{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T22:23:14Z","timestamp":1771366994182,"version":"3.50.1"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2024YFB4708900"],"award-info":[{"award-number":["2024YFB4708900"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2025"],"award-info":[{"award-number":["624B2025"]}],"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":["62473050"],"award-info":[{"award-number":["62473050"]}],"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":["92370203"],"award-info":[{"award-number":["92370203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tro.2026.3658211","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T20:31:39Z","timestamp":1769545899000},"page":"1158-1177","source":"Crossref","is-referenced-by-count":0,"title":["Learning From Videos Through Graph-to-Graphs Generative Modeling for Robotic Manipulation"],"prefix":"10.1109","volume":"42","author":[{"given":"Guangyan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3618-7423","authenticated-orcid":false,"given":"Meiling","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3265-3148","authenticated-orcid":false,"given":"Te","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengcai","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengxiao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicai","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianxing","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinran","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3964-2433","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6628-7946","authenticated-orcid":false,"given":"Yufeng","family":"Yue","sequence":"additional","affiliation":[{"name":"School of Automation, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","first-page":"6892","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. Towards Generalist Robots: Learn. Paradigms Scalable Skill Acquisition","author":"Collaboration","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref6","first-page":"416","article-title":"Real-world robot learning with masked visual pre-training","volume-title":"Proc. Conf. Robot Learn.","author":"Radosavovic","year":"2022"},{"key":"ref7","first-page":"892","article-title":"R3M: A universal visual representation for robot manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Nair","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.012"},{"key":"ref9","first-page":"537","article-title":"XIRL: Cross-embodiment inverse reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Zakka","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.026"},{"key":"ref11","first-page":"13129","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sharma","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref14","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"ref16","first-page":"1541","article-title":"General flow as foundation affordance for scalable robot learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yuan","year":"2025"},{"key":"ref17","first-page":"2475","article-title":"Flow as the cross-domain manipulation interface","volume-title":"Proc. Conf. Robot Learn.","author":"Xu","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00171"},{"key":"ref19","article-title":"OPEN TEACH: A versatile teleoperation system for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Iyer","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2956365"},{"key":"ref23","first-page":"18284","article-title":"The magical benchmark for robust imitation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Toyer","year":"2020"},{"key":"ref24","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981402"},{"key":"ref26","first-page":"2837","article-title":"Improved contrastive divergence training of energy based models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2021"},{"key":"ref27","first-page":"3732","article-title":"Learning the stein discrepancy for training and evaluating energy-based models without sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grathwohl","year":"2020"},{"key":"ref28","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Proc. Conf. robot Learn.","author":"Florence","year":"2022"},{"key":"ref29","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref30","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","article-title":"Training diffusion models with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Black","year":"2024"},{"key":"ref33","article-title":"Is conditional generative modeling all you need for decision-making?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ajay","year":"2023"},{"key":"ref34","article-title":"CARP: Visuomotor policy learning via coarse-to-fine autoregressive prediction","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Gong","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01558"},{"key":"ref36","first-page":"649","article-title":"Sparse diffusion policy: A sparse, reusable, and flexible policy for robot learning","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2025"},{"key":"ref37","article-title":"RDT-1B: A diffusion foundation model for bimanual manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref38","article-title":"Language control diffusion: Efficiently scaling through space, time, and tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref42","first-page":"1930","article-title":"Model-based inverse reinforcement learning from visual demonstrations","volume-title":"Proc. Conf. Robot Learn.","author":"Das","year":"2021"},{"key":"ref43","first-page":"654","article-title":"VideoDex: Learning dexterity from internet videos","volume-title":"Proc. Conf. Robot Learn.","author":"Shaw","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref45","first-page":"68760","article-title":"Video prediction models as rewards for reinforcement learning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Escontrela","year":"2024"},{"key":"ref46","article-title":"Learning interactive real-world simulators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"ref48","first-page":"6013","article-title":"CoTracker3: Simpler and better point tracking by pseudo-labelling real videos","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Karaev","year":"2025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"ref51","article-title":"Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.047"},{"key":"ref53","first-page":"2971","article-title":"RoboCook: Long-horizon elasto-plastic object manipulation with diverse tools","volume-title":"Proc. Conf. Robot Learn.","author":"Shi","year":"2023"},{"key":"ref54","first-page":"256","article-title":"Learning visible connectivity dynamics for cloth smoothing","volume-title":"Proc. Conf. Robot Learn.","author":"Lin","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793509"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231219020"},{"key":"ref58","first-page":"8459","article-title":"Learning to simulate complex physics with graph networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sanchez-Gonzalez","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.010"},{"key":"ref60","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2981333"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161234"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611654"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2023.104452"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2025.3530267"},{"key":"ref67","first-page":"979","article-title":"Graph-structured visual imitation","volume-title":"Proc. Conf. Robot Learn.","author":"Sieb","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00876"},{"key":"ref69","first-page":"55","article-title":"Graph inverse reinforcement learning from diverse videos","volume-title":"Proc. Conf. Robot Learn.","author":"Kumar","year":"2023"},{"key":"ref70","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton","year":"2017"},{"key":"ref71","first-page":"1","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu","year":"2019"},{"key":"ref72","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref73","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2475"},{"key":"ref75","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref86","first-page":"12381","article-title":"Root mean square layer normalization","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2019"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"ref89","first-page":"44776","article-title":"LIBERO: Benchmarking knowledge transfer for lifelong robot learning","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2021.3138382"},{"key":"ref91","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023"},{"key":"ref92","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref94","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":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref96","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref97","article-title":"MimicGen: A data generation system for scalable robot learning using human demonstrations","volume-title":"Proc. Conf. Robot Learn.","author":"Mandlekar","year":"2023"},{"key":"ref98","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref99","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer","year":"2017"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8860\/11297026\/11365992.pdf?arnumber=11365992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T21:11:32Z","timestamp":1771362692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11365992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":99,"URL":"https:\/\/doi.org\/10.1109\/tro.2026.3658211","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}