{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T12:07:45Z","timestamp":1789042065619,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370914","type":"print"},{"value":"9783032370921","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\/978-3-032-37092-1_29","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:14:08Z","timestamp":1789038848000},"page":"515-533","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predictive Structure Improves Video Diffusion Dynamics"],"prefix":"10.1007","author":[{"given":"Mi","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujia","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Dimakis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Sheng","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Du","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"29_CR1","unstructured":"Agarwal, N., et al.: Cosmos world foundation model platform for physical AI. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"29_CR2","unstructured":"Assran, M., et al.: V-JEPA 2: self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv:2506.09985 (2025)"},{"issue":"3","key":"29_CR3","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/j.0963-7214.2004.00281.x","volume":"13","author":"R Baillargeon","year":"2004","unstructured":"Baillargeon, R.: Infants\u2019 physical world. Curr. Dir. Psychol. Sci. 13(3), 89\u201394 (2004)","journal-title":"Curr. Dir. Psychol. Sci."},{"issue":"1","key":"29_CR4","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1111\/j.1745-6916.2008.00056.x","volume":"3","author":"R Baillargeon","year":"2008","unstructured":"Baillargeon, R.: Innate ideas revisited: for a principle of persistence in infants\u2019 physical reasoning. Perspect. Psychol. Sci. 3(1), 2\u201313 (2008)","journal-title":"Perspect. Psychol. Sci."},{"key":"29_CR5","unstructured":"Bansal, H., et al.: Videophy: evaluating physical commonsense for video generation. arXiv preprint arXiv:2406.03520 (2024)"},{"key":"29_CR6","unstructured":"Bardes, A., et al.: Revisiting feature prediction for learning visual representations from video. arXiv:2404.08471 (2024)"},{"issue":"45","key":"29_CR7","doi-asserted-by":"publisher","first-page":"18327","DOI":"10.1073\/pnas.1306572110","volume":"110","author":"PW Battaglia","year":"2013","unstructured":"Battaglia, P.W., Hamrick, J.B., Tenenbaum, J.B.: Simulation as an engine of physical scene understanding. Proc. Natl. Acad. Sci. 110(45), 18327\u201318332 (2013)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"29_CR8","unstructured":"Bear, D.M., et al.: Physion: evaluating physical prediction from vision in humans and machines. arXiv preprint arXiv:2106.08261 (2021)"},{"key":"29_CR9","unstructured":"Bhowmik, A., Korzhenkov, D., Snoek, C.G., Habibian, A., Ghafoorian, M.: Moalign: motion-centric representation alignment for video diffusion models. arXiv preprint arXiv:2510.19022 (2025)"},{"key":"29_CR10","unstructured":"Bordes, F., Garrido, Q., Kao, J.T., Williams, A., Rabbat, M., Dupoux, E.: Intphys 2: benchmarking intuitive physics understanding in complex synthetic environments. arXiv preprint arXiv:2506.09849 (2025)"},{"issue":"10","key":"29_CR11","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1109\/83.718487","volume":"7","author":"MA Butt","year":"1998","unstructured":"Butt, M.A., Maragos, P.: Optimum design of chamfer distance transforms. IEEE Trans. Image Process. 7(10), 1477\u20131484 (1998)","journal-title":"IEEE Trans. Image Process."},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Videocrafter2: overcoming data limitations for high-quality video diffusion models (2024)","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"29_CR13","unstructured":"Garrido, Q., et al.: Intuitive physics understanding emerges from self-supervised pretraining on natural videos. arXiv preprint arXiv:2502.11831 (2025)"},{"key":"29_CR14","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.cognition.2016.08.012","volume":"157","author":"JB Hamrick","year":"2016","unstructured":"Hamrick, J.B., Battaglia, P.W., Griffiths, T.L., Tenenbaum, J.B.: Inferring mass in complex scenes by mental simulation. Cognition 157, 61\u201376 (2016)","journal-title":"Cognition"},{"issue":"2","key":"29_CR15","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"29_CR16","unstructured":"Jang, S., Ki, T., Jo, J., Xie, S., Yoon, J., Hwang, S.J.: Self-refining video sampling. arXiv:2601.18577 