{"id":"https://openalex.org/W6948431963","doi":"https://doi.org/10.48550/arxiv.2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","display_name":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","publication_year":2025,"publication_date":"2025-02-23","ids":{"openalex":"https://openalex.org/W6948431963","doi":"https://doi.org/10.48550/arxiv.2502.16435"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.16435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2502.16435","pdf_url":"https://arxiv.org/pdf/2502.16435","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/2502.16435","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huang, Jen-Tse","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jen-Tse","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010781772","display_name":"D. Z. Dai","orcid":"https://orcid.org/0009-0000-3227-3140","observed_orcids":["https://orcid.org/0009-0000-3227-3140"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Dasen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Jen-Yuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jen-Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuan, Youliang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Youliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Xiaoyuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Wenxuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiao, Wenxiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Wenxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101941950","display_name":"Pinjia He","orcid":"https://orcid.org/0000-0003-3377-8129","observed_orcids":["https://orcid.org/0000-0003-3377-8129"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Pinjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110579339","display_name":"Zhaopeng Tu","orcid":"https://orcid.org/0000-0002-7900-6055","observed_orcids":["https://orcid.org/0000-0002-7900-6055"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Zhaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Duan, Haodong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Haodong","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":17,"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":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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":0.0006000000284984708,"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/T11605","display_name":"Visual Attention and Saliency Detection","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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9900000095367432},{"id":"https://openalex.org/keywords/mental-rotation","display_name":"mental rotation","score":0.7689999938011169},{"id":"https://openalex.org/keywords/figure-ground-discrimination","display_name":"figure-ground discrimination","score":0.9940000176429749},{"id":"https://openalex.org/keywords/automatic-test-generation","display_name":"automated test generation","score":0.531000018119812},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.367000013589859}],"concepts":[{"id":"https://openalex.org/C27362006","wikidata":"https://www.wikidata.org/wiki/Q272021","display_name":"Gestalt psychology","level":3,"score":0.7253000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589999794960022},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560699999332428},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.43149998784065247},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.42100000381469727},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35190001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3310000002384186},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.26409998536109924}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.16435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2502.16435","pdf_url":"https://arxiv.org/pdf/2502.16435","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.2502.16435","doi":"https://doi.org/10.48550/arxiv.2502.16435","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.16435","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:2502.16435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2502.16435","pdf_url":"https://arxiv.org/pdf/2502.16435","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/W6948431963.pdf","grobid_xml":"https://content.openalex.org/works/W6948431963.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W4366850553","https://openalex.org/W4388092751","https://openalex.org/W4388184869","https://openalex.org/W4388787338","https://openalex.org/W4395065466","https://openalex.org/W4399554747","https://openalex.org/W4402953065","https://openalex.org/W4403752320","https://openalex.org/W4403853618","https://openalex.org/W4404330874","https://openalex.org/W4405766390","https://openalex.org/W4406604137","https://openalex.org/W4406880731","https://openalex.org/W4407571828","https://openalex.org/W4407794264","https://openalex.org/W4413926275","https://openalex.org/W4416780398","https://openalex.org/W4417300113","https://openalex.org/W4417443023","https://openalex.org/W4417515183","https://openalex.org/W4417521014","https://openalex.org/W6891842723","https://openalex.org/W6891882440","https://openalex.org/W6948369276","https://openalex.org/W7117695888","https://openalex.org/W7119523234","https://openalex.org/W7127380112","https://openalex.org/W7164501397"],"related_works":["https://openalex.org/W7155006801","https://openalex.org/W7140120024","https://openalex.org/W7123849271","https://openalex.org/W6891885324","https://openalex.org/W7171653369","https://openalex.org/W4417286102","https://openalex.org/W7162606446","https://openalex.org/W4399794195","https://openalex.org/W4416018510","https://openalex.org/W4405355501"],"abstract_inverted_index":{"Humans":[0],"develop":[1],"perception":[2],"through":[3],"a":[4,47,56,106,168],"bottom-up":[5],"hierarchy:":[6],"from":[7,54],"basic":[8],"primitives":[9],"and":[10,75,96,120,140],"Gestalt":[11],"principles":[12],"to":[13,72,124],"high-level":[14],"semantics.":[15],"Current":[16],"Multimodal":[17],"Large":[18],"Language":[19],"Models":[20,128],"(MLLMs)":[21],"are":[22],"trained":[23],"directly":[24],"on":[25,34,131,156],"complex":[26],"downstream":[27],"tasks.":[28],"Does":[29],"it":[30],"guarantee":[31],"their":[32],"performance":[33,154],"these":[35],"foundational":[36],"visual":[37,66,173],"capabilities?":[38],"To":[39],"systematically":[40],"investigate":[41],"this":[42],"gap,":[43],"we":[44,69,85],"introduce":[45],"VisFacor,":[46,84],"benchmark":[48],"that":[49,153],"digitizes":[50],"20":[51],"vision-centric":[52],"subtests":[53],"FRCT,":[55],"well-established":[57],"cognitive":[58],"psychology":[59],"assessment":[60],"spanning":[61],"four":[62],"domains":[63],"of":[64,108,144,167,171],"human":[65],"cognition.":[67,174],"Furthermore,":[68],"design":[70],"algorithms":[71],"automatically":[73],"construct":[74,121],"validate":[76],"unlimited":[77],"test":[78],"cases":[79],"with":[80],"controllable":[81],"difficulty.":[82],"Using":[83],"evaluate":[86],"39":[87],"frontier":[88],"MLLMs,":[89],"including":[90],"both":[91],"proprietary":[92],"(e.g.,":[93,98],"GPT,":[94],"Gemini)":[95],"open-source":[97],"LLaMA,":[99],"Qwen)":[100],"models.":[101],"The":[102],"best":[103],"model":[104,145],"achieves":[105],"score":[107],"only":[109],"55.9%.":[110],"Analysis":[111],"reveals":[112],"good":[113],"internal":[114],"consistency":[115],"(Cronbach's":[116],"alpha":[117],"=":[118],"0.94)":[119],"validity":[122],"(compared":[123],"existing":[125,157],"vision":[126],"benchmarks).":[127],"consistently":[129],"fail":[130],"tasks":[132],"such":[133],"as":[134],"mental":[135],"rotation,":[136],"spatial":[137],"relation":[138],"inference,":[139],"figure-ground":[141],"discrimination,":[142],"regardless":[143],"size":[146],"or":[147],"prompting":[148],"strategy.":[149],"These":[150],"findings":[151],"suggest":[152],"improvements":[155],"general":[158],"benchmarks":[159],"might":[160],"represent":[161],"castles":[162],"in":[163],"the":[164],"air":[165],"instead":[166],"genuine":[169],"mastery":[170],"human-like":[172]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}