{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:09:29Z","timestamp":1789027769863,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370228","type":"print"},{"value":"9783032370235","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37023-5_32","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:52:49Z","timestamp":1789026769000},"page":"584-603","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lifting Embodied World Models for\u00a0Planning and\u00a0Control"],"prefix":"10.1007","author":[{"given":"Alex N.","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavel","family":"Izmailov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Bar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"32_CR1","unstructured":"Agarwal, N., et\u00a0al.: Cosmos world foundation model platform for physical AI. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"32_CR2","unstructured":"Assran, M., et al.: V-JEPA 2: self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv:2506.09985 (2025)"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Bai, Y., Tran, D., Bar, A., LeCun, Y., Darrell, T., Malik, J.: Whole-body conditioned egocentric video prediction. In: The Thirty-Ninth Annual Conference on Neural Information Processing Systems (2025). https:\/\/openreview.net\/forum?id=XDTTwmjhAg","DOI":"10.52202\/085713-5482"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Bar, A., Zhou, G., Tran, D., Darrell, T., LeCun, Y.: Navigation world models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15791\u201315801 (2025)","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"32_CR5","unstructured":"Bharadhwaj, H., Xie, K., Shkurti, F.: Model-predictive control via cross-entropy and gradient-based optimization. In: Learning for Dynamics and Control, pp. 277\u2013286. PMLR (2020)"},{"key":"32_CR6","unstructured":"Bjorck, J., et\u00a0al.: GR00T N1: an open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"issue":"10\u201311","key":"32_CR7","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Robot. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Int. J. Robot. Res."},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Du, M., Song, S.: DynaGuide: steering diffusion policies with active dynamic guidance. In: Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS) (2025)","DOI":"10.52202\/085713-1473"},{"key":"32_CR9","unstructured":"Engel, J., et al.: Project aria: a new tool for egocentric multi-modal ai research. arXiv preprint arXiv:2308.13561 (2023)"},{"key":"32_CR10","unstructured":"Fu, Z., Zhao, Q., Wu, Q., Wetzstein, G., Finn, C.: HumanPlus: humanoid shadowing and imitation from humans. In: Conference on Robot Learning, pp. 2828\u20132844. PMLR (2025)"},{"key":"32_CR11","unstructured":"Gao, S., et al.: DreamDojo: a generalist robot world model from large-scale human videos. arXiv preprint arXiv:2602.06949 (2026)"},{"key":"32_CR12","unstructured":"Goswami, R.G., et al.: World models can leverage human videos for dexterous manipulation. arXiv preprint arXiv:2512.13644 (2025)"},{"key":"32_CR13","unstructured":"Ha, D., Schmidhuber, J.: Recurrent world models facilitate policy evolution. In: Advances in Neural Information Processing Systems, vol. 31, pp. 2451\u20132463. Curran Associates, Inc. (2018). https:\/\/papers.nips.cc\/paper\/7512-recurrent-world-models-facilitate-policy-evolution, https:\/\/worldmodels.github.io"},{"key":"32_CR14","unstructured":"Hafner, D., Lillicrap, T., Ba, J., Norouzi, M.: Dream to control: learning behaviors by latent imagination. In: International Conference on Learning Representations (2019)"},{"key":"32_CR15","unstructured":"Hafner, D., et al.: Learning latent dynamics for planning from pixels. In: International Conference on Machine Learning, pp. 2555\u20132565. PMLR (2019)"},{"key":"32_CR16","unstructured":"Hafner, D., Lillicrap, T.P., Norouzi, M., Ba, J.: Mastering Atari with discrete world models. In: International Conference on Learning Representations (2020)"},{"issue":"8059","key":"32_CR17","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1038\/s41586-025-08744-2","volume":"640","author":"D Hafner","year":"2025","unstructured":"Hafner, D., Pasukonis, J., Ba, J., Lillicrap, T.: Mastering diverse control tasks through world models. Nature 640(8059), 647\u2013653 (2025)","journal-title":"Nature"},{"key":"32_CR18","unstructured":"Hansen, N., Su, H., Wang, X.: TD-MPC2: scalable, robust world models for continuous control. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"32_CR19","unstructured":"Hu, A., et al.: Gaia-1: a generative world model for autonomous driving. arXiv preprint arXiv:2309.17080 (2023)"},{"key":"32_CR20","doi-asserted-by":"publisher","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014). https:\/\/doi.org\/10.1109\/TPAMI.2013.248","DOI":"10.1109\/TPAMI.2013.248"},{"key":"32_CR21","unstructured":"Kim, M.J., et al.: OpenVLA: an open-source vision-language-action model. In: Agrawal, P., Kroemer, O., Burgard, W. (eds.) Proceedings of The 8th Conference on Robot Learning. Proceedings of Machine Learning Research, vol.\u00a0270, pp. 2679\u20132713. PMLR (2025). https:\/\/proceedings.mlr.press\/v270\/kim25c.html"},{"key":"32_CR22","unstructured":"LeCun, Y., et\u00a0al.: A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27. Open Rev. 62(1), 1\u201362 (2022)"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Ma, L., et al: Nymeria: a massive collection of multimodal egocentric daily motion in the wild. In: European Conference on Computer Vision, pp. 445\u2013465. Springer (2024)","DOI":"10.1007\/978-3-031-72691-0_25"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Ma, X., Patidar, S., Haughton, I., James, S.: Hierarchical diffusion policy for kinematics-aware multi-task robotic manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18081\u201318090 (2024)","DOI":"10.1109\/CVPR52733.2024.01712"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Merel, J., Botvinick, M., Wayne, G.: Hierarchical motor control in mammals and machines. Nat. Commun. 