{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:04:39Z","timestamp":1776978279807,"version":"3.51.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/lra.2026.3682534","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:48:20Z","timestamp":1775764100000},"page":"7031-7037","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Continual Imitation Learning With Online Meta-Adapters"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7959-0587","authenticated-orcid":false,"given":"Ruiqi","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Engineering, King's College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5825-2986","authenticated-orcid":false,"given":"Endong","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Engineering, King's College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7631-0011","authenticated-orcid":false,"given":"Guanhe","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Engineering, King's College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7213-6359","authenticated-orcid":false,"given":"Oya","family":"Celiktutan","sequence":"additional","affiliation":[{"name":"Department of Engineering, King's College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref2","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":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref4","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref8","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn. PMLR","author":"Zitkovich","year":"2023"},{"key":"ref9","article-title":"Octo: An open-source generalist robot policy","author":"Mees","year":"2024","journal-title":"First Workshop Vis.-Lang. Models Navigation Manipulation ICRA"},{"key":"ref10","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kumar","year":"2022"},{"key":"ref11","first-page":"28496","article-title":"Continual world: A robotic benchmark for continual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Woczyk","year":"2021"},{"key":"ref12","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref13","article-title":"Lossless adaptation of pretrained vision models for robotic manipulation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sharma","year":"2023"},{"key":"ref14","article-title":"TAIL: Task-specific adapters for imitation learning with large pretrained models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref15","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn. PMLR","author":"Kim","year":"2025"},{"key":"ref16","article-title":"Don\u2019t forget, there is more than forgetting: New metrics for continual learning","author":"Dz-Rodruez","year":"2018","journal-title":"Workshop Continual Learn., NeurIPS Neural Inf. Process. Syst."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00004-Y"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.004"},{"key":"ref22","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref23","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Proc. Conf. Robot Learn.","author":"Finn","year":"2017"},{"key":"ref24","article-title":"One-shot imitation from observing humans via domain-adaptive meta-learning","author":"Yu","year":"2018","journal-title":"Robot.: Sci. Syst. XIV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341462"},{"key":"ref26","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.172"},{"key":"ref29","article-title":"Evolutionary principles in self-referential learning, or on learning how to learn: The meta-meta-... hook","author":"Schmidhuber","year":"1987"},{"key":"ref30","first-page":"1920","article-title":"Online meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2019"},{"key":"ref31","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref33","first-page":"7497","article-title":"Meta-learning with an adaptive task scheduler","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yao","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_44"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1660"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/500"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref39","article-title":"When vision transformers outperform ResNets without pre-training or strong data augmentations","volume-title":"Proc. Int. Conf. Learn. Representation","author":"Chen","year":"2022"},{"key":"ref40","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Raghu","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.157"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00812"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11481819\/11478065.pdf?arnumber=11478065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:00:11Z","timestamp":1776974411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":42,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3682534","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}