{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:18:37Z","timestamp":1776716317671,"version":"3.51.2"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Dyson Technology Ltd."},{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Fellowship Scheme"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/lra.2023.3272516","type":"journal-article","created":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T22:11:48Z","timestamp":1683065508000},"page":"3956-3963","source":"Crossref","is-referenced-by-count":77,"title":["DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5587-204X","authenticated-orcid":false,"given":"Ivan","family":"Kapelyukh","sequence":"first","affiliation":[{"name":"Robot Learning Lab, Imperial College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5004-4552","authenticated-orcid":false,"given":"Vitalis","family":"Vosylius","sequence":"additional","affiliation":[{"name":"Robot Learning Lab, Imperial College London, London, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8914-8786","authenticated-orcid":false,"given":"Edward","family":"Johns","sequence":"additional","affiliation":[{"name":"Robot Learning Lab, Imperial College London, London, U.K."}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143518"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139396"},{"key":"ref15","first-page":"31986","article-title":"TarGF : Learning target gradient field for object rearrangement","author":"wu","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.01825","article-title":"LEGO-Net: Learning regular rearrangements of objects in rooms","author":"wei","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_28"},{"key":"ref17","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","author":"zeng","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref16","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","author":"shridhar","year":"0","journal-title":"Proc 5th Conf Robot Learn"},{"key":"ref19","first-page":"1113","article-title":"Learning latent plans from play","author":"lynch","year":"0","journal-title":"Proc Conf Robot Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01437"},{"key":"ref50","article-title":"Testing relational understanding in text-guided image generation","author":"conwell","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref45","first-page":"471","article-title":"Where to start? Transferring simple skills to complex environments","author":"vosylius","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref48","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"gal","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","article-title":"Feature-realistic neural fusion for real-time, open set scene understanding","author":"mazur","year":"0","journal-title":"Proc Int Conf Robot Automat"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00144"},{"key":"ref41","article-title":"ImageNet-21K pretraining for the masses","author":"ridnik","year":"0","journal-title":"Proc Neural Inf Process Syst Track Datasets Benchmarks"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759657"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00299"},{"key":"ref49","article-title":"Large language models are zero-shot reasoners","author":"kojima","year":"2022","journal-title":"arXiv 2205 11916"},{"key":"ref8","first-page":"1011","article-title":"Transformers are adaptable task planners","author":"jain","year":"0","journal-title":"Proc 6th Conf Robot Learn"},{"key":"ref7","article-title":"StructDiffusion: Object-centric diffusion for semantic rearrangement of novel objects","author":"liu","year":"0","journal-title":"Proc Robot Sci Syst"},{"key":"ref9","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"ramesh","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_21"},{"key":"ref3","first-page":"740","article-title":"My house, my rules: Learning tidying preferences with graph neural networks","author":"kapelyukh","year":"0","journal-title":"Proc 5th Int Conf Robot Learn"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811931"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/URAI.2018.8442210"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref34","article-title":"Detectron 2","author":"wu","year":"2019"},{"key":"ref37","first-page":"1638","article-title":"Contextual string embeddings for sequence labeling","author":"akbik","year":"0","journal-title":"Proc 27th Int Conf Comput Linguistics"},{"key":"ref36","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"wang","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref30","article-title":"Learning universal policies via text-guided video generation","author":"du","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/34.121791"},{"key":"ref2","first-page":"907","article-title":"Learning object arrangements in 3D scenes using human context","author":"jiang","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref1","article-title":"Rearrangement: A challenge for embodied AI","author":"batra","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811817"},{"key":"ref38","first-page":"54","article-title":"FLAIR: An easy-to-use framework for state-of-the-art NLP","author":"akbik","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref23","article-title":"Diffusion policy: Visuomotor policy learning via action diffusion","author":"chi","year":"0","journal-title":"Proc Robot Sci Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989324"},{"key":"ref20","first-page":"9191","article-title":"Visual reinforcement learning with imagined goals","author":"nair","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","author":"janner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.010","article-title":"GenAug: Retargeting behaviors to unseen situations via generative augmentation","author":"chen","year":"2023"},{"key":"ref27","article-title":"CACTI: A framework for scalable multi-task multi-scene visual imitation learning","author":"mandi","year":"2022"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2023.XIX.027","article-title":"Scaling robot learning with semantically imagined experience","author":"yu","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10128766\/10114570.pdf?arnumber=10114570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T22:56:15Z","timestamp":1702335375000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10114570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":50,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3272516","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}