{"id":"https://openalex.org/W4416613191","doi":"https://doi.org/10.48550/arxiv.2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","display_name":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4416613191","doi":"https://doi.org/10.48550/arxiv.2505.23764"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.23764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.23764","pdf_url":"https://arxiv.org/pdf/2505.23764","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":"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/2505.23764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067444646","display_name":"Sihan Yang","orcid":"https://orcid.org/0000-0001-6773-471X","observed_orcids":["https://orcid.org/0000-0001-6773-471X"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yang, Sihan","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075229879","display_name":"Runsen Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Xu, Runsen","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xie, Yiman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Yiman","raw_affiliation_strings":["Shanghai AI Laboratory","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111012217","display_name":"Sizhe Yang","orcid":"https://orcid.org/0009-0007-4462-5191","observed_orcids":["https://orcid.org/0009-0007-4462-5191"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yang, Sizhe","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361458","display_name":"Mo Li","orcid":"https://orcid.org/0000-0002-6047-9709","observed_orcids":["https://orcid.org/0000-0002-6047-9709"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"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":"Li, Mo","raw_affiliation_strings":["Shanghai AI Laboratory","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109299067","display_name":"Jingli Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Jingli","raw_affiliation_strings":["Shanghai AI Laboratory","Shanghai Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Jiaotong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110026968","display_name":"Chenming Zhu","orcid":"https://orcid.org/0009-0001-6702-5937","observed_orcids":["https://orcid.org/0009-0001-6702-5937"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhu, Chenming","raw_affiliation_strings":["Shanghai AI Laboratory","University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100782117","display_name":"Xiaochen Chen","orcid":"https://orcid.org/0000-0003-1017-2773","observed_orcids":["https://orcid.org/0000-0003-1017-2773"]},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xiaochen","raw_affiliation_strings":["Beijing Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Normal University","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028468431","display_name":"Haodong Duan","orcid":"https://orcid.org/0000-0002-3052-4177","observed_orcids":["https://orcid.org/0000-0002-3052-4177"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Duan, Haodong","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078165161","display_name":"Xiangyu Yue","orcid":"https://orcid.org/0000-0002-6887-2046","observed_orcids":["https://orcid.org/0000-0002-6887-2046"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yue, Xiangyu","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896","observed_orcids":["https://orcid.org/0000-0002-8865-7896"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lin, Dahua","raw_affiliation_strings":["Shanghai AI Laboratory","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928830","display_name":"Tai Wang","orcid":"https://orcid.org/0000-0002-5994-3498","observed_orcids":["https://orcid.org/0000-0002-5994-3498","https://orcid.org/0000-0002-3308-9262"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Tai","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020672335","display_name":"Jiangmiao Pang","orcid":"https://orcid.org/0000-0002-6711-9319","observed_orcids":["https://orcid.org/0000-0002-6711-9319"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pang, Jiangmiao","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":156,"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":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9390000104904175},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.7020000219345093},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7129999995231628},{"id":"https://openalex.org/keywords/3d-computer-vision","display_name":"3D vision","score":0.828000009059906},{"id":"https://openalex.org/keywords/spatial-ability","display_name":"spatial ability","score":0.49300000071525574},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.5839999914169312},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.5519999861717224},{"id":"https://openalex.org/keywords/scene-reconstruction","display_name":"scene