{"id":"https://openalex.org/W7214733657","doi":"https://doi.org/10.48550/arxiv.2609.33982","title":"Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim","display_name":"Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214733657","doi":"https://doi.org/10.48550/arxiv.2609.33982"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.33982","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33982","pdf_url":"https://arxiv.org/pdf/2609.33982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.33982","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058833302","display_name":"Ivan Kapelyukh","orcid":"https://orcid.org/0000-0001-5587-204X","observed_orcids":["https://orcid.org/0000-0001-5587-204X"]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Kapelyukh, Ivan","raw_affiliation_strings":["Imperial College London","Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153549083","display_name":"Yafei Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Yafei","raw_affiliation_strings":["Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102884044","display_name":"Ran Gong","orcid":"https://orcid.org/0009-0005-2826-1901","observed_orcids":["https://orcid.org/0009-0005-2826-1901"]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gong, Ran","raw_affiliation_strings":["Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020660749","display_name":"Brandon B. May","orcid":"https://orcid.org/0000-0002-9914-2441","observed_orcids":["https://orcid.org/0000-0002-9914-2441"]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"May, Brandon","raw_affiliation_strings":["Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014796462","display_name":"Tushar Kusnur","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kusnur, Tushar","raw_affiliation_strings":["Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084585983","display_name":"Laura Herlant","orcid":"https://orcid.org/0009-0004-7388-2806","observed_orcids":["https://orcid.org/0009-0004-7388-2806"]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herlant, Laura","raw_affiliation_strings":["Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049609650","display_name":"Karl Schmeckpeper","orcid":"https://orcid.org/0000-0003-4989-2022","observed_orcids":["https://orcid.org/0000-0003-4989-2022"]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Schmeckpeper, Karl","raw_affiliation_strings":["Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080385974","display_name":"Edward Johns","orcid":"https://orcid.org/0000-0002-8914-8786","observed_orcids":["https://orcid.org/0000-0002-8914-8786"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Johns, Edward","raw_affiliation_strings":["Imperial College London","Project Leads"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Project Leads","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153495127","display_name":"Xiaohan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258407","display_name":"Robotics and AI Institute","ror":"https://ror.org/00kqcs728","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258407"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Xiaohan","raw_affiliation_strings":["Project Leads","Robotics and AI Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Project Leads","institution_ids":[]},{"raw_affiliation_string":"Robotics and AI Institute","institution_ids":["https://openalex.org/I4405258407"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.018699999898672104,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/spatial-reasoning","display_name":"spatial reasoning","score":0.8759999871253967},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.984000027179718},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.7749999761581421},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9319999814033508},{"id":"https://openalex.org/keywords/evolutionary-search","display_name":"evolutionary search","score":0.7310000061988831},{"id":"https://openalex.org/keywords/object-rearrangement","display_name":"object rearrangement","score":0.5600000023841858},{"id":"https://openalex.org/keywords/training-free-inference","display_name":"training-free inference","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670000195503235},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6672000288963318},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6492000222206116},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6456999778747559},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258000135421753},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43369999527931213},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.33982","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33982","pdf_url":"https://arxiv.org/pdf/2609.33982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.33982","doi":"https://doi.org/10.48550/arxiv.2609.33982","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.33982","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.33982","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33982","pdf_url":"https://arxiv.org/pdf/2609.33982","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214733657.pdf","grobid_xml":"https://content.openalex.org/works/W7214733657.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4400065180","https://openalex.org/W7116939080"],"related_works":["https://openalex.org/W4404352956","https://openalex.org/W7204762922","https://openalex.org/W7128427679","https://openalex.org/W4414196976","https://openalex.org/W4415277511","https://openalex.org/W7221040542","https://openalex.org/W4416073598","https://openalex.org/W4417144670","https://openalex.org/W4400275526","https://openalex.org/W4401413701"],"abstract_inverted_index":{"Spatial":[0],"reasoning":[1,30,128],"is":[2],"fundamental":[3],"to":[4,12,82,97,104],"general":[5],"robot":[6],"intelligence,":[7],"as":[8],"it":[9],"enables":[10],"robots":[11],"complete":[13,143],"long-horizon":[14],"tasks":[15,109],"involving":[16],"multi-object":[17],"interaction.":[18],"We":[19,90],"introduce":[20],"Simify,":[21],"a":[22,37,42,57,61],"training-free,":[23],"test-time":[24],"framework":[25,103,119],"that":[26,117],"performs":[27,78],"explicit":[28],"spatial":[29,127],"via":[31],"massively":[32],"parallel":[33,73,133],"physics":[34],"simulation.":[35],"From":[36],"single":[38],"RGB-D":[39],"image":[40],"of":[41,72,101,142],"scene,":[43],"Simify":[44,69],"reconstructs":[45],"simulation-ready":[46],"assets":[47],"leveraging":[48],"3D":[49],"generative":[50],"models":[51,125],"and":[52,77,137,144],"vision-language":[53],"models.":[54],"Then":[55],"given":[56],"task":[58],"specified":[59],"by":[60,129],"reward":[62],"function":[63],"(e.g.,":[64],"build":[65],"the":[66,99,140],"tallest":[67],"tower),":[68],"launches":[70],"thousands":[71],"rollouts":[74],"in":[75],"simulation":[76,134],"an":[79],"evolutionary":[80],"search":[81],"optimize":[83],"object":[84,107],"arrangements,":[85],"typically":[86],"converging":[87],"within":[88],"seconds.":[89],"conduct":[91],"quantitative":[92],"experiments":[93],"on":[94,123],"real-robot":[95],"hardware":[96],"demonstrate":[98],"ability":[100],"our":[102,118],"execute":[105],"complex":[106],"rearrangement":[108],"end-to-end":[110],"with":[111],"previously":[112],"unseen":[113],"objects.":[114],"Results":[115],"show":[116],"outperforms":[120],"prior":[121],"work":[122],"foundation":[124],"for":[126,147],"effectively":[130],"exploiting":[131],"large-scale":[132],"during":[135],"inference,":[136],"also":[138],"highlight":[139],"importance":[141],"accurate":[145],"geometry":[146],"successful":[148],"sim-to-real":[149],"transfer.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}