arXiv preprint (2026)"},{"key":"29_CR17","unstructured":"Ji, S., Chen, X., Tao, X., Wan, P., Zhao, H.: Physmaster: mastering physical representation for video generation via reinforcement learning. arXiv preprint arXiv:2510.13809 (2025)"},{"key":"29_CR18","unstructured":"Jin, Y., et al.: Pyramidal flow matching for efficient video generative modeling. arXiv preprint arXiv:2410.05954 (2024)"},{"key":"29_CR19","unstructured":"Kang, B., et al.: How far is video generation from world model: a physical law perspective. arXiv preprint arXiv:2411.02385 (2024)"},{"key":"29_CR20","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"29_CR21","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"29_CR22","unstructured":"Kong, W., et al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"29_CR23","unstructured":"Kuaishou: Kling (2024). https:\/\/kling.kuaishou.com. Accessed 2024"},{"key":"29_CR24","unstructured":"Li, C., Michel, O., Pan, X., Liu, S., Roberts, M., Xie, S.: Pisa experiments: exploring physics post-training for video diffusion models by watching stuff drop. arXiv preprint arXiv:2503.09595 (2025)"},{"key":"29_CR25","unstructured":"Li, Y., et al.: Branchgrpo: stable and efficient GRPO with structured branching in diffusion models. arXiv preprint arXiv:2509.06040 (2025)"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Li, Z., Tucker, R., Snavely, N., Holynski, A.: Generative image dynamics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24142\u201324153 (2024)","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Flow-GRPO: training flow matching models via online RL. arXiv preprint arXiv:2505.05470 (2025)","DOI":"10.52202\/085713-1362"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: Videodpo: omni-preference alignment for video diffusion generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8009\u20138019 (2025)","DOI":"10.1109\/CVPR52734.2025.00750"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., Ren, Z., Gupta, S., Wang, S.: Physgen: rigid-body physics-grounded image-to-video generation. In: European Conference on Computer Vision, pp. 360\u2013378. Springer (2024)","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"29_CR30","unstructured":"Luma: Dream machine (2024). https:\/\/lumalabs.ai\/dream-machine. Accessed 2024"},{"key":"29_CR31","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"29_CR32","unstructured":"Nan, K., et al.: Openvid-1m: a large-scale high-quality dataset for text-to-video generation. arXiv preprint arXiv:2407.02371 (2024)"},{"key":"29_CR33","unstructured":"OpenAI: Sora (2024). https:\/\/sora.com. Accessed 2024"},{"key":"29_CR34","unstructured":"OpenAI: Sora 2 system card (2025). https:\/\/cdn.openai.com\/pdf\/50d5973c-c4ff-4c2d-986f-c72b5d0ff069\/sora_2_system_card.pdf. Accessed 21 Jan 2026"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"29_CR36","unstructured":"Ravi, N., et al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"29_CR38","unstructured":"Runway: Gen-3 Alpha (2024)"},{"key":"29_CR39","unstructured":"Shao, Z., et al.: Deepseekmath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"29_CR40","unstructured":"Singh, J., et al.: What matters for representation alignment: global information or spatial structure? arXiv preprint arXiv:2512.10794 (2025)"},{"key":"29_CR41","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"issue":"4","key":"29_CR42","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1037\/0033-295X.99.4.605","volume":"99","author":"ES Spelke","year":"1992","unstructured":"Spelke, E.S., Breinlinger, K., Macomber, J., Jacobson, K.: Origins of knowledge. Psychol. Rev. 99(4), 605 (1992)","journal-title":"Psychol. Rev."},{"issue":"1","key":"29_CR43","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/j.1467-7687.2007.00569.x","volume":"10","author":"ES Spelke","year":"2007","unstructured":"Spelke, E.S., Kinzler, K.D.: Core knowledge. Dev. Sci. 10(1), 89\u201396 (2007)","journal-title":"Dev. Sci."},{"key":"29_CR44","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning, pp. 843\u2013852. PMLR (2015)"},{"key":"29_CR45","unstructured":"Teng, H., et al.: Magi-1: autoregressive video generation at scale. arXiv preprint arXiv:2505.13211 (2025)"},{"key":"29_CR46","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"issue":"9","key":"29_CR47","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.tics.2017.05.012","volume":"21","author":"TD Ullman","year":"2017","unstructured":"Ullman, T.D., Spelke, E., Battaglia, P., Tenenbaum, J.B.: Mind games: game engines as an architecture for intuitive physics. Trends Cogn. Sci. 21(9), 649\u2013665 (2017)","journal-title":"Trends Cogn. Sci."