{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:16:38Z","timestamp":1777889798405,"version":"3.51.4"},"reference-count":42,"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\/iccv51701.2025.01112","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11958-11968","source":"Crossref","is-referenced-by-count":0,"title":["EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow"],"prefix":"10.1109","author":[{"given":"Yixiang","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiyan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiabing","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehan","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,New Laboratory of Pattern Recognition (NLPR)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref2","article-title":"$\\pi_{0}:$ A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint arXiv"},{"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"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","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 arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref7","article-title":"Learning universal policies via text-guided video generation","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Video language planning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Du","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref10","article-title":"FLIP: Flow-centric generative planning as general-purpose manipulation world model","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Gao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos","author":"Karaev","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","first-page":"2679","article-title":"Openvla: An opensource vision-language-action model","volume-title":"In Proceedings of The 8th Conference on Robot Learning","author":"Jin Kim"},{"key":"ref16","article-title":"Learning to act from actionless videos through dense correspondences","volume-title":"The Twelfth International Conference on Learning Representations","author":"Ko"},{"key":"ref17","article-title":"Bridgevla: Input-output alignment for efficient 3d manipulation learning with vision-language models","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3526436"},{"key":"ref19","article-title":"Dreamitate: Real-world visuomotor policy learning via video generation","volume-title":"In 8th Annual Conference on Robot Learning","author":"Liang"},{"key":"ref20","article-title":"RDT-1b: a diffusion foundation model for bimanual manipulation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Liu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"ref22","first-page":"892","article-title":"R3m: A universal visual representation for robot manipulation","volume-title":"In Proceedings of The 6th Conference on Robot Learning","author":"Nair"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01327"},{"key":"ref24","article-title":"Octo: An open-source generalist robot policy","volume-title":"In Proceedings of Robotics: Science and Systems","author":"Model Team"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International Conference on Machine Learning","author":"Radford"},{"key":"ref27","article-title":"SAM 2: Segment anything in images and videos","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ravi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128834"},{"key":"ref29","article-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref31","article-title":"Denoising diffusion implicit models","volume-title":"In International Conference on Learning Representations","author":"Song"},{"key":"ref32","article-title":"Open xembodiment: Robotic learning datasets and RT-x models","author":"Vuong","year":"2023","journal-title":"In Towards Generalist Robots: Learning Paradigms for Scalable Skill Acquisition @ CoRL2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.092"},{"key":"ref34","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"In International Conference on Learning Representations","author":"Wu"},{"key":"ref35","article-title":"Flow as the cross-domain manipulation interface","volume-title":"In 8th Annual Conference on Robot Learning","author":"Xu"},{"key":"ref36","article-title":"Learning interactive real-world simulators","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Yang"},{"key":"ref37","article-title":"Metaworld: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"In Conference on Robot Learning","author":"Yu"},{"key":"ref38","article-title":"Dexgraspnet 2.0: Learning generative dexterous grasping in largescale synthetic cluttered scenes","volume-title":"2nd Workshop on Dexterous Manipulation: Design, Perception and Control (RSS)","author":"Yu","year":"2024"},{"key":"ref39","article-title":"General flow as foundation affordance for scalable robot learning","volume-title":"In 8th Annual Conference on Robot Learning","author":"Yuan"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.106"},{"key":"ref41","article-title":"VIOLA: Object-centric imitation learning for vision-based robot manipulation","volume-title":"In 6th Annual Conference on Robot Learning","author":"Zhu"},{"key":"ref42","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"In Conference on Robot Learning","author":"Zitkovich"}],"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\/11443440.pdf?arnumber=11443440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:20:01Z","timestamp":1777612801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01112","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}