{"id":"https://openalex.org/W7138431409","doi":"https://doi.org/10.1609/aaai.v40i16.38389","title":"Beyond Counting: Evaluating Abstract and Emotional Reasoning in Vision-Language Models","display_name":"Beyond Counting: Evaluating Abstract and Emotional Reasoning in Vision-Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138431409","doi":"https://doi.org/10.1609/aaai.v40i16.38389"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38389","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38389","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38389/42351","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38389/42351","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129713448","display_name":"Yuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Zhou","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, UCAS"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, UCAS","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661720","display_name":"Yan Zhang","orcid":null},"institutions":[{"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":"Yan Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038083485","display_name":"Jianlong Chang","orcid":"https://orcid.org/0000-0002-0610-907X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianlong Chang","raw_affiliation_strings":["Huawei"],"affiliations":[{"raw_affiliation_string":"Huawei","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677933","display_name":"Xin Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I68581759","display_name":"China Academy of Launch Vehicle Technology","ror":"https://ror.org/012z62f48","country_code":"CN","type":"facility","lineage":["https://openalex.org/I68581759"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Gu","raw_affiliation_strings":["Research and Development Department of China Academy of Launch Vehicle Technology"],"affiliations":[{"raw_affiliation_string":"Research and Development Department of China Academy of Launch Vehicle Technology","institution_ids":["https://openalex.org/I68581759"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703939","display_name":"Ying Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129753129","display_name":"Kun Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Ding","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698759","display_name":"Guangwen Yang","orcid":null},"institutions":[{"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":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641951","display_name":"Shiming Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiming Xiang","raw_affiliation_strings":["MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, UCAS"],"affiliations":[{"raw_affiliation_string":"MAIS, Institute of Automation, Chinese Academy of Sciences\nSchool of Artificial Intelligence, UCAS","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5129713448"],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81268657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"13809","last_page":"13817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9117000102996826,"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":0.9117000102996826,"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/T11148","display_name":"Language, Metaphor, and Cognition","score":0.026200000196695328,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6937000155448914},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.646399974822998},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5874999761581421},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5527999997138977},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5376999974250793},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4887000024318695},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3804999887943268},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.36820000410079956},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6937000155448914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6486999988555908},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.646399974822998},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343999862670898},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47380000352859497},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.33410000801086426},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.31540000438690186},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38389","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38389","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38389/42351","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38389","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38389","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38389/42351","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8731286525726318,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138431409.pdf","grobid_xml":"https://content.openalex.org/works/W7138431409.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,22,56],"rapid":[2],"progress":[3,187],"of":[4,28,62,113,132],"Vision":[5],"Language":[6],"Models":[7],"(VLMs),":[8],"existing":[9],"benchmarks":[10],"still":[11],"concentrate":[12],"on":[13],"coarse-grained":[14],"object":[15],"recognition":[16],"or":[17],"simple":[18],"relational":[19],"reasoning,":[20],"leaving":[21],"fine-grained":[23,51,178],"and":[24,52,58,88,93,96,99,124,136,148,155,168,171,184,196],"higher-order":[25,53,126],"reasoning":[26,127],"abilities":[27],"these":[29,50],"systems":[30],"largely":[31],"unexamined.":[32],"To":[33],"bridge":[34],"this":[35],"critical":[36],"evaluation":[37,131],"gap,":[38],"we":[39,64],"introduce":[40],"EmojiGrid,":[41],"a":[42,66,81,110,140,176],"novel":[43],"diagnostic":[44],"benchmark":[45,179],"specifically":[46],"designed":[47],"to":[48,180],"probe":[49],"skills.":[54],"Leveraging":[55],"universal":[57],"semantically":[59],"rich":[60],"nature":[61],"emojis,":[63],"synthesize":[65],"grid\u2011based":[67],"visual":[68,200],"dataset":[69],"paired":[70],"with":[71,163],"29,000+":[72],"QA":[73],"pairs.":[74],"Each":[75],"pair":[76],"is":[77],"explicitly":[78],"anchored":[79],"in":[80,153],"three-level":[82],"cognitive":[83,114,150],"taxonomy":[84],"comprising":[85],"(i)":[86],"Perception":[87],"Information":[89],"Extraction,":[90],"(ii)":[91],"Relational":[92],"Structural":[94],"Reasoning,":[95],"(iii)":[97],"Abstraction":[98],"Advanced":[100],"Cognition.":[101],"These":[102],"dimensions":[103],"further":[104],"decompose":[105],"into":[106],"nine":[107],"categories":[108],"covering":[109],"broad":[111],"range":[112],"skills,":[115],"including":[116],"counting,":[117],"spatial":[118,166],"relations,":[119],"compositional":[120,164],"logic,":[121,165],"semantic":[122,172],"sentiment,":[123],"related":[125],"tasks.":[128],"Our":[129],"extensive":[130],"25":[133],"state-of-the-art":[134],"open-source":[135],"proprietary":[137],"VLMs":[138],"reveals":[139],"significant":[141],"performance":[142],"gap":[143],"between":[144],"foundational":[145],"perceptual":[146],"tasks":[147],"higher-level":[149],"abilities,":[151],"particularly":[152],"abstraction":[154],"advanced":[156],"emotional":[157,170],"reasoning.":[158],"Notably,":[159],"all":[160],"models":[161,189],"struggle":[162],"consistency,":[167],"especially":[169],"understanding.":[173],"EmojiGrid":[174],"provides":[175],"quantifiable,":[177],"diagnose":[181],"VLM":[182],"limitations":[183],"guides":[185],"future":[186],"toward":[188],"that":[190],"can":[191],"truly":[192],"perceive,":[193],"reason":[194],"about,":[195],"interpret":[197],"complex,":[198],"symbol-rich":[199],"scenes.":[201]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}