutes of data: Physics-constrained and uncertainty-aware neural stochastic differential equations","author":"Djeumou","year":"2023","journal-title":"arXiv preprint arXiv:2306.06335"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197560"},{"key":"ref59","doi-asserted-by":"crossref","first-page":"115664","DOI":"10.1016\/j.cma.2022.115664","article-title":"Pi-vae: Physics-informed variational auto-encoder for stochastic differential equations","volume":"403","author":"Zhong","year":"2023","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"issue":"1","key":"ref60","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TNNLS.2023.3325432","article-title":"PhyTaylor: Partially Physics-Knowledge-Enhanced Deep Neural Networks via NN Editing","volume":"36","author":"Mao","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2290"},{"key":"ref62","article-title":"End-to-end differentiable physics for learning and control","volume":"31","author":"de Avila Belbute-Peres","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref64","article-title":"Uniworld: Autonomous driving pre-training via world models","author":"Min","year":"2023","journal-title":"arXiv preprint arXiv:2308.07234"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127609"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00635"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.65109\/teuc5537"},{"key":"ref68","article-title":"Visualpredicator: Learning abstract world models with neuro-symbolic predicates for robot planning","author":"Liang","year":"2024","journal-title":"arXiv preprint arXiv:2410.23156"}],"event":{"name":"2026 ACM\/IEEE 17th International Conference on Cyber-Physical Systems (ICCPS)","location":"Saint Malo, France","start":{"date-parts":[[2026,5,11]]},"end":{"date-parts":[[2026,5,14]]}},"container-title":["2026 ACM\/IEEE 17th International Conference on Cyber-Physical Systems (ICCPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11570664\/11570679\/11570733.pdf?arnumber=11570733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:33:40Z","timestamp":1782279220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11570733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccps68698.2026.00024","relation":{},"subject":[],"published":{"date-parts":[[2026,5,11]]}}}