{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T20:07:55Z","timestamp":1785787675029,"version":"3.56.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Shanghai Qi Zhi Institute"},{"DOI":"10.13039\/100031931","name":"Shanghai Artificial Intelligence Laboratory","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100031931","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/lra.2026.3711479","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T19:45:30Z","timestamp":1783626330000},"page":"10672-10679","source":"Crossref","is-referenced-by-count":0,"title":["X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning"],"prefix":"10.1109","volume":"11","author":[{"given":"Maanping","family":"Shao","sequence":"first","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5044-1535","authenticated-orcid":false,"given":"Feihong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baiye","family":"Cheng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2574-8608","authenticated-orcid":false,"given":"Zhengrong","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8578-1261","authenticated-orcid":false,"given":"Huazhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.157"},{"key":"ref5","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref6","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Touvron"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref10","article-title":"Galaxea open-world dataset and G0 dual-system VLA model","author":"Jiang","year":"2025"},{"key":"ref11","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NeurIPS","author":"Hinton","year":"2015"},{"key":"ref12","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Yu","year":"2020"},{"key":"ref13","article-title":"Manipulators and manipulation in high dimensional spaces","author":"Kumar","year":"2016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref16","article-title":"PaliGemma: A versatile 3B VLM for transfer","author":"Beyer","year":"2024"},{"key":"ref17","first-page":"730","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd IAPR Asian Conf. Pattern Recognit.","author":"Simonyan","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1459-z"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref22","first-page":"724","article-title":"Theia: Distilling diverse vision foundation models for robot Learning","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Shang","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26348-4_11"},{"key":"ref24","first-page":"1","article-title":"Memory-consistent neural networks for imitation learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sridhar","year":"2024"},{"key":"ref25","first-page":"17","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","volume-title":"Proc. 9th Conf. Robot Learn.","volume":"305","author":"Intelligence","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247088"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref28","first-page":"1","article-title":"Masked world models for visual control","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Seo","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2389"},{"key":"ref30","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref35","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11606541\/11602640.pdf?arnumber=11602640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T19:13:47Z","timestamp":1785784427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11602640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":37,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3711479","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}