{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:45:54Z","timestamp":1780105554921,"version":"3.54.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01837","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19752-19763","source":"Crossref","is-referenced-by-count":2,"title":["Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos"],"prefix":"10.1109","author":[{"given":"Yi","family":"Chen","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuying","family":"Ge","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiliang","family":"Tang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhuo","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixiao","family":"Ge","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"ref2","article-title":"$\\pi_{0}:$ A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Zero-shot robotic manipulation with pre-trained image-editing diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Black","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Genie: Generative interactive environments","volume-title":"Forty-first International Conference on Machine Learning","author":"Bruce","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4411"},{"key":"ref8","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","volume-title":"Berkeley UR5 demonstration dataset","author":"Yunliang Chen"},{"key":"ref10","article-title":"Igor: Image-goal representations are the atomic control units for foundation models in embodied ai","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1069"},{"key":"ref13","author":"Dass","year":"2023","journal-title":"Clvr jaco play dataset"},{"key":"ref14","article-title":"Scaling cross-embodied learning: One policy for manipulation, navigation, locomotion and aviation","volume-title":"8th Annual Conference on Robot Learning","author":"Doshi","year":"2024"},{"key":"ref15","first-page":"8469","article-title":"Palm-e: An embodied multimodal language model","volume-title":"International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref16","article-title":"Learning universal policies via text-guided video generation","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1578"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref21","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"International Conference on Learning Representations","author":"Hafner","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4484"},{"key":"ref23","article-title":"Learning an actionable discrete diffusion policy via large-scale actionless video pre-training","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"He","year":"2024"},{"key":"ref24","first-page":"16000","article-title":"asked autoencoders are scalable vision learners","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"He","year":"2022"},{"key":"ref25","first-page":"14975","article-title":"Vima: robot manipulation with multimodal prompts","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Jiang","year":"2023"},{"key":"ref26","article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","volume-title":"ICRA 2024 Workshop-Back to the Future: Robot Learning Going Probabilistic","author":"Ke","year":"2024"},{"key":"ref27","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Learning to act from actionless videos through dense correspondences","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ko","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3526436"},{"key":"ref30","article-title":"Cogact: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Evaluating real-world robot manipulation policies in simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"The Twelfth In-ternational Conference on Learning Representations","author":"Li","year":"2024"},{"key":"ref33","article-title":"Dreamitate: Real-world visuomotor policy learning via video generation","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref35","article-title":"Robouniview: Visual-language model with unified view representation for robotic manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Multistage cable routing through hierarchical imitation learning","author":"Luo","year":"2023","journal-title":"arXiv pre-print"},{"key":"ref37","article-title":"VIP: Towards universal visual reward and representation via value-implicit pre-training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Jason Ma","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968114"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref41","article-title":"Octo: An opensource generalist robot policy","volume-title":"First Workshop on VisionLanguage Models for Navigation and Manipulation at ICRA 2024","author":"Mees","year":"2024"},{"key":"ref42","first-page":"892","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"Conference on Robot Learning","author":"Nair","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref44","author":"Pari","year":"2021","journal-title":"The surprising effectiveness of representation learning for visual imitation"},{"key":"ref45","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"issue":"140","key":"ref46","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref47","article-title":"A generalist agent. Transactions on Machine Learning Research, 2022","author":"Reed","journal-title":"Featured Certification, Outstanding Certification"},{"key":"ref48","author":"Rosete-Beas","year":"2022","journal-title":"Latent plans for task agnostic offline reinforcement learning"},{"key":"ref49","article-title":"Learning to act without actions","author":"Schmidt","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref52","article-title":"Open xembodiment: Robotic learning datasets and RT-x models","author":"Vuong","year":"2023","journal-title":"Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition @ CoRL2023"},{"key":"ref53","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke","year":"2023"},{"key":"ref54","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu","year":"2024"},{"key":"ref55","article-title":"ivideoGPT: Interactive videoGPTs are scalable world models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wu","year":"2024"},{"key":"ref56","article-title":"Learning interactive real-world simulators","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang","year":"2024"},{"key":"ref57","article-title":"Video as the new language for real-world decision making","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Latent action pretraining from videos","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"3d-vla: A 3d vision-language-action generative world model","author":"Zhen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160594"},{"key":"ref61","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"6th Annual Conference on Robot Learning (CoRL)","author":"Zhu","year":"2022"},{"key":"ref62","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich","year":"2023"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446155.pdf?arnumber=11446155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:22:04Z","timestamp":1777612924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446155\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01837","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}