{"id":"https://openalex.org/W4406400870","doi":"https://doi.org/10.1038/s42256-024-00963-y","title":"Visual cognition in multimodal large language models","display_name":"Visual cognition in multimodal large language models","publication_year":2025,"publication_date":"2025-01-15","ids":{"openalex":"https://openalex.org/W4406400870","doi":"https://doi.org/10.1038/s42256-024-00963-y"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-024-00963-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00963-y","pdf_url":"https://www.nature.com/articles/s42256-024-00963-y.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.nature.com/articles/s42256-024-00963-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035640324","display_name":"Luca M. Schulze Buschoff","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Luca M. Schulze Buschoff","raw_affiliation_strings":["Institute for Human-Centered AI, Helmholtz Munich, Oberschlei\u00dfheim, Germany","Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0009-0002-2964-2843","affiliations":[{"raw_affiliation_string":"Institute for Human-Centered AI, Helmholtz Munich, Oberschlei\u00dfheim, Germany","institution_ids":["https://openalex.org/I4210100097"]},{"raw_affiliation_string":"Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210112925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092048108","display_name":"Elif Akata","orcid":"https://orcid.org/0009-0001-2016-7671"},"institutions":[{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elif Akata","raw_affiliation_strings":["Institute for Human-Centered AI, Helmholtz Munich, Oberschlei\u00dfheim, Germany","Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany","University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":"https://orcid.org/0009-0001-2016-7671","affiliations":[{"raw_affiliation_string":"Institute for Human-Centered AI, Helmholtz Munich, Oberschlei\u00dfheim, Germany","institution_ids":["https://openalex.org/I4210100097"]},{"raw_affiliation_string":"Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210112925"]},{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061457780","display_name":"Matthias Bethge","orcid":"https://orcid.org/0000-0002-6417-7812"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Bethge","raw_affiliation_strings":["University of T\u00fcbingen, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101768980","display_name":"Eric Schulz","orcid":"https://orcid.org/0000-0003-3088-0371"},"institutions":[{"id":"https://openalex.org/I4210100097","display_name":"Institute of Bioinformatics and Systems Biology","ror":"https://ror.org/0127fwn18","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672","https://openalex.org/I4210100097"]},{"id":"https://openalex.org/I4210112925","display_name":"Max Planck Institute for Biological Cybernetics","ror":"https://ror.org/026nmvv73","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210112925"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eric Schulz","raw_affiliation_strings":["Institute for Human-Centered AI, Helmholtz Munich, Oberschlei\u00dfheim, Germany","Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Centered AI, Helmholtz Munich, Oberschlei\u00dfheim, Germany","institution_ids":["https://openalex.org/I4210100097"]},{"raw_affiliation_string":"Max Planck Institute for Biological Cybernetics, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210112925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035640324"],"corresponding_institution_ids":["https://openalex.org/I4210100097","https://openalex.org/I4210112925"],"apc_list":{"value":9750,"currency":"EUR","value_usd":11690},"apc_paid":{"value":9750,"currency":"EUR","value_usd":11690},"fwci":59.1955,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.99942587,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"96","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9952999949455261,"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/cognition","display_name":"Cognition","score":0.7021641731262207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48618096113204956},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4468914270401001},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3751606345176697},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.3051167130470276},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28364089131355286}],"concepts":[{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.7021641731262207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48618096113204956},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4468914270401001},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3751606345176697},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.3051167130470276},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28364089131355286}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s42256-024-00963-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00963-y","pdf_url":"https://www.nature.com/articles/s42256-024-00963-y.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s42256-024-00963-y","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-024-00963-y","pdf_url":"https://www.nature.com/articles/s42256-024-00963-y.pdf","source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1038848454","display_name":null,"funder_award_id":"EXC 2064/1 \u2013 390727645","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G1341008233","display_name":null,"funder_award_id":"EXC 2064/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5415233182","display_name":null,"funder_award_id":"01IS18039A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G7907426250","display_name":null,"funder_award_id":"390727645","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8128963897","display_name":null,"funder_award_id":"EXC 