{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:04Z","timestamp":1777888624205,"version":"3.51.4"},"reference-count":70,"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\/iccv51701.2025.01268","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13662-13672","source":"Crossref","is-referenced-by-count":0,"title":["AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulation"],"prefix":"10.1109","author":[{"given":"Guanxing","family":"Lu","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tengbo","family":"Yu","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyuan","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Season Si","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents","author":"Ahn","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898330"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981402"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246899"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11916277_39"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095109"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref8","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning (CoRL)","author":"Brohan","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2020.01.043"},{"key":"ref10","article-title":"Pali-3 vision language models: Smaller, faster, stronger","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref12","article-title":"Open-television: Teleoperation with immersive active visual feedback","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref14","article-title":"Intrinsic motivation for encouraging synergistic behavior","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Chitnis","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196958"},{"key":"ref16","article-title":"Active vision might be all you need: Exploring active vision in bimanual robotic manipulation","author":"Chuang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"6892","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Collaboration","year":"2024"},{"key":"ref18","article-title":"Bunny-visionpro: Real-time bimanual dexterous teleoperation for imitation learning","author":"Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2023.3295249"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00102"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160763"},{"key":"ref22","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561980"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610763"},{"key":"ref25","article-title":"Dag-plan: Generating directed acyclic dependency graphs for dual-arm cooperative planning","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SMC54092.2024.10831380"},{"key":"ref27","first-page":"694","article-title":"Rvt: Robotic view transformer for 3d object manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Goyal","year":"2023"},{"key":"ref28","first-page":"782","article-title":"Untangling dense knots by learning task-relevant keypoints","volume-title":"Conference on Robot Learning (CoRL)","author":"Grannen","year":"2020"},{"key":"ref29","first-page":"563","article-title":"Stabilize to act: Learning to coordinate for bimanual manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Grannen","year":"2023"},{"key":"ref30","article-title":"Peract2: Benchmarking and learning for robotic bimanual manipulation tasks","volume-title":"Conference on Robot Learning (CoRL)","author":"Grotz","year":"2024"},{"key":"ref31","first-page":"24","article-title":"Flingbot: The unreasonable effectiveness of dynamic manipulation for cloth unfolding","volume-title":"Conference on Robot Learning (CoRL)","author":"Ha","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3285478"},{"key":"ref33","first-page":"540","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","volume-title":"Conference on Robot Learning (CoRL)","author":"Huang","year":"2023"},{"key":"ref34","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Jaegle","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610434"},{"key":"ref37","article-title":"Bi-manual manipulation and attachment via sim-to-real reinforcement learning","author":"Kataoka","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","author":"Ke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref40","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref43","article-title":"Llm+p: Empowering large language models with optimal planning proficiency","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Voxact-b: Voxel-based acting and stabilizing policy for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462870"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref49","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Shridhar","year":"2023"},{"key":"ref50","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802181"},{"key":"ref54","first-page":"1723","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning (CoRL)","author":"Walke","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref56","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2024","journal-title":"Transactions on Machine Learning Research (TMLR), 2024"},{"key":"ref57","first-page":"1132","article-title":"Influencing towards stable multi-agent interactions","volume-title":"Conference on Robot Learning (CoRL)","author":"Wang","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2044470"},{"key":"ref59","article-title":"Gello: A general, low-cost, and intuitive teleoperation framework for robot manipulators","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","first-page":"2323","article-title":"Chaineddiffuser: Unifying trajectory diffusion and keypose prediction for robotic manipulation","volume-title":"Conference on Robot Learning (CoRL)","author":"Xian","year":"2023"},{"key":"ref61","article-title":"Deep imitation learning for bimanual robotic manipulation","author":"Xie","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref62","article-title":"Ace: A cross-platform visual-exoskeletons system for low-cost dexterous teleoperation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2014.6974516"},{"key":"ref64","article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"You","year":"2020"},{"key":"ref65","article-title":"Bikc: Keypose-conditioned consistency policy for bimanual robotic manipulation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","first-page":"284","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"Conference on Robot Learning (CoRL)","author":"Ze","year":"2023"},{"key":"ref67","first-page":"302","article-title":"Bootstrap your own skills: Learning to solve new tasks with large language model guidance","volume-title":"Conference on Robot Learning (CoRL)","author":"Zhang","year":"2023"},{"key":"ref68","article-title":"Dair: Disentangled attention intrinsic regularization for safe and efficient bimanual manipulation","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Empowering embodied manipulation: A bimanual-mobile robot manipulation dataset for household tasks","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"}],"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\/11444319.pdf?arnumber=11444319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:51:32Z","timestamp":1777611092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01268","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}