{"id":"https://openalex.org/W4415133763","doi":"https://doi.org/10.48550/arxiv.2506.02537","title":"VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning","display_name":"VisuRiddles: Fine-grained Perception is a Primary Bottleneck for Multimodal Large Language Models in Abstract Visual Reasoning","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4415133763","doi":"https://doi.org/10.48550/arxiv.2506.02537"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.02537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02537","pdf_url":"https://arxiv.org/pdf/2506.02537","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.02537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015410459","display_name":"Hao Yan","orcid":"https://orcid.org/0009-0007-7750-0758"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yan, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022743719","display_name":"Xingchen Liu","orcid":"https://orcid.org/0000-0001-5597-7722"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xingchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767918","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-1335-7645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cao, Zhenbiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Zhenbiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041002670","display_name":"Handong Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Handong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114677156","display_name":"Liang Yin","orcid":"https://orcid.org/0009-0002-1180-148X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Liang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042666332","display_name":"Xinxing Su","orcid":"https://orcid.org/0000-0002-0412-7688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Xinxing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434170","display_name":"Zihao Chen","orcid":"https://orcid.org/0000-0002-6733-4756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112882104","display_name":"Jihao Wu","orcid":"https://orcid.org/0000-0003-3235-0446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030174783","display_name":"Minghui Liao","orcid":"https://orcid.org/0000-0002-2583-4314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Minghui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weng, Chao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344369","display_name":"Wei Chen","orcid":"https://orcid.org/0009-0000-5168-6645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100389396","display_name":"Yuliang Liu","orcid":"https://orcid.org/0000-0002-3037-173X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039363991","display_name":"Xiang Bai","orcid":"https://orcid.org/0000-0002-3449-5940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Xiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5015410459"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9941999912261963,"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":0.9941999912261963,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9401000142097473,"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":0.9151999950408936,"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":0.7921000123023987},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.777999997138977},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6527000069618225},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/principal","display_name":"Principal (computer security)","score":0.448199987411499},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3889000117778778},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7921000123023987},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.777999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581999897956848},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5424000024795532},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3912000060081482},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.02537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02537","pdf_url":"https://arxiv.org/pdf/2506.02537","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.02537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.02537","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.02537","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02537","pdf_url":"https://arxiv.org/pdf/2506.02537","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415133763.pdf","grobid_xml":"https://content.openalex.org/works/W4415133763.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"strides":[1],"in":[2,13,30,42],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"have":[8],"significantly":[9],"advanced":[10],"their":[11,51],"performance":[12,155],"many":[14],"reasoning":[15,70,79,121],"tasks.":[16,162],"However,":[17],"Abstract":[18],"Visual":[19],"Reasoning":[20],"(AVR)":[21],"remains":[22],"a":[23,59],"critical":[24],"challenge,":[25],"primarily":[26],"due":[27],"to":[28,49,67],"limitations":[29],"perceiving":[31],"abstract":[32,52,107],"graphics.":[33],"To":[34],"tackle":[35],"this":[36],"issue,":[37],"we":[38,56,82],"investigate":[39],"the":[40,84,145,154],"bottlenecks":[41],"current":[43],"MLLMs":[44,158],"and":[45,76,123,129,148,165],"synthesize":[46],"training":[47,104,127],"data":[48,105],"improve":[50],"visual":[53,142],"perception.":[54],"First,":[55],"propose":[57],"VisuRiddles,":[58],"benchmark":[60],"for":[61,92,106,117],"AVR,":[62],"featuring":[63],"tasks":[64],"meticulously":[65],"constructed":[66],"assess":[68],"models'":[69],"capacities":[71],"across":[72],"five":[73],"core":[74],"dimensions":[75],"two":[77],"high-level":[78],"categories.":[80],"Second,":[81],"introduce":[83],"Perceptual":[85],"Riddle":[86],"Synthesizer":[87],"(PRS),":[88],"an":[89],"automated":[90],"framework":[91,151],"generating":[93],"riddles":[94],"with":[95],"fine-grained":[96,112,141],"perceptual":[97,113],"descriptions.":[98],"PRS":[99],"not":[100],"only":[101],"generates":[102],"valuable":[103],"graphics":[108],"but":[109],"also":[110],"provides":[111],"description,":[114],"crucially":[115],"allowing":[116],"supervision":[118],"over":[119],"intermediate":[120],"stages":[122],"thereby":[124],"improving":[125],"both":[126],"efficacy":[128],"model":[130],"interpretability.":[131],"Our":[132,163],"extensive":[133],"experimental":[134],"results":[135],"on":[136,159],"VisuRiddles":[137],"empirically":[138],"validate":[139],"that":[140],"perception":[143],"is":[144],"principal":[146],"bottleneck":[147],"our":[149],"synthesis":[150],"markedly":[152],"enhances":[153],"of":[156],"contemporary":[157],"these":[160],"challenging":[161],"code":[164],"dataset":[166],"will":[167],"be":[168],"released":[169],"at":[170],"https://github.com/yh-hust/VisuRiddles":[171]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-14T00:00:00"}