{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T10:07:53Z","timestamp":1789380473139,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370280","type":"print"},{"value":"9783032370297","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\/978-3-032-37029-7_2","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:46:23Z","timestamp":1789379183000},"page":"20-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PhysMani: Physics-Principled 3D World Model for\u00a0Dynamic Object Manipulation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8163-267X","authenticated-orcid":false,"given":"Peng","family":"Yun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9655-2187","authenticated-orcid":false,"given":"Shouwang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4780-3767","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9683-1359","authenticated-orcid":false,"given":"Jinxi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2915-7960","authenticated-orcid":false,"given":"Jianan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2419-4140","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"2_CR1","unstructured":"Achiam, J.: GPT-4 technical report (2023). (). arXiv:2303.08774 arXiv preprint"},{"key":"2_CR2","unstructured":"Agarwal, N.: Cosmos world foundation model platform for physical AI, (2025). arXiv:2501.03575 arXiv preprint"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Akinola, I., Xu, J., Song, S., Allen, P.K.: Dynamic grasping with reachability and motion awareness. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 9422\u20139429. (2021)","DOI":"10.1109\/IROS51168.2021.9636057"},{"key":"2_CR4","unstructured":"Ali, A.: World simulation with video foundation models for physical AI, (2025). arXiv:2511.00062 arXiv preprint"},{"key":"2_CR5","unstructured":"Assran, M.: V-JEPA 2: Self-supervised video models enable understanding, prediction and planning, (2025). arXiv:2506.09985 arXiv preprint"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Bar-Tal, O.: Lumiere: a space-time diffusion model for video generation. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311. (2024)","DOI":"10.1145\/3680528.3687614"},{"key":"2_CR7","unstructured":"Barcellona, L.: Dream to manipulate: compositional world models empowering robot imitation learning with imagination. In: International Conference on Learning Representations, vol. 2025, pp. 56729\u201356763. (2025)"},{"key":"2_CR8","unstructured":"Bi, H.: Motus: a unified latent action world model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 35101\u201335113. (2026)"},{"key":"2_CR9","unstructured":"Black, K., et\u00a0al.: pi0.5: a vision-language-action model with open-world generalization. In: Conference on Robot Learning (2025)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Black, K.: pi0: a vision-language-action flow model for general robot control. In: Proceedings of Robotics Science and Systems,, LosAngeles, CA, USA (2025)","DOI":"10.15607\/RSS.2025.XXI.010"},{"key":"2_CR11","unstructured":"Blattmann, A.: Stable video diffusion: scaling latent video diffusion models to large datasets, (2023). arXiv:2311.15127 arXiv preprint"},{"key":"2_CR12","unstructured":"Bruce, J.: Genie: Generative interactive environments. International Conference on Machine Learning, (2024)"},{"key":"2_CR13","unstructured":"Chen, Y.: TeleWorld: towards dynamic multimodal synthesis with a 4D world model, (2026). arXiv:2601.00051 arXiv preprint"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Christen, S.: Learning human-to-robot handovers from point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9654\u20139664. (2023)","DOI":"10.1109\/CVPR52729.2023.00931"},{"key":"2_CR15","unstructured":"Coumans, E., Bai, Y.: PyBullet, a Python module for physics simulation for games, robotics and machine learning. http:\/\/pybullet.org (2016\u20132021). Accessed 28 Jun 2026"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"D\u2019Ambrosio, D.B., et\u00a0al.: Achieving human level competitive robot table tennis. In: IEEE International Conference on Robotics and Automation, pp. 74\u201382 (2025)","DOI":"10.1109\/ICRA55743.2025.11127501"},{"issue":"3","key":"2_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3746449","volume":"58","author":"J Ding","year":"2025","unstructured":"Ding, J., et al.: Understanding world or predicting future? a comprehensive survey of world models. ACM Comput. Surv. 58(3), 1\u201338 (2025)","journal-title":"ACM Comput. Surv."},{"key":"2_CR18","unstructured":"Gao, G.: Towards human-level intelligence via human-like whole-body manipulation, (2025). arXiv:2507.17141 arXiv preprint"},{"key":"2_CR19","unstructured":"Gervet, T., Xian, Z., Gkanatsios, N., Fragkiadaki, K.: Act 3D: 3D feature field transformers for multi-task robotic manipulation. In: Conference on Robot Learning, (2023)"},{"key":"2_CR20","unstructured":"Gkanatsios, N.: 3D FlowMatch Actor: Unified 3D policy for single-and dual-arm manipulation (2025). (). arXiv:2508.11002 arXiv preprint"},{"key":"2_CR21","unstructured":"Goyal, A., Xu, J., Guo, Y., Blukis, V., Chao, Y.W., Fox, D.: RVT: Robotic view transformer for 3D object manipulation. In: Conference on Robot Learning, pp. 694\u2013710. (2023)"},{"key":"2_CR22","unstructured":"Grattafiori, A.: The Llama 3 herd of models, (2024). arXiv:2407.21783 arXiv preprint"},{"key":"2_CR23","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.101222(3), 440 (2018)"},{"issue":"8059","key":"2_CR24","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":"2_CR25","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems. NIPS \u201920, Curran Associates Inc, Red Hook, NY, USA (2020)"},{"key":"2_CR26","unstructured":"Hu, E.J.