{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:21:35Z","timestamp":1781018495128,"version":"3.54.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127926","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"6896-6903","source":"Crossref","is-referenced-by-count":3,"title":["Deformpam: Data-Efficient Learning for Long-Horizon Deformable Object Manipulation Via Preference-Based Action Alignment"],"prefix":"10.1109","author":[{"given":"Wendi","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref5","article-title":"ALOHA unleashed: A simple recipe for robot dexterity","volume-title":"8th Annual Conference on Robot Learning","author":"Zhao","year":"2024"},{"key":"ref6","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross","year":"2011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161546"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981402"},{"key":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00786"},{"key":"ref12","first-page":"3321","article-title":"Unifolding: Towards sample-efficient, scalable, and generalizable robotic garment folding","volume-title":"Conference on Robot Learning. PMLR","author":"Xue","year":"2023"},{"key":"ref13","first-page":"24","article-title":"Flingbot: The unreasonable effectiveness of dynamic manipulation for cloth unfolding","volume-title":"Conference on Robot Learning. PMLR","author":"Ha","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01546"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161402"},{"key":"ref18","article-title":"Differentiable particles for general-purpose deformable object manipulation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref22","first-page":"4654","article-title":"Taco: Learning task decomposition via temporal alignment for control","volume-title":"International Conference on Machine Learning. PMLR","author":"Shiarlis","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460689"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3443610"},{"key":"ref25","first-page":"201","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","volume-title":"Conference on Robot Learning. PMLR","author":"Wang","year":"2023"},{"key":"ref26","first-page":"11131132","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning. PMLR","author":"Lynch","year":"2020"},{"key":"ref27","article-title":"From play to policy: Conditional behavior generation from uncurated robot data","volume-title":"The Eleventh International Conference on Learning Representations","author":"Cui"},{"key":"ref28","first-page":"1838","article-title":"Latent plans for task-agnostic offline reinforcement learning","volume-title":"Conference on Robot Learning. PMLR","author":"Rosete-Beas","year":"2023"},{"key":"ref29","first-page":"642660","article-title":"Robocook: Longhorizon elasto-plastic object manipulation with diverse tools","volume-title":"Conference on Robot Learning. PMLR","author":"Shi","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref31","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.041"},{"key":"ref33","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref34","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Contrastive prefence learning: Learning from human feedback without rl","author":"Hejna","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Preference alignment with flow matching","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"A general language assistant as a laboratory for alignment","author":"Askell","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Args: Alignment as reward-guided search","volume-title":"The Twelfth International Conference on Learning Representations","author":"Khanov"},{"key":"ref39","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2012.2205651"},{"key":"ref41","author":"Coumans","year":"2016","journal-title":"Pybullet, a python module for physics simulation for games, robotics and machine learning"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00905"},{"key":"ref43","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref45","article-title":"Smaug: Fixing failure modes of preference optimisation with dpo-positive","author":"Pal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"On the limited generalization capability of the implicit reward model induced by","author":"Lin","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127926.pdf?arnumber=11127926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:45:50Z","timestamp":1756881950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127926","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}