{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T06:21:04Z","timestamp":1778998864354,"version":"3.51.4"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303405"],"award-info":[{"award-number":["62303405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Natural Science Foundation Project","award":["2023J400"],"award-info":[{"award-number":["2023J400"]}]},{"name":"Open Research Fund Program of Beijing National Research Center for Information Science and Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/lra.2025.3619835","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:55:27Z","timestamp":1760032527000},"page":"12125-12132","source":"Crossref","is-referenced-by-count":1,"title":["ImitDiff: Transferring Foundation-Model Priors for Distraction-Robust Visuomotor Policy"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9740-5834","authenticated-orcid":false,"given":"Yuhang","family":"Dong","sequence":"first","affiliation":[{"name":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8388-7193","authenticated-orcid":false,"given":"Haizhou","family":"Ge","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0580-1951","authenticated-orcid":false,"given":"Yupei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[{"name":"Youtu, Tencent, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2651-913X","authenticated-orcid":false,"given":"Beiwen","family":"Tian","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongrui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Jia","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruixiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2627-4397","authenticated-orcid":false,"given":"Zhucun","family":"Xue","sequence":"additional","affiliation":[{"name":"College of Control Science and Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3894-9858","authenticated-orcid":false,"given":"Guyue","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7802-0675","authenticated-orcid":false,"given":"Longhua","family":"Ma","sequence":"additional","affiliation":[{"name":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7292-4056","authenticated-orcid":false,"given":"Guanzhong","family":"Tian","sequence":"additional","affiliation":[{"name":"Ningbo Global Innovation Center, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.045"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref3","first-page":"126004","article-title":"Instruction-guided visual masking","volume-title":"Proc. 38th Adv. Neural Inf. Process. Syst.","author":"Zheng","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3357432"},{"key":"ref5","first-page":"4573","article-title":"ReKep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Huang","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128681"},{"key":"ref7","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref8","article-title":"OtterHD: A high-resolution multi-modality model","author":"Li","year":"2023"},{"key":"ref9","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref11","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref13","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref14","first-page":"5326","article-title":"Manipulate-anything: Automating real-world robots using vision-language models","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"Duan","year":"2024"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref16","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref17","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref18","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Karras","year":"2022"},{"key":"ref19","first-page":"4263","article-title":"Parallel sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Shih","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref21","first-page":"63399","article-title":"One-step diffusion policy: Fast visuomotor policies via diffusion distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2025"},{"key":"ref22","first-page":"78651","article-title":"Inductive moment matching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.071"},{"key":"ref24","first-page":"58736","article-title":"Mixformerv2: Efficient fully transformer tracking","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Cui","year":"2023"},{"key":"ref25","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_43"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11169302\/11197930.pdf?arnumber=11197930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:48:04Z","timestamp":1777060084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11197930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":27,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3619835","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}