{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:40:36Z","timestamp":1766061636113,"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"}],"funder":[{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246478","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9808-9815","source":"Crossref","is-referenced-by-count":0,"title":["CLAP: A Closed-Loop Diffusion Transformer Action Foundation Model for Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Mu","family":"Li","sequence":"first","affiliation":[{"name":"South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubo","family":"Dong","sequence":"additional","affiliation":[{"name":"South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co. Ltd.,Application Innovation Laboratory,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenguang","family":"Yang","sequence":"additional","affiliation":[{"name":"South China University of Technology,Key Laboratory of Autonomous Systems and Networked Control, Ministry of Education, College of Automation Science and Engineering,Guangzhou,China,510640"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","year":"2022","author":"Zeng","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref4"},{"article-title":"Vision-language foundation models as effective robot imitators","year":"2023","author":"Li","key":"ref5"},{"article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","year":"2024","author":"Huang","key":"ref6"},{"article-title":"Open-vla: An open-source vision-language-action model","year":"2024","author":"Kim","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref9"},{"article-title":"\u03c00.5: a vision-language-action model with open-world generalization","year":"2025","author":"Intelligence","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"article-title":"Llarva: Vision-action instruction tuning enhances robot learning","year":"2024","author":"Niu","key":"ref12"},{"article-title":"Tracevla: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies","year":"2024","author":"Zheng","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3544909"},{"article-title":"Diffusion-vla: Scaling robot foundation models via unified diffusion and autoregression","year":"2024","author":"Wen","key":"ref15"},{"article-title":"Robotic control via embodied chain-of-thought reasoning","year":"2024","author":"Zawalski","key":"ref16"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128452"},{"article-title":"Octo: An open-source generalist robot policy","year":"2024","author":"Team","key":"ref22"},{"article-title":"Rdt-1b: a diffusion foundation model for bimanual manipulation","year":"2024","author":"Liu","key":"ref23"},{"key":"ref24","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref25"},{"article-title":"Phi-3 technical report: A highly capable language model locally on your phone","year":"2024","author":"Abdin","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","year":"2023","author":"Awadalla","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_21"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3729343"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"issue":"140","key":"ref32","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"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"article-title":"Cogact: A foundational vision-language-action model for synergizing cognition and action in robotic manipulation","year":"2024","author":"Li","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3372778"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801581"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_17"}],"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\/11246478.pdf?arnumber=11246478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:33Z","timestamp":1766061393000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246478","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}