reconstruction","score":0.48500001430511475}],"concepts":[{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.8393999934196472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723800003528595},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6115999817848206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48660001158714294},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.4361000061035156},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C517642484","wikidata":"https://www.wikidata.org/wiki/Q2388514","display_name":"Intelligence analysis","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2806999981403351},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.23764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.23764","pdf_url":"https://arxiv.org/pdf/2505.23764","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.23764","doi":"https://doi.org/10.48550/arxiv.2505.23764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.23764","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:2505.23764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.23764","pdf_url":"https://arxiv.org/pdf/2505.23764","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":"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/W4416613191.pdf","grobid_xml":"https://content.openalex.org/works/W4416613191.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2964339842","https://openalex.org/W4382490555","https://openalex.org/W4389217168","https://openalex.org/W4399695957","https://openalex.org/W4402671266","https://openalex.org/W4403363374","https://openalex.org/W4403370767","https://openalex.org/W4403443917","https://openalex.org/W4403445186","https://openalex.org/W4404782761","https://openalex.org/W4405172832","https://openalex.org/W4405279515","https://openalex.org/W4405300890","https://openalex.org/W4405434026","https://openalex.org/W4406072889","https://openalex.org/W4407794264","https://openalex.org/W4409016787","https://openalex.org/W4412945426","https://openalex.org/W4413144646","https://openalex.org/W4413559154","https://openalex.org/W4415796658","https://openalex.org/W4416053382","https://openalex.org/W4416453804","https://openalex.org/W4417515183","https://openalex.org/W6948279226","https://openalex.org/W6979267127","https://openalex.org/W7128590487"],"related_works":["https://openalex.org/W4416453796","https://openalex.org/W7130585528","https://openalex.org/W4417297059","https://openalex.org/W4404782872","https://openalex.org/W7171504465","https://openalex.org/W4416706257","https://openalex.org/W4413144646","https://openalex.org/W4415016087","https://openalex.org/W4415539019","https://openalex.org/W7124297557"],"abstract_inverted_index":{"Spatial":[0],"intelligence":[1],"is":[2],"essential":[3],"for":[4,123,164],"multimodal":[5],"large":[6],"language":[7],"models":[8],"(MLLMs)":[9],"operating":[10],"in":[11],"the":[12,28,92,114,120,127],"complex":[13],"physical":[14],"world.":[15],"Existing":[16],"benchmarks,":[17],"however,":[18],"probe":[19],"only":[20],"single-image":[21],"relations":[22],"and":[23,72,81,85,100,119,151,158],"thus":[24],"fail":[25],"to":[26,43],"assess":[27],"multi-image":[29,44],"spatial":[30,45,166],"reasoning":[31,75,103,129,156],"that":[32,139],"real-world":[33],"deployments":[34],"demand.":[35],"We":[36,77],"introduce":[37],"MMSI-Bench,":[38],"a":[39,73,89],"VQA":[40],"benchmark":[41],"dedicated":[42],"intelligence.":[46,167],"Six":[47],"3D-vision":[48],"researchers":[49],"spent":[50],"more":[51],"than":[52],"300":[53],"hours":[54],"meticulously":[55],"crafting":[56],"1,000":[57],"challenging,":[58],"unambiguous":[59],"multiple-choice":[60],"questions":[61],"from":[62],"over":[63],"120,000":[64],"images,":[65],"each":[66],"paired":[67],"with":[68],"carefully":[69],"designed":[70],"distractors":[71],"stepwise":[74],"process.":[76],"conduct":[78],"extensive":[79],"experiments":[80],"evaluate":[82],"37":[83],"open-source":[84,94],"proprietary":[86],"MLLMs,":[87],"observing":[88],"wide":[90],"gap:":[91],"strongest":[93],"model":[95,104],"attains":[96],"roughly":[97],"30%":[98],"accuracy":[99],"OpenAI's":[101],"GPT-5":[102],"reaches":[105],"40%,":[106],"while":[107],"humans":[108],"score":[109],"97%.":[110],"These":[111],"results":[112],"underscore":[113],"challenging":[115],"nature":[116],"of":[117],"MMSI-Bench":[118],"substantial":[121],"headroom":[122],"future":[124],"research.":[125],"Leveraging":[126],"annotated":[128],"processes,":[130],"we":[131],"also":[132],"provide":[133],"an":[134],"automated":[135],"error":[136],"analysis":[137],"pipeline":[138],"diagnoses":[140],"four":[141],"dominant":[142],"failure":[143],"modes,":[144],"including":[145],"(1)":[146],"grounding":[147],"errors,":[148,153,157,161],"(2)":[149],"overlap-matching":[150],"scene-reconstruction":[152],"(3)":[154],"situation-transformation":[155],"(4)":[159],"spatial-logic":[160],"offering":[162],"insights":[163],"advancing":[165],"Project":[168],"page:":[169],"https://runsenxu.com/projects/MMSI_Bench":[170],".":[171]},"counts_by_year":[{"year":2026,"cited_by_count":125},{"year":2025,"cited_by_count":31}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2025-10-10T00:00:00"}
