{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:39:58Z","timestamp":1757608798585,"version":"3.44.0"},"reference-count":33,"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\/icra55743.2025.11127927","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"16752-16758","source":"Crossref","is-referenced-by-count":0,"title":["ASCENT: Autonomous Skill Learning Toward Complex Embodied Tasks With Foundation Models"],"prefix":"10.1109","author":[{"given":"Haolin","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yatsen University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuecheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Embodied AI Innovation Lab, Huawei Cloud,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Embodied AI Innovation Lab, Huawei Cloud,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sitong","family":"Mao","sequence":"additional","affiliation":[{"name":"Embodied AI Innovation Lab, Huawei Cloud,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hesheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weigang","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yatsen University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunbo","family":"Zhou","sequence":"additional","affiliation":[{"name":"Embodied AI Innovation Lab, Huawei Cloud,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2022.2041907"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-024-00324-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.799893"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2141622.2141689"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3669754.3669788"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610375"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3344393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3432741"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611494"},{"key":"ref11","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"The (r) evolution of multimodal large language models: A survey","author":"Caffagni","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161528"},{"key":"ref15","first-page":"5982","article-title":"Procthor: Large-scale embodied ai using procedural generation","volume":"35","author":"Deitke","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01539"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref18","article-title":"Layoutgpt: Compositional visual planning and generation with large language models","volume":"36","author":"Feng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref20","article-title":"Anyhome: Openvocabulary generation of structured and textured 3d homes","author":"Wen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00684"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref23","article-title":"Adaptive procedural task generation for hard-exploration problems","author":"Fang","year":"2020","journal-title":"arXiv preprint"},{"issue":"3","key":"ref24","first-page":"6","article-title":"Vima: General robot manipulation with multimodal prompts","volume":"2","author":"Jiang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Gensim: Generating robotic simulation tasks via large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents","author":"Ahn","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.32"},{"key":"ref29","first-page":"806","article-title":"Predicting stable configurations for semantic placement of novel objects","volume-title":"Conference on robot learning","author":"Paxton"},{"key":"ref30","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610566"},{"key":"ref32","article-title":"Roboclip: One demonstration is enough to learn robot policies","volume":"36","author":"Sontakke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Eureka: Human-level reward design via coding large language models","author":"Jason Ma","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11127927.pdf?arnumber=11127927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:45:47Z","timestamp":1756881947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127927","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}