{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:07Z","timestamp":1777890187513,"version":"3.51.4"},"reference-count":61,"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\/501100003422","name":"King Abdullah University of Science and Technology","doi-asserted-by":"publisher","award":["5940"],"award-info":[{"award-number":["5940"]}],"id":[{"id":"10.13039\/501100003422","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\/iccv51701.2025.01067","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11469-11479","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion-Based Imaginative Coordination for Bimanual Manipulation"],"prefix":"10.1109","author":[{"given":"Huilin","family":"Xu","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Ding","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiakun","family":"Xu","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixiang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Chen","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinjie","family":"Mai","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Xu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898330"},{"key":"ref2","first-page":"2","article-title":"$\\pi_{0}:$ A vision-languageaction flow model for general robot control","author":"Black","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","first-page":"3","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":"10.1016\/j.promfg.2020.01.043"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196958"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769891"},{"key":"ref9","first-page":"3","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0403"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","first-page":"3","article-title":"Cosmos world foundation model platform for physical ai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3295249"},{"key":"ref14","first-page":"8","article-title":"Mobile aloha: Learning bimanual mobile manipulation with lowcost whole-body teleoperation","volume-title":"Conference on Robot Learning (CoRL)","author":"Fu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610763"},{"key":"ref16","first-page":"2","article-title":"Dag-plan: Generating directed acyclic dependency graphs for dual-arm cooperative planning","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"563","article-title":"Stabilize to act: Learning to coordinate for bimanual manipulation","volume-title":"Conference on Robot Learning","author":"Grannen","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref19","first-page":"2","article-title":"Peract2: Benchmarking and learning for robotic bimanual manipulation tasks","volume-title":"CoRL 2024 Workshop on Whole-body Control and Bimanual Manipulation: Applications in Humanoids and Beyond","author":"Grotz","year":"2024"},{"key":"ref20","first-page":"5","article-title":"Maniskill2: A unified benchmark for generalizable manipulation skills","volume-title":"International Conference on Learning Representations","author":"Gu","year":"2023"},{"key":"ref21","first-page":"3","article-title":"Prediction with action: Visual policy learning via joint denoising process","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Guo","year":"2024"},{"key":"ref22","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"International Conference on Learning Representations","author":"Hafner","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2011.6181638"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Learning manipulation by predicting interaction","volume-title":"Proceedings of Robotics: Science and Systems (RSS)","author":"Jia","year":"2024"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3526436"},{"key":"ref29","article-title":"Planning-guided diffusion policy learning for generalizable contact-rich bimanual manipulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160739"},{"key":"ref31","article-title":"Voxact-b: Voxel-based acting and stabilizing policy for bimanual manipulation","volume-title":"Conference on Robot Learning","author":"Arthur Liu","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3153728"},{"key":"ref33","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Anybimanual: Transferring unimanual policy for general bimanual manipulation","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"3","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2016.xii.019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"ref38","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196839"},{"key":"ref40","first-page":"4","article-title":"Action-conditional video prediction using deep networks in atari games","volume":"28","author":"Oh","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref41","first-page":"2","article-title":"Bimanual long-horizon manipulation via temporalcontext transformer rl","author":"Oh","year":"2024","journal-title":"IEEE Robotics and Automation Letters"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/978-1-84800-015-5","volume-title":"Distributed consensus in multi-vehicle cooperative control","author":"Ren","year":"2008"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.07.005"},{"key":"ref45","first-page":"1","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref46","first-page":"3","article-title":"Predictive inverse dynamics models are scalable learners for robotic manipulation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Tian","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref48","first-page":"3","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord Den","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802181"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1298"},{"key":"ref51","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"International Conference on Learning Representations","author":"Wu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.10.007"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1451055"},{"key":"ref54","article-title":"Latent action pretraining from videos","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ye","year":"2025"},{"key":"ref55","first-page":"2","article-title":"Bikc: Keypose-conditioned consistency policy for bimanual robotic manipulation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref57","first-page":"2","article-title":"Empowering embodied manipulation: A bimanual-mobile robot manipulation dataset for household tasks","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3550849"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref60","first-page":"2","article-title":"ALOHA unleashed: A simple recipe for robot dexterity","volume-title":"8th Annual Conference on Robot Learning","author":"Zhao","year":"2024"},{"key":"ref61","article-title":"Dualafford: Learning collaborative visual affordance for dual-gripper manipulation","volume-title":"International Conference on Learning Representations","author":"Zhao","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\/11444784.pdf?arnumber=11444784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:09Z","timestamp":1777613409000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01067","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}