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations, (2022)"},{"issue":"2","key":"2_CR27","doi-asserted-by":"publisher","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","volume":"5","author":"S James","year":"2020","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: RLBench: the robot learning benchmark & learning environment. IEEE Robot. Autom. Lett. 5(2), 3019\u20133026 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"James, S., Wada, K., Laidlow, T., Davison, A.J.: Coarse-to-fine q-attention: efficient learning for visual robotic manipulation via discretisation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13739\u201313748. (2022)","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Kawaharazuka, K., Oh, J., Yamada, J., Posner, I., Zhu, Y.: Vision-language-action models for robotics: a review towards real-world applications, IEEE Access (2025)","DOI":"10.36227\/techrxiv.175502755.53627529\/v1"},{"key":"2_CR30","unstructured":"Ke, T.W., Gkanatsios, N., Fragkiadaki, K.: 3D diffuser actor: policy diffusion with 3D scene representations. In: Conference on Robot Learning, (2024)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimkuehler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph 42(4), (2023)","DOI":"10.1145\/3592433"},{"key":"2_CR32","unstructured":"Kim, M.J.: OpenVLA: an open-source vision-language-action model. In: Conference on Robot Learning, (2024)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Kitano, H., Asada, M., Kuniyoshi, Y., Noda, I., Osawa, E.: Robocup: the robot world cup initiative. In: International Conference on Autonomous Agents, pp. 340\u2013347. (1997)","DOI":"10.1145\/267658.267738"},{"key":"2_CR34","unstructured":"Kong, W.: HunyuanVideo: a systematic framework for large video generative models, (2024). arXiv:2412.03603 arXiv preprint"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Li, J., Song, Z., Yang, B.: NVFi: Neural velocity fields for 3D physics learning from dynamic videos. Thirty-seventh Conference on Neural Information Processing Systems, (2023)","DOI":"10.52202\/075280-1508"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Li, J., Song, Z., Yang, B.: TRACE: learning 3D Gaussian physical dynamics from multi-view videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8820\u20138829. (2025)","DOI":"10.1109\/ICCV51701.2025.00825"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Li, J., Song, Z., Zhou, S., Yang, B.: FreeGave: 3D physics learning from dynamic videos by Gaussian velocity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12433\u201312443. (2025)","DOI":"10.1109\/CVPR52734.2025.01160"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Li, W.: PIN-WM: learning physics-informed world models for non-prehensile manipulation, (2025). arXiv:2504.16693 arXiv preprint","DOI":"10.15607\/RSS.2025.XXI.153"},{"key":"2_CR39","unstructured":"Li, X.: A comprehensive survey on world models for embodied AI, (2025). arXiv:2510.16732 arXiv preprint"},{"key":"2_CR40","unstructured":"Li, Y., Wu, J., Tedrake, R., Tenenbaum, J.B., Torralba, A.: Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids. In: International Conference on Learning Representations, (2019)"},{"key":"2_CR41","unstructured":"Liu, A.: DeepSeek-V3 technical report (2024). (). arXiv:2412.19437 arXiv preprint"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Liu, B.: LIBERO: benchmarking knowledge transfer for lifelong robot learning. In: Advances in Neural Information Processing Systems. NIPS \u201923, Curran Associates Inc, Red Hook, NY, USA (2023)","DOI":"10.52202\/075280-1939"},{"key":"2_CR43","unstructured":"Liu, H., Lee, L., Lee, K., Abbeel, P.: Instruction-following agents with multimodal transformer. arXiv preprint arXiv:2210.13431 (2022)"},{"key":"2_CR44","first-page":"34892","volume-title":"Advances in Neural Information Processing Systems","author":"H Liu","year":"2023","unstructured":"Liu, H., et al.: Visual instruction tuning. In: Levine, S. (ed.) Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916. Inc, Curran Associates (2023)"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, R.: Target-referenced reactive grasping for dynamic objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8824\u20138833. (2023)","DOI":"10.1109\/CVPR52729.2023.00852"},{"key":"2_CR46","unstructured":"Liu, X., Gong, C.: Flow straight and fast: learning to generate and transfer data with rectified flow. In: International Conference on Learning Representations, (2023)"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Lu, G.: ManiGaussian: dynamic Gaussian splatting for multi-task robotic manipulation. In: European Conference on Computer Vision, pp. 349\u2013366. (2024)","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"2_CR48","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3650584","volume-title":"A survey on vision-language-action models for embodied AI","author":"Y Ma","year":"2026","unstructured":"Ma, Y., Song, Z., Zhuang, Y., Hao, J., King, I.: A survey on vision-language-action models for embodied AI. IEEE Trans. Neural Netw. Learn, Syst (2026)"},{"issue":"5","key":"2_CR49","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1007\/s10514-018-9799-1","volume":"43","author":"N Marturi","year":"2019","unstructured":"Marturi, N., et al.: Dynamic grasp and trajectory planning for moving objects. Auton. Robot. 