{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:09Z","timestamp":1777865349907,"version":"3.51.4"},"reference-count":57,"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\/iccv51701.2025.01029","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11058-11068","source":"Crossref","is-referenced-by-count":0,"title":["DyWA: Dynamics-Adaptive World Action Model for Generalizable Non-Prehensile Manipulation"],"prefix":"10.1109","author":[{"given":"Jiangran","family":"Lyu","sequence":"first","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Li","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuesong","family":"Shi","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyi","family":"Xu","sequence":"additional","affiliation":[{"name":"Galbot"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Computer Science, Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"issue":"119","key":"ref2","first-page":"16","article-title":"Introduction to inverse kinematics with jacobian transpose, pseudoinverse and damped least squares methods","volume":"17","author":"Buss","year":"2004","journal-title":"IEEE Journal of Robotics and Automation"},{"key":"ref3","article-title":"Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation","author":"Cheang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Drivinggpt: Unifying driving world modeling and planning with multi-modal autoregressive transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Scaling offline model-based rl via jointly-optimized world-action model pretraining","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811872"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref8","article-title":"Corn: Contact-based object representation for nonprehensile manipulation of general unseen objects","volume-title":"12th International Conference on Learning Representations, ICLR 2024. International Conference on Learning Representations, ICLR","author":"Cho","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802523"},{"key":"ref10","first-page":"1","article-title":"Learning visuotactile estimation and control for non-prehensile manipulation under occlusions","volume-title":"The 8th Conference on Robot Learning","author":"Del Aguila Ferrandis","year":"2024"},{"key":"ref11","article-title":"Prediction with action: Visual policy learning via joint denoising process","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Guo","year":"2024"},{"key":"ref12","article-title":"Recurrent world models facilitate policy evolution","volume":"31","author":"Ha","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Mastering atari with discrete world models","author":"Hafner","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794366"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1505"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.129"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341657"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref21","article-title":"Enhancing exploration with diffusion policies in hybrid off-policy rl: Application to nonprehensile manipulation","author":"Le","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"22554","article-title":"An analysis of svd for deep rotation estimation","volume":"33","author":"Levinson","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","first-page":"679","article-title":"Learning preconditions of hybrid force-velocity controllers for contact-rich manipulation","volume-title":"Conference on Robot Learning","author":"Liang","year":"2023"},{"key":"ref24","volume-title":"Polymetis","author":"Lin","year":"2021"},{"key":"ref25","article-title":"Scissorbot: Learning generalizable scissor skill for paper cutting via simulation, imitation, and sim2real","volume-title":"8th Annual Conference on Robot Learning","author":"Lyu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548257"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00909"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref30","article-title":"Follow-your-creation: Empowering 4d creation through video inpainting","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32643"},{"key":"ref32","article-title":"Follow-your-motion: Video motion transfer via efficient spatial-temporal decoupled finetuning","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922067762"},{"key":"ref34","first-page":"137","article-title":"Contact-invariant optimization for hand manipulation","volume-title":"Proceedings of the ACM SIGGRAPH\/Eurographics symposium on computer animation","author":"Mordatch","year":"2012"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185539"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811942"},{"key":"ref37","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"Andrew","year":"1999","journal-title":"Icml"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"},{"key":"ref41","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","volume":"30","author":"Ruizhongtai Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"Sofar: Language-grounded orientation bridges spatial reasoning and object manipulation","author":"Qi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref43","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to noregret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Ross","year":"2011"},{"key":"ref44","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"International conference on machine learning","author":"Sekar","year":"2020"},{"key":"ref45","article-title":"Asgrasp: Generalizable transparent object reconstruction and grasping from rgb-d active stereo camera","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref48","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.035"},{"issue":"2","key":"ref50","first-page":"6","article-title":"Learning interactive real-world simulators","volume":"1","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.012"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758091"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161271"},{"key":"ref55","first-page":"150","article-title":"Learning to grasp the ungraspable with emergent extrinsic dexterity","volume-title":"Conference on Robot Learning","author":"Zhou","year":"2023"},{"key":"ref56","first-page":"241","article-title":"Hacman: Learning hybrid actor-critic maps for 6d non-prehensile manipulation","volume-title":"Conference on Robot Learning","author":"Zhou","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.015"}],"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\/11445531.pdf?arnumber=11445531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:42Z","timestamp":1777529922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01029","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}