2064","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8915364236","display_name":null,"funder_award_id":"2064/1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"},{"id":"https://openalex.org/F4320336029","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406400870.pdf","grobid_xml":"https://content.openalex.org/works/W4406400870.grobid-xml"},"referenced_works_count":109,"referenced_works":["https://openalex.org/W40029570","https://openalex.org/W244491643","https://openalex.org/W1511739467","https://openalex.org/W1965831205","https://openalex.org/W1982966536","https://openalex.org/W2002170215","https://openalex.org/W2010931158","https://openalex.org/W2011301426","https://openalex.org/W2055904739","https://openalex.org/W2059100041","https://openalex.org/W2102630578","https://openalex.org/W2110597679","https://openalex.org/W2120380598","https://openalex.org/W2123713131","https://openalex.org/W2128152674","https://openalex.org/W2143891888","https://openalex.org/W2145780367","https://openalex.org/W2188746823","https://openalex.org/W2498626120","https://openalex.org/W2507135045","https://openalex.org/W2522500382","https://openalex.org/W2594035753","https://openalex.org/W2609031512","https://openalex.org/W2619383789","https://openalex.org/W2625439778","https://openalex.org/W2671811403","https://openalex.org/W2749069611","https://openalex.org/W2765191723","https://openalex.org/W2789580031","https://openalex.org/W2799950781","https://openalex.org/W2806280256","https://openalex.org/W2847827297","https://openalex.org/W2904925972","https://openalex.org/W2909534157","https://openalex.org/W2930789748","https://openalex.org/W2937454300","https://openalex.org/W2962802170","https://openalex.org/W2963305465","https://openalex.org/W2963965884","https://openalex.org/W2964138343","https://openalex.org/W2970971581","https://openalex.org/W3003257820","https://openalex.org/W3004346089","https://openalex.org/W3015965768","https://openalex.org/W3035965352","https://openalex.org/W3045548659","https://openalex.org/W3096013785","https://openalex.org/W3096397561","https://openalex.org/W3099878876","https://openalex.org/W3108490213","https://openalex.org/W3136535094","https://openalex.org/W3150635270","https://openalex.org/W3160638507","https://openalex.org/W3163675517","https://openalex.org/W3172887788","https://openalex.org/W3185341429","https://openalex.org/W3198599617","https://openalex.org/W4211017739","https://openalex.org/W4221143046","https://openalex.org/W4233071853","https://openalex.org/W4281690148","https://openalex.org/W4283080831","https://openalex.org/W4292213411","https://openalex.org/W4297677272","https://openalex.org/W4300402905","https://openalex.org/W4301435598","https://openalex.org/W4307844977","https://openalex.org/W4312480274","https://openalex.org/W4318919287","https://openalex.org/W4319322519","https://openalex.org/W4323655724","https://openalex.org/W4360836968","https://openalex.org/W4362458506","https://openalex.org/W4366822724","https://openalex.org/W4366850553","https://openalex.org/W4381827075","https://openalex.org/W4385262478","https://openalex.org/W4385292963","https://openalex.org/W4385430086","https://openalex.org/W4385571689","https://openalex.org/W4386042678","https://openalex.org/W4386740843","https://openalex.org/W4386827556","https://openalex.org/W4387378202","https://openalex.org/W4388000629","https://openalex.org/W4389518675","https://openalex.org/W4392773006","https://openalex.org/W4399893213","https://openalex.org/W4401024343","https://openalex.org/W4401042756","https://openalex.org/W4402671548","https://openalex.org/W4405140008","https://openalex.org/W6712034760","https://openalex.org/W6713645886","https://openalex.org/W6739901393","https://openalex.org/W6748203849","https://openalex.org/W6772383348","https://openalex.org/W6778883912","https://openalex.org/W6800751262","https://openalex.org/W6838461927","https://openalex.org/W6851949647","https://openalex.org/W6853108898","https://openalex.org/W6853344003","https://openalex.org/W6887904745","https://openalex.org/W6949209083","https://openalex.org/W6969259846","https://openalex.org/W6981194214","https://openalex.org/W6982639720","https://openalex.org/W7014595873"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2081348319","https://openalex.org/W1974622901","https://openalex.org/W4248151009","https://openalex.org/W3127991229","https://openalex.org/W2074627502"],"abstract_inverted_index":{"Abstract":[0],"A":[1],"chief":[2],"goal":[3],"of":[4,38,52,79,87,98,119,128,145,179],"artificial":[5],"intelligence":[6],"is":[7],"to":[8,26,68,105],"build":[9],"machines":[10],"that":[11,20],"think":[12],"like":[13],"people.":[14],"Yet":[15,46],"it":[16],"has":[17],"been":[18],"argued":[19],"deep":[21],"neural":[22],"network":[23],"architectures":[24],"fail":[25],"accomplish":[27],"this.":[28],"Researchers":[29],"have":[30,62],"asserted":[31],"these":[32,107,129,149],"models\u2019":[33],"limitations":[34],"in":[35,65,84,135,148],"the":[36,50,66,76,85,103,154,177],"domains":[37,86],"causal":[39,90,114],"reasoning,":[40],"intuitive":[41,44,88,93,117],"physics":[42],"and":[43,92,116,137,166,174],"psychology.":[45,94],"recent":[47],"advancements,":[48],"namely":[49],"rise":[51],"large":[53,81],"language":[54,82,172],"models,":[55,173],"particularly":[56],"those":[57],"designed":[58],"for":[59,156,161],"visual":[60,139],"processing,":[61],"rekindled":[63],"interest":[64],"potential":[67],"emulate":[69],"human-like":[70],"cognitive":[71],"abilities.":[72],"This":[73],"paper":[74],"evaluates":[75],"current":[77],"state":[78],"vision-based":[80,171],"models":[83,109,130],"physics,":[89],"reasoning":[91],"Through":[95],"a":[96,132],"series":[97],"controlled":[99],"experiments,":[100],"we":[101],"investigate":[102],"extent":[104],"which":[106],"modern":[108],"grasp":[110],"complex":[111],"physical":[112,164],"interactions,":[113],"relationships":[115],"understanding":[118,162],"others\u2019":[120],"preferences.":[121],"Our":[122,151],"findings":[123],"reveal":[124],"that,":[125],"while":[126],"some":[127],"demonstrate":[131],"notable":[133],"proficiency":[134],"processing":[136],"interpreting":[138],"data,":[140],"they":[141],"still":[142],"fall":[143],"short":[144],"human":[146],"capabilities":[147],"areas.":[150],"results":[152],"emphasize":[153],"need":[155],"integrating":[157],"more":[158],"robust":[159],"mechanisms":[160],"causality,":[163],"dynamics":[165],"social":[167],"cognition":[168],"into":[169],"modern-day,":[170],"point":[175],"out":[176],"importance":[178],"cognitively":[180],"inspired":[181],"benchmarks.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":28}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}