{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:00:24Z","timestamp":1777528824011,"version":"3.51.4"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China - General Program","award":["62376006"],"award-info":[{"award-number":["62376006"]}]},{"name":"National Youth Talent Support Program","award":["8200800081"],"award-info":[{"award-number":["8200800081"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/lra.2024.3438036","type":"journal-article","created":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T17:40:18Z","timestamp":1722620418000},"page":"8258-8265","source":"Crossref","is-referenced-by-count":9,"title":["LVDiffusor: Distilling Functional Rearrangement Priors From Large Models Into Diffusor"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2935-4067","authenticated-orcid":false,"given":"Yiming","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9120-4621","authenticated-orcid":false,"given":"Mingdong","family":"Wu","sequence":"additional","affiliation":[{"name":"Hyperplane Lab, School of CS, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Yang","sequence":"additional","affiliation":[{"name":"Hyperplane Lab, School of CS, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6150-2788","authenticated-orcid":false,"given":"Jiyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hyperplane Lab, School of CS, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2579-7004","authenticated-orcid":false,"given":"Hui","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7984-9909","authenticated-orcid":false,"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"Hyperplane Lab, School of CS, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364916649248"},{"key":"ref2","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achlioptas","year":"2018"},{"key":"ref3","article-title":"Rearrangement: A challenge for embodied AI","author":"Batra","year":"2020"},{"key":"ref4","article-title":"Training diffusion models with reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Black","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref6","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3115406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0771-050X(80)90013-3"},{"key":"ref9","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Proc. Conf. Robot Learn.","author":"Ha","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487797"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref12","first-page":"540","article-title":"Voxposer: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_21"},{"key":"ref14","first-page":"740","article-title":"My house, my rules: Learning tidying preferences with graph neural networks","volume-title":"Proc. 5th Annu. Conf. Robot Learn.","author":"Kapelyukh","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref16","article-title":"Aligning text-to-image models using human feedback","author":"Lee","year":"2023"},{"key":"ref17","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref20","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811931"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4018\/ijrcm.2019010105"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00618"},{"key":"ref25","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":"ref26","article-title":"Hierarchical text-conditional image generation with clip latents","volume-title":"arXiv:2204.06125","author":"Ramesh"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6224553"},{"key":"ref30","first-page":"2030","article-title":"Shelving, stacking, hanging: Relational pose diffusion for multi-modal rearrangement","volume-title":"Proc. Conf. Robot Learn.","author":"Simeonov","year":"2023"},{"key":"ref31","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref33","first-page":"16353","article-title":"Find what you want: Learning demand-conditioned object attribute space for demand-driven navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref34","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"ref36","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref38","first-page":"31986","article-title":"TarGF: Learning target gradient field to rearrange objects without explicit goal specification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185552"},{"key":"ref40","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zeng","year":"2022"},{"key":"ref41","first-page":"54627","article-title":"Generative category-level object pose estimation via diffusion models","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935173"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548541"},{"key":"ref45","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Zitkovich","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10638067\/10621583.pdf?arnumber=10621583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:33:16Z","timestamp":1734982396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10621583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":45,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3438036","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}