10(1), 5489 (2019)","DOI":"10.1038\/s41467-019-13239-6"},{"key":"32_CR26","unstructured":"Mereu, R., et al.: Generative world modelling for humanoids: 1x world model challenge technical report. arXiv preprint arXiv:2510.07092 (2025)"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Mur-Labadia, L., et al.: V-JEPA 2.1: unlocking dense features in video self-supervised learning. arXiv preprint arXiv:2603.14482 (2026)","DOI":"10.1007\/978-3-032-37369-4_36"},{"key":"32_CR28","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"32_CR29","unstructured":"Hansen, N., Jyothir, S.V., Sobal, V., LeCun, Y., Wang, X., Su, H.: Hierarchical world models as visual whole-body humanoid controllers (2025)"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Ghosh, D., et al.: Octo: an open-source generalist robot policy. In: Proceedings of Robotics: Science and Systems, Delft, Netherlands (2024)","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Park, S., Ghosh, D., Eysenbach, B., Levine, S.: HIQL: offline goal-conditioned RL with latent states as actions. In: Proceedings of the 37th International Conference on Neural Information Processing Systems, pp. 34866\u201334891 (2023)","DOI":"10.52202\/075280-1515"},{"key":"32_CR32","unstructured":"Parthasarathy, A., et al.: Closing the train-test gap in world models for gradient-based planning. arXiv preprint arXiv:2512.09929 (2025)"},{"key":"32_CR33","unstructured":"Psenka, M., Rabbat, M., Krishnapriyan, A., LeCun, Y., Bar, A.: Parallel stochastic gradient-based planning for world models. arXiv preprint arXiv:2602.00475 (2026)"},{"key":"32_CR34","unstructured":"Robine, J., H\u00f6ftmann, M., Uelwer, T., Harmeling, S.: Transformer-based world models are happy with 100k interactions. arXiv preprint arXiv:2303.07109 (2023)"},{"key":"32_CR35","unstructured":"Roetenberg, D., Luinge, H., Slycke, P., et\u00a0al.: Xsens MVN: full 6DoF human motion tracking using miniature inertial sensors. Xsens Motion Technologies BV, Technical report 1(2009), 1\u20137 (2009)"},{"issue":"1","key":"32_CR36","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/S0377-2217(96)00385-2","volume":"99","author":"RY Rubinstein","year":"1997","unstructured":"Rubinstein, R.Y.: Optimization of computer simulation models with rare events. Eur. J. Oper. Res. 99(1), 89\u2013112 (1997)","journal-title":"Eur. J. Oper. Res."},{"key":"32_CR37","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Sridhar, A., Shah, D., Glossop, C., Levine, S.: NoMaD: goal masked diffusion policies for navigation and exploration. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 63\u201370. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"32_CR39","doi-asserted-by":"crossref","unstructured":"Taheri, O., Choutas, V., Black, M.J., Tzionas, D.: GOAL: generating 4D whole-body motion for hand-object grasping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13263\u201313273 (2022)","DOI":"10.1109\/CVPR52688.2022.01291"},{"issue":"6","key":"32_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3687951","volume":"43","author":"C Tessler","year":"2024","unstructured":"Tessler, C., Guo, Y., Nabati, O., Chechik, G., Peng, X.B.: MaskedMimic: unified physics-based character control through masked motion inpainting. ACM Trans. Graphics (TOG) 43(6), 1\u201321 (2024)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"32_CR41","unstructured":"Tevet, G., et al.: CLoSD: closing the loop between simulation and diffusion for multi-task character control. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=pZISppZSTv"},{"key":"32_CR42","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2022)"},{"issue":"2","key":"32_CR43","doi-asserted-by":"publisher","first-page":"344","DOI":"10.2514\/1.G001921","volume":"40","author":"G Williams","year":"2017","unstructured":"Williams, G., Aldrich, A., Theodorou, E.A.: Model predictive path integral control: From theory to parallel computation. J. Guid. Control. Dyn. 40(2), 344\u2013357 (2017)","journal-title":"J. Guid. Control. Dyn."},{"key":"32_CR44","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: OmniControl: control any joint at any time for human motion generation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"32_CR45","unstructured":"Yang, S., et al.: Learning interactive real-world simulators. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=sFyTZEqmUY"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Ze, Y., et al.: Generalizable humanoid manipulation with 3D diffusion policies. In: 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2873\u20132880. IEEE (2025)","DOI":"10.1109\/IROS60139.2025.11246340"},{"issue":"6","key":"32_CR47","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","unstructured":"Zhang, M., et al.: MotionDiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR48","unstructured":"Zhou, G., Pan, H., LeCun, Y., Pinto, L.: DINO-WM: world models on pre-trained visual features enable zero-shot planning. In: Forty-second International Conference on Machine Learning (2025). https:\/\/openreview.net\/forum?id=D5RNACOZEI"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37023-5_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:53:05Z","timestamp":1789026785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37023-5_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370228","9783032370235"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37023-5_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}