{"id":"https://openalex.org/W7166804489","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1268","title":"ComicVQA: A Benchmark for Visual Reasoning in Multimodal LLMs","display_name":"ComicVQA: A Benchmark for Visual Reasoning in Multimodal LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166804489","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1268"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1268","pdf_url":"https://aclanthology.org/2026.findings-acl.1268.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1268.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110982973","display_name":"Eric Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Esther Gan","raw_affiliation_strings":["National University of Singapore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore ,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025906003","display_name":"H. Alex Brown","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hannah Brown","raw_affiliation_strings":["National University of Singapore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore ,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022071541","display_name":"David Herel","orcid":"https://orcid.org/0009-0000-1861-3778"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"David Herel","raw_affiliation_strings":["Czech Technical University in Prague ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Technical University in Prague ,","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770306","display_name":"Kenji Kawaguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kenji Kawaguchi","raw_affiliation_strings":["National University of Singapore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore ,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139753314","display_name":"Min-Yen Kan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore ,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139739162","display_name":"Michael Qizhe Shieh","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I66855515","display_name":"Repsol (Spain)","ror":"https://ror.org/028bzjj61","country_code":"ES","type":"company","lineage":["https://openalex.org/I66855515"]}],"countries":["ES","SG"],"is_corresponding":false,"raw_author_name":"Michael Qizhe Shieh","raw_affiliation_strings":["National University of Singapore ,","absolute AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore ,","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"absolute AI","institution_ids":["https://openalex.org/I66855515"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83631004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25347","last_page":"25370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.755299985408783,"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":0.755299985408783,"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/T10028","display_name":"Topic Modeling","score":0.029100000858306885,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.027000000700354576,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.43470001220703125},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.38370001316070557},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.30219998955726624},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.28450000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5967000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5551999807357788},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26269999146461487}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1268","pdf_url":"https://aclanthology.org/2026.findings-acl.1268.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1268","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1268","pdf_url":"https://aclanthology.org/2026.findings-acl.1268.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331617","display_name":"National Supercomputing Centre Singapore","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166804489.pdf","grobid_xml":"https://content.openalex.org/works/W7166804489.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"Comic":[2],"Visual":[3],"Question":[4],"Answering":[5],"(ComicVQA),":[6],"a":[7,69,85,110],"comics-based":[8],"benchmark":[9,112],"for":[10,113],"evaluating":[11],"MLLMs":[12,93],"on":[13,40,46,65,96],"visual":[14,24,104,116],"reasoning.ComicVQA":[15],"comprises":[16],"of":[17],"(i)":[18],"Missing":[19,41],"Panel":[20,28,42,47],"Prediction,":[21],"testing":[22],"fine-grained":[23,103],"grounding":[25],"and":[26,44,55,75,84,100],"(ii)":[27],"Sorting,":[29,48],"which":[30],"evaluates":[31],"sequential":[32],"narrative":[33],"understanding.Proprietary":[34],"models":[35,51,74],"achieve":[36,61],"up":[37],"to":[38],"62.6%":[39],"Prediction":[43],"46.4%":[45],"whereas":[49],"open-source":[50],"reach":[52],"only":[53],"47.7%":[54],"26.9%,":[56],"respectively.In":[57],"contrast,":[58],"human":[59],"annotators":[60],"over":[62],"83%":[63],"accuracy":[64],"both":[66],"tasks,":[67],"revealing":[68],"large":[70],"gap":[71],"between":[72],"current":[73,92],"human-level":[76],"multimodal":[77,115],"understanding":[78],"in":[79,118],"comics.Through":[80],"controlled":[81],"ordering":[82],"ablations":[83],"detailed":[86],"error":[87],"taxonomy,":[88],"we":[89],"show":[90],"that":[91],"rely":[94],"primarily":[95],"coarse":[97],"temporal":[98],"cues":[99],"struggle":[101],"with":[102],"reasoning.These":[105],"findings":[106],"demonstrate":[107],"ComicVQA":[108],"as":[109],"diagnostic":[111],"advancing":[114],"reasoning":[117],"comics.":[119],"1":[120]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-07-02T00:00:00"}