43(5), 1241\u20131256 (2019)","journal-title":"Auton. Robot."},{"issue":"3","key":"2_CR50","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/LRA.2022.3180108","volume":"7","author":"O Mees","year":"2022","unstructured":"Mees, O., Hermann, L., Rosete-Beas, E., Burgard, W.: CALVIN: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks. IEEE Robot. Autom. Lett. 7(3), 7327\u20137334 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Motamed, S., Culp, L., Swersky, K., Jaini, P., Geirhos, R.: Do generative video models understand physical principles? In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 948\u2013958. (2026)","DOI":"10.1109\/WACV61042.2026.00099"},{"key":"2_CR52","unstructured":"Noh, D.: Latent adaptive planner for dynamic manipulation. In: Conference on Robot Learning, pp. 2430\u20132448. (2025)"},{"key":"2_CR53","unstructured":"Team, O.M.: Octo: an open-source generalist robot policy. In: Proceedings of Robotics: Science and Systems,, Delft, Netherlands (2024)"},{"key":"2_CR54","unstructured":"Qwen Team: Qwen2.5-VL Technical Report (2025). (). arXiv:2502.13923 arXiv preprint"},{"key":"2_CR55","unstructured":"Sapkota, R., Cao, Y., Roumeliotis, K.I., Karkee, M.: Vision-language-action models: concepts, progress, applications and challenges, (2025). arXiv:2505.04769 arXiv preprint"},{"key":"2_CR56","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Perceiver-Actor: a multi-task transformer for robotic manipulation. In: Conference on Robot Learning, pp. 785\u2013799. (2023)"},{"key":"2_CR57","unstructured":"Tang, J.: Hunyuan-gamecraft-2: instruction-following interactive game world model, (2025). arXiv:2511.23429 arXiv preprint"},{"key":"2_CR58","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 6000\u20136010. NIPS\u201917, Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"2_CR59","unstructured":"Walke, H.R.: BridgeData v2: a dataset for robot learning at scale, pp. 1723\u20131736. (2023). Conference on Robot Learning"},{"key":"2_CR60","unstructured":"Team, W.: Wan: open and advanced large-scale video generative models (2025). (). arXiv:2503.20314 arXiv preprint"},{"key":"2_CR61","unstructured":"Xie, H.: DynamicVLA: a vision-language-action model for dynamic object manipulation, (2026). arXiv:2601.22153 arXiv preprint"},{"key":"2_CR62","unstructured":"Yang, A.: Qwen 2.5-1m technical report, (2025). arXiv:2501.15383 arXiv preprint"},{"key":"2_CR63","unstructured":"Ye, S.: World action models are zero-shot policies. In: International Conference on Learning Representations the 2nd Workshop on World Models: Understanding, Modelling and Scaling, (2026)"},{"key":"2_CR64","unstructured":"Zhang, D.: Pure vision language action (VLA) models: a comprehensive survey, (2025). arXiv:2509.19012 arXiv preprint"},{"issue":"6","key":"2_CR65","doi-asserted-by":"publisher","first-page":"5209","DOI":"10.1109\/LRA.2025.3557746","volume":"10","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Wang, R., Chen, X.: Dynamic behavior cloning with temporal feature prediction: enhancing robotic arm manipulation in moving object tasks. IEEE Robot. Autom. Lett. 10(6), 5209\u20135216 (2025)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2_CR66","unstructured":"Zhou, S.: PhysInOne: visual physics learning and reasoning in one suite. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 33131\u201333142. (2026)"},{"issue":"7","key":"2_CR67","doi-asserted-by":"publisher","first-page":"7466","DOI":"10.1109\/TIE.2023.3301512","volume":"71","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y., et al.: Spatiotemporal optimal trajectory planning for safe planar manipulation of a moving object. IEEE Trans. Industr. Electron. 71(7), 7466\u20137476 (2023)","journal-title":"IEEE Trans. Industr. Electron."},{"key":"2_CR68","unstructured":"Zhu, Z.: Is Sora a world simulator? A comprehensive survey on general world models and beyond, (2024). arXiv:2405.03520 arXiv preprint"},{"key":"2_CR69","unstructured":"Zitkovich, B.: RT-2: Vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. (2023)"}],"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\/978-3-032-37029-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:46:53Z","timestamp":1789379213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37029-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370280","9783032370297"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37029-7_2","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":"15 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"}}]}}