{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:29:57Z","timestamp":1777984197104,"version":"3.51.4"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"German Research Foundation (DFG) and the National Science Foundation of China (NSFC) through the Project Crossmodal Learning","award":["DFG TRR-169\/NSFC 62061136001"],"award-info":[{"award-number":["DFG TRR-169\/NSFC 62061136001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tsmc.2025.3611698","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T17:34:06Z","timestamp":1758735246000},"page":"8675-8688","source":"Crossref","is-referenced-by-count":0,"title":["DreamArrangement: Learning Language-Conditioned Robotic Rearrangement of Objects via Denoising Diffusion and VLM Planner"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0169-8896","authenticated-orcid":false,"given":"Wenkai","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Informatics, Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7684-964X","authenticated-orcid":false,"given":"Changming","family":"Xiao","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Tsinghua (THUAI) and the Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Gao","sequence":"additional","affiliation":[{"name":"Mech-Mind Robotics, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3546-6305","authenticated-orcid":false,"given":"Fuchun","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8088-367X","authenticated-orcid":false,"given":"Changshui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Tsinghua (THUAI) and the Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7856-5760","authenticated-orcid":false,"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Rearrangement: A challenge for embodied AI","author":"Batra","year":"2020","journal-title":"arXiv:2011.01975"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref3","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":"Ahn"},{"key":"ref4","first-page":"8469","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess"},{"key":"ref5","article-title":"SG-bot: Object rearrangement via coarse-to-fine robotic imagination on scene graphs","author":"Zhai","year":"2023","journal-title":"arXiv:2309.12188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3272516"},{"key":"ref7","article-title":"StructDiffusion: Object-centric diffusion for semantic rearrangement of novel objects","author":"Liu","year":"2022","journal-title":"arXiv:2211.04604"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"ref9","article-title":"Diffuscene: Scene graph denoising diffusion probabilistic model for generative indoor scene synthesis","author":"Tang","year":"2023","journal-title":"arXiv:2303.14207"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811931"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/3468.952716"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-101119-071628"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref16","first-page":"9414","article-title":"Language as an abstraction for hierarchical deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.047"},{"key":"ref19","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Stepputtis"},{"key":"ref20","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref21","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zeng"},{"key":"ref22","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3310505"},{"key":"ref24","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref25","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv:2210.02303"},{"key":"ref28","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref29","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref30","article-title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Couairon"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00091"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3209680"},{"key":"ref34","article-title":"VIMA: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022","journal-title":"arXiv:2210.03094"},{"key":"ref35","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0550-3213(81)90056-0"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref38","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv:2401.14159"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3357432"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11205930\/11176993.pdf?arnumber=11176993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:58Z","timestamp":1763059498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11176993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":41,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3611698","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.171171867.71552439\/v1","asserted-by":"object"}]},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}