{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:23:16Z","timestamp":1780579396477,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322607"],"award-info":[{"award-number":["62322607"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236010"],"award-info":[{"award-number":["62236010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276261"],"award-info":[{"award-number":["62276261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2021128"],"award-info":[{"award-number":["2021128"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/lra.2025.3526436","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T19:50:28Z","timestamp":1736193028000},"page":"1912-1919","source":"Crossref","is-referenced-by-count":12,"title":["GR-MG: Leveraging Partially-Annotated Data via Multi-Modal Goal-Conditioned Policy"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8404-5779","authenticated-orcid":false,"given":"Peiyan","family":"Li","sequence":"first","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6442-8159","authenticated-orcid":false,"given":"Hongtao","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8239-7229","authenticated-orcid":false,"given":"Yan","family":"Huang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1992-4644","authenticated-orcid":false,"given":"Chilam","family":"Cheang","sequence":"additional","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-8647","authenticated-orcid":false,"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9412-1457","authenticated-orcid":false,"given":"Tao","family":"Kong","sequence":"additional","affiliation":[{"name":"ByteDance Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref3","article-title":"Octo: An open-source generalist robot policy","volume-title":"Proc. Robot.: Sci. Syst.","author":"Team","year":"2024"},{"key":"ref4","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2024"},{"key":"ref5","article-title":"Vision-language foundation models as effective robot imitators","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref6","article-title":"AutoRT: Embodied foundation models for large scale orchestration of robotic agents","author":"Ahn","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.047"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.012"},{"key":"ref12","first-page":"24639","article-title":"Video pretraining (VPT): Learning to act by watching unlabeled online videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Baker","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref14","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","volume-title":"12th Int. Conf. Learn. Representations","author":"Black","year":"2024"},{"key":"ref15","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Du","year":"2024"},{"key":"ref16","article-title":"Video language planning","author":"Du","year":"2023","journal-title":"12th Int. Conf. Learn. Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611293"},{"key":"ref19","article-title":"Robocat: A self-improving foundation agent for robotic manipulation","author":"Bousmalis","year":"2023"},{"key":"ref20","article-title":"ViNT: A foundation model for visual navigation","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.121"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref24","article-title":"VIMA: General robot manipulation with multimodal prompts","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Jiang","year":"2023"},{"key":"ref25","article-title":"Mutex: Learning unified policies from multimodal task specifications","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref27","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"Proc. 6th Annu. Conf. Robot Learn.","author":"Nair","year":"2022"},{"key":"ref28","article-title":"Masked visual pre-training for motor control","author":"Xiao","year":"2022"},{"key":"ref29","first-page":"655","article-title":"Where are we in the search for an artificial visual cortex for embodied intelligence?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Majumdar","year":"2023"},{"key":"ref30","article-title":"Learning interactive real-world simulators","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"issue":"140","key":"ref32","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"8","key":"ref33","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref37","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref38","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref39","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3466076"},{"key":"ref41","article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","author":"Ke","year":"2024"},{"key":"ref42","article-title":"OpenVLA: An open-source vision-language-action model","author":"Kim","year":"2024"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10805214\/10829675.pdf?arnumber=10829675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:03:59Z","timestamp":1737399839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10829675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":42,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3526436","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}