{"id":"https://openalex.org/W7224969818","doi":"https://doi.org/10.48550/arxiv.2610.39639","title":"Where Do Vision Language Models Fail at 3D Reasoning?","display_name":"Where Do Vision Language Models Fail at 3D Reasoning?","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224969818","doi":"https://doi.org/10.48550/arxiv.2610.39639"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39639","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39639","pdf_url":"https://arxiv.org/pdf/2610.39639","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027408987","display_name":"Khai Le-Duc","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le-Duc, Khai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160208624","display_name":"Nguyen Kim Hai Bui","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bui, Nguyen Kim Hai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128000626","display_name":"An Ngo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngo, An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067248058","display_name":"Hoang Nam Do","orcid":"https://orcid.org/0000-0003-4800-8434","observed_orcids":["https://orcid.org/0000-0003-4800-8434"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoang, Nam D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102516926","display_name":"Yueqi Song","orcid":"https://orcid.org/0009-0008-1081-8953","observed_orcids":["https://orcid.org/0009-0008-1081-8953"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yueqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160182124","display_name":"Jiarui Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiarui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160181660","display_name":"Thai Quoc Hoang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoang, Thai Quoc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160221421","display_name":"Fang Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012291455","display_name":"Chris Ngo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngo, Chris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160162534","display_name":"Terry Jingchen Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Terry Jingchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038581447","display_name":"Mona Diab","orcid":"https://orcid.org/0000-0002-7696-1436","observed_orcids":["https://orcid.org/0000-0002-7696-1436"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diab, Mona T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160161950","display_name":"Ran Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savarese, Silvio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160212795","display_name":"Xiao-Ming Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiao-Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.9039999842643738},{"id":"https://openalex.org/keywords/3d-reasoning","display_name":"3D reasoning","score":0.9829999804496765},{"id":"https://openalex.org/keywords/procedural-content-generation","display_name":"procedural content generation","score":0.47200000286102295},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.3970000147819519},{"id":"https://openalex.org/keywords/qwen3-5","display_name":"Qwen3.5","score":0.6389999985694885},{"id":"https://openalex.org/keywords/open-weight-models","display_name":"open-weight models","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6276000142097473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6025999784469604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5921000242233276},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5224000215530396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4677000045776367},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39639","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39639","pdf_url":"https://arxiv.org/pdf/2610.39639","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.2610.39639","doi":"https://doi.org/10.48550/arxiv.2610.39639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39639","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39639","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39639","pdf_url":"https://arxiv.org/pdf/2610.39639","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224969818.pdf","grobid_xml":"https://content.openalex.org/works/W7224969818.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4413155672","https://openalex.org/W7213402754","https://openalex.org/W4409262625","https://openalex.org/W7220864230","https://openalex.org/W7206215876","https://openalex.org/W7162030744","https://openalex.org/W7140588253","https://openalex.org/W7140043981","https://openalex.org/W7166860874","https://openalex.org/W4407126860"],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"can":[2],"get":[3],"individual":[4,37,122],"judgments":[5,38],"right":[6],"while":[7],"struggling":[8],"to":[9,74],"recover":[10,152],"and":[11,39,45,116,186,194],"consistently":[12],"use":[13],"the":[14,63,84,132,143,148,156,161],"exact":[15,127,137,182],"properties":[16],"of":[17,31],"a":[18,28,52,78,106],"3D":[19,179],"object.":[20],"To":[21,130],"characterize":[22],"this":[23],"gap,":[24],"we":[25,134],"introduce":[26],"BedBench,":[27],"controlled":[29],"benchmark":[30],"thirteen":[32],"procedurally":[33],"generated":[34],"tasks":[35],"spanning":[36],"composite":[40],"answers.":[41],"Across":[42],"twelve":[43],"open-weight":[44],"four":[46],"frontier":[47],"models,":[48],"per-color":[49,93,138],"counting":[50],"exposes":[51],"pronounced":[53],"weakness:":[54],"humans":[55],"achieve":[56],"93.3%":[57],"accuracy,":[58],"compared":[59],"with":[60,90],"7.2%":[61],"for":[62,155,160],"best":[64],"model.":[65],"Targeted":[66],"fine-tuning":[67],"raises":[68],"one":[69],"model's":[70,145,149],"accuracy":[71,191],"from":[72],"3.0%":[73,159],"68.6%,":[75],"but":[76,124],"reveals":[77],"further":[79,165],"difficulty:":[80],"its":[81,91,101],"answers":[82,128,150],"about":[83],"most":[85],"common":[86],"colors":[87],"remain":[88,140],"inconsistent":[89],"own":[92],"counts.":[94],"Supplying":[95],"those":[96],"counts":[97,139],"as":[98],"text":[99],"improves":[100],"judgments,":[102,123],"showing":[103],"that":[104,167],"recovering":[105],"property":[107],"does":[108],"not":[109],"mean":[110],"using":[111],"it":[112],"consistently.":[113],"Reasoning,":[114],"scaling,":[115],"added":[117],"visual":[118,173],"cues":[119],"each":[120],"improve":[121],"none":[125],"makes":[126],"reliable.":[129],"locate":[131],"difficulty,":[133],"probe":[135,157],"Qwen3.5-27B:":[136],"recoverable":[141],"at":[142],"language":[144],"input,":[146],"yet":[147],"rarely":[151],"them":[153],"(65.0%":[154],"vs.":[158],"model).":[162],"Image-removal":[163],"controls":[164],"show":[166],"some":[168],"apparent":[169],"successes":[170],"require":[171],"no":[172],"evidence.":[174],"These":[175],"findings":[176],"motivate":[177],"evaluating":[178],"reasoning":[180],"by":[181],"correctness,":[183],"consistent":[184],"use,":[185],"image":[187],"dependence,":[188],"rather":[189],"than":[190],"alone.":[192],"Code":[193],"dataset":[195],"are":[196],"publicly":[197],"available:":[198],"https://github.com/leduckhai/BedBench":[199]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}