{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:35:51Z","timestamp":1772303751257,"version":"3.50.1"},"reference-count":41,"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\/icra55743.2025.11127280","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"4462-4469","source":"Crossref","is-referenced-by-count":1,"title":["MuST: Multi-Head Skill Transformer for Long-Horizon Dexterous Manipulation with Skill Progress"],"prefix":"10.1109","author":[{"given":"Kai","family":"Gao","sequence":"first","affiliation":[{"name":"Amazon Robotics,MA,USA"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}]},{"given":"Erica","family":"Aduh","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}]},{"given":"Dylan","family":"Randle","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}]},{"given":"Jane","family":"Shi","sequence":"additional","affiliation":[{"name":"Amazon Robotics,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref3","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref5","author":"Brohan","year":"2023","journal-title":"Rt-1: Robotics transformer for real-world control at scale"},{"key":"ref6","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"7th Annual Conference on Robot Learning","author":"Zitkovich"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref8","article-title":"Equibot: Sim (3)-equivariant diffusion policy for generalizable and data efficient learning","volume-title":"8th Annual Conference on Robot Learning","author":"Yang"},{"key":"ref9","volume-title":"Learning to generalize across long-horizon tasks from human demonstrations","author":"Mandlekar","year":"2021"},{"key":"ref10","first-page":"1087","article-title":"One-shot imitation learning","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Duan"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6906922"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v20i1.13436"},{"key":"ref14","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume":"29","author":"Kulkarni","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"International Conference on Learning Representations","author":"Eysenbach"},{"key":"ref16","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"International conference on machine learning","author":"Vezhnevets"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"ref19","first-page":"9465","article-title":"Rrl: Resnet as representation for reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Shah"},{"key":"ref20","article-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents","author":"Ahn","year":"2024","journal-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref23","first-page":"1678","article-title":"What matters in learning from offline human demonstrations for robot manipulation","volume-title":"Conference on Robot Learning","author":"Mandlekar"},{"key":"ref24","article-title":"Moka: Open-vocabulary robotic manipulation through mark-based visual prompting","author":"Liu","year":"2024","journal-title":"First Workshop on Vision-Language Models for Navigation and Manipulation at ICRA"},{"key":"ref25","article-title":"Vima: General robot manipulation with multimodal prompts","author":"Jiang","journal-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop"},{"key":"ref26","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v30i1.6739"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/02783649231178565"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561716"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802562"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812367"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63596-0_17"},{"key":"ref34","first-page":"2905","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","volume-title":"Conference on Robot Learning","author":"Mishra"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160220"},{"key":"ref36","first-page":"2113","article-title":"Hydra: Hybrid robot actions for imitation learning","volume-title":"Conference on Robot Learning","author":"Belkhale"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"ref39","volume-title":"Nvidia simready assets","year":"2024"},{"key":"ref40","year":"2024","journal-title":"Sketchfab open-source 3d models"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"}],"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\/11127280.pdf?arnumber=11127280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:45:09Z","timestamp":1756881909000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127280","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}