{"id":"https://openalex.org/W4415539028","doi":"https://doi.org/10.1145/3746027.3758208","title":"VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence","display_name":"VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539028","doi":"https://doi.org/10.1145/3746027.3758208"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758208","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758208","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090942417","display_name":"Chenhui Qiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhui Qiang","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5358-8659","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaoyang Wei","orcid":"https://orcid.org/0000-0002-5708-7157"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyang Wei","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5708-7157","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086353603","display_name":"Xumeng Han","orcid":"https://orcid.org/0000-0002-1636-463X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xumeng Han","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1636-463X","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zipeng Wang","orcid":"https://orcid.org/0009-0006-0918-5357"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zipeng Wang","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-0918-5357","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siyao Li","orcid":"https://orcid.org/0009-0007-3386-9502"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyao Li","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-3386-9502","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055543314","display_name":"Xiangyuan Lan","orcid":"https://orcid.org/0000-0001-8564-0346"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyuan Lan","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8564-0346","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665072","display_name":"Jiao Jiao","orcid":"https://orcid.org/0000-0003-3495-5158"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianbin Jiao","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3495-5158","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000034551","display_name":"Zhenjun Han","orcid":"https://orcid.org/0000-0002-9970-5152"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjun Han","raw_affiliation_strings":["University of the Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9970-5152","affiliations":[{"raw_affiliation_string":"University of the Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12698","last_page":"12705"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9950000047683716,"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/T10028","display_name":"Topic Modeling","score":0.9939000010490417,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6787999868392944},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5393000245094299},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5338000059127808},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.4226999878883362},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4162999987602234},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.35830000042915344},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.3472000062465668}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6787999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5799000263214111},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023000240325928},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4239000082015991},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.4226999878883362},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4162999987602234},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.271699994802475},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758208","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758208","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W3120043490","https://openalex.org/W4312846625","https://openalex.org/W4393149524","https://openalex.org/W4402716330","https://openalex.org/W4402727764","https://openalex.org/W4403791888","https://openalex.org/W4403792420","https://openalex.org/W4405595839","https://openalex.org/W4412945214"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,37,102,124,185],"rapid":[2],"development":[3],"of":[4,123],"MLLMs,":[5],"evaluating":[6],"their":[7],"visual":[8,61,115,161,177,193,201],"capabilities":[9,190],"has":[10],"become":[11],"increasingly":[12],"crucial.":[13],"Current":[14],"benchmarks":[15],"primarily":[16],"fall":[17],"into":[18],"two":[19],"main":[20],"types:":[21],"basic":[22],"perception":[23],"benchmarks,which":[24],"focus":[25],"on":[26,45,68,75,119],"local":[27,72],"details":[28,73],"but":[29,49],"lack":[30],"deep":[31],"reasoning":[32,41,65,165,182,198],"(e.g.,":[33],"''what":[34],"is":[35,156,208],"in":[36,154,174,191],"image?''),":[38],"and":[39,63,149,163,179,197,203],"mainstream":[40],"benchmarks,":[42],"which":[43],"concentrate":[44],"prominent":[46],"image":[47,85,125],"elements":[48],"may":[50],"fail":[51],"to":[52,107,187],"assess":[53],"subtle":[54,176],"clues":[55,130,162],"requiring":[56],"intricate":[57],"analysis.":[58,95,205],"However,":[59],"profound":[60],"understanding":[62,202],"complex":[64,135],"depend":[66],"more":[67,90],"interpreting":[69],"subtle,":[70],"inconspicuous":[71],"than":[74],"perceiving":[76],"salient,":[77],"macro-level":[78],"objects.":[79],"These":[80],"details,":[81],"though":[82],"occupying":[83],"minimal":[84],"area,":[86],"often":[87,117],"contain":[88],"richer,":[89],"critical":[91],"information":[92],"for":[93,134,199],"robust":[94],"To":[96],"bridge":[97],"this":[98],"gap,":[99],"we":[100],"introduce":[101],"VER-Bench,":[103],"a":[104],"novel":[105],"framework":[106],"evaluate":[108],"MLLMs'":[109],"ability":[110],"to:":[111],"1)":[112],"identify":[113],"fine-grained":[114,192],"clues,":[116],"occupying,":[118],"average,":[120],"just":[121],"0.25%":[122],"area;":[126],"2)":[127],"integrate":[128],"these":[129],"with":[131],"world":[132],"knowledge":[133],"reasoning.":[136],"Comprising":[137],"374":[138],"carefully":[139],"designed":[140],"questions":[141],"across":[142],"Geospatial,":[143],"Temporal,":[144],"Situational,":[145],"Intent,":[146],"System":[147],"State,":[148],"Symbolic":[150],"reasoning,":[151],"each":[152],"question":[153],"VER-Bench":[155,169],"accompanied":[157],"by":[158],"structured":[159],"evidence:":[160],"question-related":[164],"derived":[166],"from":[167],"them.":[168],"reveals":[170],"current":[171],"models'":[172,189],"limitations":[173],"extracting":[175],"evidence":[178,194],"constructing":[180],"evidence-based":[181],"chains,":[183],"highlighting":[184],"need":[186],"enhance":[188],"extraction,":[195],"integration,":[196],"genuine":[200],"human-like":[204],"The":[206],"dataset":[207],"available":[209],"at":[210],"https://github.com/verbta/ACMMM-25-Materials.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}