{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:40:03Z","timestamp":1779385203237,"version":"3.53.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation","award":["2423068"],"award-info":[{"award-number":["2423068"]}]},{"DOI":"10.13039\/100000199","name":"U.S. Department of Agriculture","doi-asserted-by":"publisher","award":["2023-67021-39072"],"award-info":[{"award-number":["2023-67021-39072"]}],"id":[{"id":"10.13039\/100000199","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000199","name":"U.S. Department of Agriculture","doi-asserted-by":"publisher","award":["2024-67021-42878"],"award-info":[{"award-number":["2024-67021-42878"]}],"id":[{"id":"10.13039\/100000199","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/lra.2025.3542317","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T18:34:32Z","timestamp":1739558072000},"page":"3350-3357","source":"Crossref","is-referenced-by-count":1,"title":["VILP: Imitation Learning With Latent Video Planning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2789-1910","authenticated-orcid":false,"given":"Zhengtong","family":"Xu","sequence":"first","affiliation":[{"name":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2610-3502","authenticated-orcid":false,"given":"Qiang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5914-3573","authenticated-orcid":false,"given":"Yu","family":"She","sequence":"additional","affiliation":[{"name":"School of Industrial Engineering, Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref2","article-title":"Video language planning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du","year":"2024"},{"key":"ref3","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Du","year":"2024"},{"key":"ref4","article-title":"Learning to act from actionless video through dense correspondences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ko","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref7","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021"},{"key":"ref8","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. Robot Learn.","author":"Florence","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref10","article-title":"Behavior generation with latent actions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2024"},{"key":"ref11","article-title":"Deep generative models in robotics: A survey on learning from multimodal demonstrations","author":"Urain","year":"2024"},{"key":"ref12","article-title":"Learning interactive real-world simulators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref13","article-title":"Seer: Language instructed video prediction with latent diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2024"},{"key":"ref14","article-title":"Dreamitate: Real-world visuomotor policy learning via video generation","volume-title":"Proc. Conf. Robot Learn.","author":"Liang","year":"2024"},{"key":"ref15","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref16","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref17","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref21","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2022"},{"key":"ref22","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","article-title":"UniT: Unified tactile representation for robot learning","author":"Xu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3486542"},{"key":"ref28","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng","year":"2021"},{"key":"ref29","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Mandlekar","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.016"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10893718\/10887293-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10893718\/10887293.pdf?arnumber=10887293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T18:57:31Z","timestamp":1740769051000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":30,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3542317","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}