{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:08:43Z","timestamp":1761480523178,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819520978","type":"print"},{"value":"9789819520985","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"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\/978-981-95-2098-5_4","type":"book-chapter","created":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:01:06Z","timestamp":1761480066000},"page":"37-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RoboImagine: A Robotic Video Generation Model, for Autoregressive Long-Term Task Video Generation with Geometric and Dynamic Consistency Augmentation"],"prefix":"10.1007","author":[{"given":"Conglin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongkun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanjiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqi","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Gan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"4_CR1","unstructured":"Ajay, A., et al.: Compositional foundation models for hierarchical planning. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4_CR2","unstructured":"Black, K., et\u00a0al.: $$\\pi $$0: a vision-language-action flow model for general robot control (2024). https:\/\/arxiv.org\/abs\/2410.24164"},{"key":"4_CR3","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"4_CR4","unstructured":"Brohan, A., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818 (2023)"},{"key":"4_CR5","unstructured":"Brohan, A., et\u00a0al.: Rt-1: Robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Bu, Q., et al.: UniVLA: learning to act anywhere with task-centric latent actions. arXiv preprint arXiv:2505.06111 (2025)","DOI":"10.15607\/RSS.2025.XXI.014"},{"key":"4_CR7","unstructured":"Chen, L.Y., Adebola, S., Goldberg, K.: Berkeley UR5 demonstration dataset. https:\/\/sites.google.com\/view\/berkeley-ur5\/home"},{"key":"4_CR8","unstructured":"Chen, X., et\u00a0al.: Pali-x: on scaling up a multilingual vision and language model. arXiv preprint arXiv:2305.18565 (2023)"},{"key":"4_CR9","unstructured":"Chen, Y., et al.: MOTO: latent motion token as the bridging language for robot manipulation. arXiv preprint arXiv:2412.04445 (2024)"},{"key":"4_CR10","unstructured":"Collaboration, O.X.E., et\u00a0al.: Open X-embodiment: robotic learning datasets and RT-X models. https:\/\/arxiv.org\/abs\/2310.08864 (2023)"},{"key":"4_CR11","unstructured":"Deng, S., et\u00a0al.: GraspVLA: a grasping foundation model pre-trained on billion-scale synthetic action data. arXiv preprint arXiv:2505.03233 (2025)"},{"key":"4_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"4_CR13","unstructured":"Driess, D., et\u00a0al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"4_CR14","unstructured":"Du, Y., et\u00a0al.: Video language planning. arXiv preprint arXiv:2310.10625 (2023)"},{"key":"4_CR15","unstructured":"Du, Y., et al.: Learning universal policies via text-guided video generation. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Ebert, F., et al.: Bridge data: boosting generalization of robotic skills with cross-domain datasets. CoRR arxiv:2109.13396 (2021)","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"4_CR17","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221 (2022)"},{"key":"4_CR18","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR19","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR20","unstructured":"Kim, M.J., et\u00a0al.: OpenVLA: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"4_CR21","unstructured":"Ko, P.C., Mao, J., Du, Y., Sun, S.H., Tenenbaum, J.B.: Learning to act from actionless videos through dense correspondences. arXiv:2310.08576 (2023)"},{"key":"4_CR22","unstructured":"Li, X., et al.: Evaluating real-world robot manipulation policies in simulation (2024). https:\/\/arxiv.org\/abs\/2405.05941"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Liang, Z., Mu, Y., Ma, H., Tomizuka, M., Ding, M., Luo, P.: SkillDiffuser: interpretable hierarchical planning via skill abstractions in diffusion-based task execution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16467\u201316476 (2024)","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"4_CR24","unstructured":"Liu, S., et al.: RDT-1B: a diffusion foundation model for bimanual manipulation. arXiv preprint arXiv:2410.07864 (2024)"},{"key":"4_CR25","unstructured":"OpenAI, Achiam, J., et\u00a0al.: GPT-4 technical report (2024). https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"4_CR26","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR27","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"4_CR28","unstructured":"Soni, A., et al.: VideoAgent: self-improving video generation (2024). https:\/\/arxiv.org\/abs\/2410.10076"},{"key":"4_CR29","unstructured":"Team, O.M., et al.: Octo: an open-source generalist robot policy (2024). https:\/\/arxiv.org\/abs\/2405.12213"},{"key":"4_CR30","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"4_CR31","unstructured":"Wang, B., et al.: This &that: language-gesture controlled video generation for robot planning. arXiv preprint arXiv:2407.05530 (2024)"},{"key":"4_CR32","first-page":"124420","volume":"37","author":"L Wang","year":"2024","unstructured":"Wang, L., Chen, X., Zhao, J., He, K.: Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers. Adv. Neural. Inf. Process. Syst. 37, 124420\u2013124450 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Karma: augmenting embodied AI agents with long-and-short term memory systems. arXiv preprint arXiv:2409.14908 (2024)","DOI":"10.1109\/ICRA55743.2025.11128047"},{"key":"4_CR34","unstructured":"Wen, J., et\u00a0al.: Diffusion-vla: scaling robot foundation models via unified diffusion and autoregression. arXiv preprint arXiv:2412.03293 (2024)"},{"key":"4_CR35","doi-asserted-by":"publisher","unstructured":"Xing, J., et al.: DynamiCrafter: animating open-domain images with video diffusion priors. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 399\u2013417. Springer, Heidelberg (2025). https:\/\/doi.org\/10.1007\/978-3-031-72952-2_23","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Xing, Z., et al.: A survey on video diffusion models. ACM Comput. Surv. 57, 1\u201342 (2023)","DOI":"10.1145\/3696415"},{"key":"4_CR37","unstructured":"Ye, S., et\u00a0al.: Latent action pretraining from videos. arXiv preprint arXiv:2410.11758 (2024)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-2098-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T12:01:17Z","timestamp":1761480077000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-2098-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"ISBN":["9789819520978","9789819520985"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-2098-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"27 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Okayama","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}