{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:42Z","timestamp":1777888722232,"version":"3.51.4"},"reference-count":50,"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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["92470202,U21A20471"],"award-info":[{"award-number":["92470202,U21A20471"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01155","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12427-12437","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework"],"prefix":"10.1109","author":[{"given":"Jian-Jian","family":"Jiang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Xiang","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ling-An","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Lin","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dandan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Imperial College,Imperial-X Initiative and Department of Bioengineering,London,U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3504792"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00169"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref5","article-title":"Learning robotic manipulation policies from point clouds with conditional flow matching","volume-title":"In Conference on Robot Learning","author":"Chisari"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref9","article-title":"Peract2: Benchmarking and learning for robotic bimanual manipulation tasks","volume-title":"Conference on Robot Learning","author":"Grotz","year":"2024"},{"key":"ref10","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"ACE: off-policy actor-critic with causalityaware entropy regularization","volume-title":"In International Conference on Machine Learning","author":"Ji"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2023.3262461"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78113-1_22"},{"key":"ref14","article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","author":"Ke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Surgical robot transformer (SRT): imitation learning for surgical tasks","volume-title":"In Conference on Robot Learning","author":"Woong Kim"},{"key":"ref16","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref18","article-title":"Interact: Inter-dependency aware action chunking with hierarchical attention transformers for bimanual manipulation","volume-title":"In Conference on Robot Learning","author":"Lee"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref21","article-title":"Flow matching for generative modeling","volume-title":"In International Conference on Learning Representations","author":"Lipman"},{"key":"ref22","article-title":"Voxact-b: Voxel-based acting and stabilizing policy for bimanual manipulation","volume-title":"In Conference on Robot Learning","author":"Arthur Liu"},{"key":"ref23","article-title":"RDT-1B: a diffusion foundation model for bimanual manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_20"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610040"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01712"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/9.262032"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835519"},{"key":"ref31","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"In Conference on Robot Learning","author":"Shridhar"},{"key":"ref32","article-title":"Denoising diffusion implicit models","volume-title":"In International Conference on Learning Representations","author":"Song"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128749"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1487"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01099"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"ref38","article-title":"Learning score-based grasping primitive for human-assisting dexterous grasping","author":"Wu","year":"2023","journal-title":"In Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-73383-3_21","article-title":"An economic framework for 6-dof grasp detection","volume-title":"In European Conference on Computer Vision","author":"Wu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref41","article-title":"Drm: Mastering visual reinforcement learning through dormant ratio minimization","volume-title":"In International Conference on Learning Representations","author":"Xu"},{"key":"ref42","article-title":"Gnfactor: Multi-task real robot learning with generalizable neural feature fields","volume-title":"In Conference on Robot Learning","author":"Ze"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref44","article-title":"Empowering embodied manipulation: A bimanual-mobile robot manipulation dataset for household tasks","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02100"},{"key":"ref48","article-title":"Exploring the limits of vision-language-action ma-nipulations in cross-task generalization","author":"Zhou","year":"2025","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3366008"},{"key":"ref50","article-title":"RT-2: vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich","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\/11444689.pdf?arnumber=11444689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:53Z","timestamp":1777611233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01155","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}