{"id":"https://openalex.org/W4414463417","doi":"https://doi.org/10.1109/tsmc.2025.3611698","title":"DreamArrangement: Learning Language-Conditioned Robotic Rearrangement of Objects via Denoising Diffusion and VLM Planner","display_name":"DreamArrangement: Learning Language-Conditioned Robotic Rearrangement of Objects via Denoising Diffusion and VLM Planner","publication_year":2025,"publication_date":"2025-09-24","ids":{"openalex":"https://openalex.org/W4414463417","doi":"https://doi.org/10.1109/tsmc.2025.3611698"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3611698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3611698","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101542024","display_name":"Wenkai Chen","orcid":"https://orcid.org/0000-0003-0169-8896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenkai Chen","raw_affiliation_strings":["Department of Informatics, Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0169-8896","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103152843","display_name":"Changming Xiao","orcid":"https://orcid.org/0000-0001-7684-964X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changming Xiao","raw_affiliation_strings":["Institute for Artificial Intelligence, Tsinghua (THUAI) and the Department of Automation, Tsinghua University, Beijing, China","Tsinghua (THUAI) and the Department of Automation, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7684-964X","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Tsinghua (THUAI) and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua (THUAI) and the Department of Automation, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020584921","display_name":"Ge Gao","orcid":"https://orcid.org/0000-0002-8159-9101"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ge Gao","raw_affiliation_strings":["Mech-Mind Robotics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mech-Mind Robotics, Beijing, China","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3546-6305","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065063835","display_name":"Changshui Zhang","orcid":"https://orcid.org/0000-0002-8088-367X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changshui Zhang","raw_affiliation_strings":["Institute for Artificial Intelligence, Tsinghua (THUAI) and the Department of Automation, Tsinghua University, Beijing, China","Tsinghua (THUAI) and the Department of Automation, Institute for Artificial Intelligence, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8088-367X","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Tsinghua (THUAI) and the Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua (THUAI) and the Department of Automation, Institute for Artificial Intelligence, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326970","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-7856-5760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Department of Informatics, Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7856-5760","affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical Aspects of Multimodal Systems (TAMS) Group, Universität Hamburg, Hamburg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22091164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":"11","first_page":"8675","last_page":"8688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.955299973487854,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5791000127792358},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4909999966621399},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.46000000834465027},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.43630000948905945},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4293999969959259},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42500001192092896},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.4097999930381775},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4018999934196472},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3767000138759613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387999892234802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6850000023841858},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4018999934196472},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.25200000405311584},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3611698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3611698","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1971159979","https://openalex.org/W2013035813","https://openalex.org/W2143668817","https://openalex.org/W2303345904","https://openalex.org/W2963367210","https://openalex.org/W3003205975","https://openalex.org/W3176484337","https://openalex.org/W3206916018","https://openalex.org/W3216352822","https://openalex.org/W4285218426","https://openalex.org/W4312933868","https://openalex.org/W4313179182","https://openalex.org/W4319299843","https://openalex.org/W4367721889","https://openalex.org/W4383097638","https://openalex.org/W4383109478","https://openalex.org/W4385245566","https://openalex.org/W4386075912","https://openalex.org/W4386758039","https://openalex.org/W4391128534"],"related_works":[],"abstract_inverted_index":{"The":[0,224],"capability":[1],"for":[2,47,60,78],"robotic":[3,48,203],"systems":[4],"to":[5,100,129,142,162,184],"rearrange":[6],"objects":[7],"based":[8],"on":[9],"human":[10,56,190],"instructions":[11],"represents":[12],"a":[13,88,97,111,123,138,212,221],"critical":[14],"step":[15],"toward":[16],"realizing":[17],"embodied":[18],"intelligence.":[19],"Recently,":[20],"diffusion-based":[21],"learning":[22,35,160],"has":[23,36],"shown":[24],"significant":[25],"advancements":[26],"in":[27,39],"the":[28,52,131,164,174,185],"field":[29],"of":[30,54,118,134,168,214],"data":[31],"generation":[32],"while":[33],"prompt-based":[34,65],"proven":[37],"effective":[38],"formulating":[40],"robot":[41],"manipulation":[42],"strategies.":[43],"However,":[44],"prior":[45],"solutions":[46],"rearrangement":[49,61,72,94,115,197],"have":[50],"overlooked":[51],"significance":[53],"integrating":[55],"preferences":[57],"and":[58,104,136,150,199,217],"optimizing":[59],"efficiency.":[62,200],"Additionally,":[63],"traditional":[64],"approaches":[66],"struggle":[67],"with":[68,220],"complex,":[69],"semantically":[70],"meaningful":[71],"tasks":[73,219],"without":[74,188],"predefined":[75],"target":[76,151],"states":[77],"objects.":[79,169],"To":[80],"address":[81],"these":[82],"challenges,":[83],"our":[84,178,207],"work":[85],"first":[86],"introduces":[87],"comprehensive":[89],"two":[90,119],"dimensional":[91],"(2-D)":[92],"tabletop":[93],"dataset,":[95],"utilizing":[96],"physical":[98],"simulator":[99],"capture":[101],"interobject":[102],"relationships":[103],"semantic":[105],"configurations.":[106],"Then,":[107],"we":[108,156],"present":[109],"DreamArrangement,":[110],"novel":[112],"language-conditioned":[113],"object":[114],"scheme,":[116],"consisting":[117],"primary":[120],"processes:":[121],"employing":[122],"transformer-based":[124],"multimodal":[125],"denoising":[126],"diffusion":[127],"model":[128,141],"envisage":[130],"desired":[132],"arrangement":[133],"objects,":[135],"leveraging":[137],"vision\u2013language":[139],"foundational":[140],"derive":[143],"actionable":[144],"policies":[145],"from":[146,177],"text,":[147],"alongside":[148],"initial":[149],"visual":[152],"information.":[153],"In":[154],"particular,":[155],"introduce":[157],"an":[158],"efficiency-oriented":[159],"strategy":[161],"minimize":[163],"average":[165],"motion":[166],"distance":[167],"Given":[170],"few-shot":[171],"instruction":[172],"examples,":[173],"learned":[175],"policy":[176],"synthetic":[179],"dataset":[180],"can":[181,209,227],"be":[182,228],"transferred":[183],"real":[186],"world":[187],"extra":[189],"intervention.":[191],"Extensive":[192],"simulations":[193],"validate":[194],"DreamArrangement\u2019s":[195],"superior":[196],"quality":[198],"Moreover,":[201],"real-world":[202],"experiments":[204],"confirm":[205],"that":[206],"method":[208],"adeptly":[210],"execute":[211],"range":[213],"challenging,":[215],"language-conditioned,":[216],"long-horizon":[218],"singular":[222],"model.":[223],"demonstration":[225],"video":[226],"found":[229],"at":[230],"https://youtu.be/fq25-DjrbQE":[231]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}