{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:45:29Z","timestamp":1789235129792,"version":"build-2803163510"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100017607","name":"Shenzhen Municipal Fundamental Research Program","doi-asserted-by":"crossref","award":["JCYJ20230807114202005"],"award-info":[{"award-number":["JCYJ20230807114202005"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2024B0101040004"],"award-info":[{"award-number":["2024B0101040004"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20240903104008012"],"award-info":[{"award-number":["KJZD20240903104008012"]}]},{"name":"Shenzhen Science and Technology Program","award":["ZDCY20250901113000001"],"award-info":[{"award-number":["ZDCY20250901113000001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3688078","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:49:24Z","timestamp":1777319364000},"page":"10695-10712","source":"Crossref","is-referenced-by-count":1,"title":["YOTO++: Learning Long-Horizon Closed-Loop Bimanual Manipulation From One-Shot Human Video Demonstrations"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2220-7286","authenticated-orcid":false,"given":"Huayi","family":"Zhou","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1988-4400","authenticated-orcid":false,"given":"Ruixiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Weihai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunxin","family":"Tai","sequence":"additional","affiliation":[{"name":"DexForce","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueci","family":"Deng","sequence":"additional","affiliation":[{"name":"DexForce","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7464-523X","authenticated-orcid":false,"given":"Guiliang","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2661-5700","authenticated-orcid":false,"given":"Kui","family":"Jia","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630565"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref3","first-page":"2327","article-title":"Deep imitation learning for bimanual robotic manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196958"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3445630"},{"key":"ref6","article-title":"PerAct2: Benchmarking and learning for robotic bimanual manipulation tasks","author":"Grotz","year":"2024"},{"key":"ref7","first-page":"4354","article-title":"Voxact-B: Voxel-based acting and stabilizing policy for bimanual manipulation","volume-title":"Proc. Conf. Robot. Learn.","author":"Liu","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref11","first-page":"29982","article-title":"RDT-1B: A Diffusion Foundation Model for Bimanual Manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.078"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610763"},{"key":"ref14","first-page":"3828","article-title":"Object-centric dexterous manipulation from human motion data","volume-title":"Proc. Conf. Robot. Learn.","author":"Chen","year":"2024"},{"key":"ref15","first-page":"299","article-title":"OKAMI: Teaching humanoid robots manipulation skills through single video imitation","volume-title":"Proc. Conf. Robot. Learn.","author":"Li","year":"2025"},{"key":"ref16","first-page":"318","article-title":"TieBot: Learning to knot a tie from visual demonstration through a real-to-sim-to-real approach","volume-title":"Proc. 8th Conf. Robot. Learn.","author":"Peng","year":"2024"},{"key":"ref17","first-page":"2069","article-title":"Robot see robot do: Imitating articulated object manipulation with monocular 4d reconstruction","volume-title":"Proc. Conf. Robot. Learn.","volume":"270","author":"Kerr","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref22","first-page":"785","article-title":"Perceiver-Actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot. Learn.","volume":"229","author":"Shridhar","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref25","first-page":"28085","article-title":"Sam 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3569218"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref30","first-page":"1595","article-title":"Equibot: Sim (3)-equivariant diffusion policy for generalizable and data efficient learning","volume-title":"Proc. Conf. Robot. Learn.","author":"Yang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.055"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01712"},{"key":"ref33","first-page":"2323","article-title":"ChainedDiffuser: Unifying trajectory diffusion and keypose prediction for robotic manipulation","volume-title":"Proc. Conf. Robot. Learn.","author":"Xian","year":"2023"},{"key":"ref34","first-page":"1949","article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","volume-title":"Proc. Conf. Robot. Learn.","author":"Ke","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.123"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.149"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2808924"},{"key":"ref38","first-page":"192","article-title":"FabricFlowNet: Bimanual cloth manipulation with a flow-based policy","volume-title":"Proc. Conf. Robot. Learn.","author":"Weng","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161546"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161402"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341841"},{"key":"ref42","first-page":"1887","article-title":"Dynamic handover: Throw and catch with bimanual hands","volume-title":"Proc. Conf. Robot. Learn.","author":"Huang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3381551"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160739"},{"key":"ref45","first-page":"5220","article-title":"Twisting lids off with two hands","volume-title":"Proc. Conf. Robot. Learn.","author":"Lin","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3366008"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3198020"},{"key":"ref49","article-title":"DualAfford: Learning collaborative visual affordance for dual-gripper manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3573081"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3153728"},{"key":"ref52","first-page":"563","article-title":"Stabilize to act: Learning to coordinate for bimanual manipulation","volume-title":"Proc. Conf. Robot. Learn.","author":"Grannen","year":"2023"},{"key":"ref53","first-page":"4066","article-title":"Mobile ALOHA: Learning bimanual mobile manipulation using low-cost whole-body teleoperation","volume-title":"Proc. Conf. Robot. Learn.","author":"Fu","year":"2024"},{"key":"ref54","article-title":"ALOHA 2: An enhanced low-cost hardware for bimanual teleoperation","author":"Aldaco","year":"2024"},{"key":"ref55","first-page":"19","article-title":"ALOHA unleashed: A simple recipe for robot dexterity","volume-title":"Proc. Conf. Robot. Learn.","author":"Zhao","year":"2024"},{"key":"ref56","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot. Sci. Syst.","author":"Team","year":"2024"},{"key":"ref57","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot. Learn.","author":"Kim","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128180"},{"key":"ref60","first-page":"5166","article-title":"Bimanual dexterity for complex tasks","volume-title":"Proc. Conf. Robot. Learn.","author":"Shaw","year":"2024"},{"key":"ref61","first-page":"2828","article-title":"HumanPlus: Humanoid shadowing and imitation from humans","volume-title":"Proc. Conf. Robot. Learn.","author":"Fu","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3553454"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247017"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128717"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128253"},{"key":"ref67","first-page":"2729","article-title":"Open-television: Teleoperation with immersive active visual feedback","volume-title":"Proc. Conf. Robot. Learn.","author":"Cheng","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00050"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02054"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128322"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00985"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127525"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"ref78","first-page":"40938","article-title":"Learning to act from actionless videos through dense correspondences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ko","year":"2024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.134"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2986648"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272571"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3372102"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref84","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":"ref85","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Jang","year":"2022"},{"key":"ref86","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref87","first-page":"1","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref88","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611491"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01705"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2787"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adv7594"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2004.1371616"},{"key":"ref95","first-page":"3270","article-title":"Dexterous grasping via eigengrasps: A low-dimensional approach to a high-complexity problem","volume-title":"Proc. Robot.: Sci. Syst.","author":"Ciocarlie","year":"2007"},{"key":"ref96","first-page":"46130","article-title":"CORN: Contact-based object representation for nonprehensile manipulation of general unseen objects","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cho","year":"2024"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01029"},{"key":"ref98","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Qi","year":"2017"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2004.829463"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.899621"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11495283.pdf?arnumber=11495283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:06:37Z","timestamp":1786129597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11495283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":106,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3688078","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}