{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:01:28Z","timestamp":1777888888577,"version":"3.51.4"},"reference-count":48,"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"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24511103100"],"award-info":[{"award-number":["24511103100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00669","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["Spatial-Temporal Aware Visuomotor Diffusion Policy Learning"],"prefix":"10.1109","author":[{"given":"Zhenyang","family":"Liu","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yikai","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuanning","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longfei","family":"Liang","sequence":"additional","affiliation":[{"name":"NeuHelium Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160275"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref6","first-page":"5531","article-title":"Bayesian imitation learning for end-to-end mobile manipulation","volume-title":"International Conference on Machine Learning","author":"Du","year":"2022"},{"key":"ref7","first-page":"158","article-title":"Ramirez, Ayzaan Wahid, Laura Downs, Adrian Wong, Johnny Lee, Igor Mordatch, and Jonathan Tompson","volume-title":"Conference on robot learning","author":"Florence","year":"2022"},{"key":"ref8","article-title":"Recurrent world models facilitate policy evolution","volume":"31","author":"Ha","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"arXiv preprint","author":"Hafner","year":"2019"},{"key":"ref10","article-title":"Mastering atari with discrete world models","volume-title":"arXiv preprint","author":"Hafner","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.009"},{"key":"ref13","article-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline","volume-title":"arXiv preprint","author":"Hansen","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1505"},{"key":"ref16","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref20","article-title":"Openvla: An open-source vision-language-action model","volume-title":"arXiv preprint","author":"Kim","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3526436"},{"key":"ref22","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","volume-title":"arXiv preprint","author":"Liu","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00352"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754918"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref26","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"arXiv preprint","author":"Mandlekar","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3136"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.064"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv preprint","author":"Schulman","year":"2017"},{"key":"ref32","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Conference on Robot Learning","author":"Seo","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1668"},{"key":"ref34","article-title":"On bringing robots home","volume-title":"arXiv preprint","author":"Muhammad","year":"2023"},{"key":"ref35","first-page":"785","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar","year":"2023"},{"key":"ref36","volume-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2389"},{"key":"ref38","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","volume-title":"arXiv preprint","author":"Wang","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref40","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","volume-title":"arXiv preprint","author":"Wang","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref43","article-title":"Policy representation via diffusion probability model for reinforcement learning","volume-title":"arXiv preprint","author":"Yang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref45","article-title":"Generalized animal imitator: Agile locomotion with versatile motion prior","volume-title":"arXiv preprint","author":"Yang","year":"2023"},{"key":"ref46","first-page":"284","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on Robot Learning","author":"Ze","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2473"}],"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\/11445021.pdf?arnumber=11445021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:28Z","timestamp":1777611688000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00669","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}