{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:19Z","timestamp":1765520179591,"version":"3.48.0"},"reference-count":40,"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\/iros60139.2025.11246732","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"6203-6210","source":"Crossref","is-referenced-by-count":0,"title":["RoboSwap: A GAN-driven Video Diffusion Framework For Unsupervised Robot Arm Swapping"],"prefix":"10.1109","author":[{"given":"Yang","family":"Bai","sequence":"first","affiliation":[{"name":"Ludwig Maximilian University of Munich"}]},{"given":"Liudi","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center"}]},{"given":"George","family":"Eskandar","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center"}]},{"given":"Fengyi","family":"Shen","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center"}]},{"given":"Dong","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center"}]},{"given":"Mohammad","family":"Altillawi","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center"}]},{"given":"Ziyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Munich Research Center"}]},{"given":"Gitta","family":"Kutyniok","sequence":"additional","affiliation":[{"name":"Ludwig Maximilian University of Munich"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462901"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636080"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.024"},{"key":"ref4","article-title":"Third-person visual imitation learning via decoupled hierarchical controller","author":"Sharma","year":"2019","journal-title":"NeurIPS"},{"article-title":"Reinforcement learning with videos: Combining offline observations with interaction","volume-title":"Conference on Robot Learning","author":"Schmeckpeper","key":"ref5"},{"key":"ref6","first-page":"3536","article-title":"Xskill: Cross embodiment skill discovery","volume-title":"Conference on Robot Learning","author":"Xu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.052"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610288"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.069"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687656"},{"key":"ref12","article-title":"Anyv2v: A tuning-free framework for any video-to-video editing tasks","author":"Ku","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"ref15","article-title":"Generating videos with scene dynamics","author":"Vondrick","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","year":"2022","author":"Gal","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"article-title":"Hoi-swap: Swapping objects in videos with hand-object interaction awareness","year":"2024","author":"Xue","key":"ref23"},{"key":"ref24","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on machine learning","author":"Ramesh"},{"article-title":"Cogvideo: Large scale pretraining for text-to-video generation via transformers","year":"2022","author":"Hong","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"article-title":"Revideo: Remake a video with motion and content control","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Mou","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3535182"},{"article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","year":"2024","author":"Ren","key":"ref30"},{"article-title":"Track anything: Segment anything meets videos","year":"2023","author":"Yang","key":"ref31"},{"article-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer","year":"2024","author":"Yang","key":"ref32"},{"article-title":"Inpaint anything: Segment anything meets image inpainting","year":"2023","author":"Yu","key":"ref33"},{"issue":"140","key":"ref34","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":"Journal of machine learning research"},{"issue":"2","key":"ref35","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref36","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246732.pdf?arnumber=11246732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:13:05Z","timestamp":1765519985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246732","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}