{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:06:16Z","timestamp":1779347176408,"version":"3.51.4"},"reference-count":25,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0103"],"award-info":[{"award-number":["2021SHZDZX0103"]}]},{"name":"Key Project of Comprehensive Prosperity Plan of Fudan University","award":["XM06231744"],"award-info":[{"award-number":["XM06231744"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/lra.2026.3692096","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:18Z","timestamp":1778528898000},"page":"7932-7939","source":"Crossref","is-referenced-by-count":0,"title":["GIL-3D: U-Shaped Diffusion Transformers for Generalizable 3D Imitation Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5455-7987","authenticated-orcid":false,"given":"Xiyue","family":"Wang","sequence":"first","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6737-8983","authenticated-orcid":false,"given":"Aoran","family":"Mei","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linzhi","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1365-396X","authenticated-orcid":false,"given":"Zhongxue","family":"Gan","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-740X","authenticated-orcid":false,"given":"Guo-Niu","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Jang","year":"2022"},{"key":"ref2","article-title":"Robotic manipulation via imitation learning: Taxonomy, evolution, benchmark, and challenges","author":"Li","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref4","first-page":"2323","article-title":"ChainedDiffuser: Unifying trajectory diffusion and keypose prediction for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Xian","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2473"},{"key":"ref6","first-page":"1949","article-title":"3D diffuser actor: Policy diffusion with 3D scene representations","volume-title":"Proc. Conf. Robot Learn.","author":"Ke","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801678"},{"key":"ref8","first-page":"694","article-title":"RVT: Robotic view transformer for 3D object manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Goyal","year":"2023"},{"key":"ref9","first-page":"3949","article-title":"Act3D: 3D feature field transformers for multi-task robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Gervet","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2025.100217"},{"key":"ref14","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng","year":"2021"},{"key":"ref15","first-page":"3732","article-title":"Learning the stein discrepancy for training and evaluating energy-based models without sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Grathwohl","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref18","first-page":"23301","article-title":"LIV: Language-image representations and rewards for robotic control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma","year":"2023"},{"key":"ref19","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2023"},{"key":"ref20","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00236"},{"key":"ref23","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11246340"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11520964\/11513725.pdf?arnumber=11513725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:10:20Z","timestamp":1779343820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11513725\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":25,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3692096","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}