},{"key":"29_CR48","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"29_CR49","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: WISA: world simulator assistant for physics-aware text-to-video generation. arXiv preprint arXiv:2503.08153 (2025)","DOI":"10.52202\/085713-0191"},{"issue":"5","key":"29_CR50","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1007\/s11263-024-02295-1","volume":"133","author":"Y Wang","year":"2025","unstructured":"Wang, Y., et al.: Lavie: high-quality video generation with cascaded latent diffusion models. Int. J. Comput. Vision 133(5), 3059\u20133078 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR51","unstructured":"Wu, H., et al.: Geometry forcing: marrying video diffusion and 3D representation for consistent world modeling. arXiv preprint arXiv:2507.07982 (2025)"},{"key":"29_CR52","unstructured":"Wu, J., Yildirim, I., Lim, J.J., Freeman, B., Tenenbaum, J.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. Adv. Neural. Inf. Process. Syst. 28 (2015)"},{"key":"29_CR53","unstructured":"Wu, J., Lu, E., Kohli, P., Freeman, B., Tenenbaum, J.: Learning to see physics via visual de-animation. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"29_CR54","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: Densedpo: fine-grained temporal preference optimization for video diffusion models. arXiv preprint arXiv:2506.03517 (2025)","DOI":"10.52202\/085713-5713"},{"key":"29_CR55","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: Dynamicrafter: animating open-domain images with video diffusion priors. arXiv preprint arXiv:2310.12190 (2023)","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Xue, Q., Yin, X., Yang, B., Gao, W.: Phyt2v: LLM-guided iterative self-refinement for physics-grounded text-to-video generation. arXiv preprint arXiv:2412.00596 (2024)","DOI":"10.1109\/CVPR52734.2025.01754"},{"key":"29_CR57","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"29_CR58","unstructured":"Xue, Z., et al.: Dancegrpo: unleashing GRPO on visual generation. arXiv preprint arXiv:2505.07818 (2025)"},{"key":"29_CR59","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: VLIPP: towards physically plausible video generation with vision and language informed physical prior. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12360\u201312370 (2025)","DOI":"10.1109\/ICCV51701.2025.01149"},{"key":"29_CR60","unstructured":"Yang, Z., et al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"29_CR61","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. arXiv preprint arXiv:2410.06940 (2024)"},{"key":"29_CR62","unstructured":"Yuan, J., et al.: Likephys: evaluating intuitive physics understanding in video diffusion models via likelihood preference. arXiv preprint arXiv:2510.11512 (2025)"},{"key":"29_CR63","unstructured":"Yuan, J., et al.: Inference-time physics alignment of video generative models with latent world models. arXiv preprint arXiv:2601.10553 (2026)"},{"key":"29_CR64","unstructured":"Yuan, Y., Wang, X., Wickremasinghe, T., Nadir, Z., Ma, B., Chan, S.H.: Newtongen: physics-consistent and controllable text-to-video generation via neural newtonian dynamics. arXiv preprint arXiv:2509.21309 (2025)"},{"key":"29_CR65","unstructured":"Zhan, G., Ma, X., Xie, W., Zisserman, A.: Inferring dynamic physical properties from video foundation models. arXiv preprint arXiv:2510.02311 (2025)"},{"key":"29_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Videorepa: learning physics for video generation through relational alignment with foundation models. arXiv preprint arXiv:2505.23656 (2025)","DOI":"10.52202\/085713-4091"},{"key":"29_CR67","unstructured":"Zheng, Z., et al.: Open-sora: democratizing efficient video production for all. arXiv preprint arXiv:2412.20404 (2024)"}],"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\/978-3-032-37092-1_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:14:31Z","timestamp":1789038871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37092-1_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370914","9783032370921"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37092-1_29","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"}}]}}