{"id":"https://openalex.org/W4415329133","doi":"https://doi.org/10.48550/arxiv.2505.15616","title":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models","display_name":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4415329133","doi":"https://doi.org/10.48550/arxiv.2505.15616"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.15616","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.15616","pdf_url":"https://arxiv.org/pdf/2505.15616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053695187","display_name":"Ruilin Yao","orcid":"https://orcid.org/0009-0002-6654-2294","observed_orcids":["https://orcid.org/0009-0002-6654-2294"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"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"]},{"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":"Yao, Ruilin","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences","Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Bo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Bo","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109747583","display_name":"Jirui Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"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"]},{"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":"Huang, Jirui","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences","Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104089217","display_name":"Xinwei Long","orcid":"https://orcid.org/0009-0006-5097-5430","observed_orcids":["https://orcid.org/0009-0006-5097-5430"]},"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":"Long, Xinwei","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056616130","display_name":"Yifang Zhang","orcid":"https://orcid.org/0009-0001-3902-1277","observed_orcids":["https://orcid.org/0009-0001-3902-1277"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yifang","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zou, Tianyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zou, Tianyu","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035870404","display_name":"Yu\u2010Fei Wu","orcid":"https://orcid.org/0000-0002-3970-3999","observed_orcids":["https://orcid.org/0000-0002-3970-3999"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Yufei","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109506509","display_name":"Shichao Su","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Su, Shichao","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103166791","display_name":"Yifan Xu","orcid":"https://orcid.org/0000-0003-2467-888X","observed_orcids":["https://orcid.org/0000-0003-2467-888X"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yifan","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zeng, Wenxi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Wenxi","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077129218","display_name":"Zhaoyu Yang","orcid":"https://orcid.org/0000-0002-9239-1461","observed_orcids":["https://orcid.org/0000-0002-9239-1461"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Zhaoyu","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Guoyou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Guoyou","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113029149","display_name":"Shilan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shilan","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038201049","display_name":"Zichan Li","orcid":"https://orcid.org/0000-0002-1461-4121","observed_orcids":["https://orcid.org/0000-0002-1461-4121"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zichan","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003775716","display_name":"Yaxiong Chen","orcid":"https://orcid.org/0000-0002-2903-6723","observed_orcids":["https://orcid.org/0000-0002-2903-6723"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yaxiong","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101598103","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-3836-0664","observed_orcids":["https://orcid.org/0000-0002-3836-0664","https://orcid.org/0000-0002-4006-7029"]},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong, Shengwu","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102970133","display_name":"Peng Xu","orcid":"https://orcid.org/0000-0002-6431-1110","observed_orcids":["https://orcid.org/0000-0002-6431-1110"]},"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":"Xu, Peng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319576","display_name":"Jiajun Zhang","orcid":"https://orcid.org/0000-0001-7107-4814","observed_orcids":["https://orcid.org/0000-0001-7107-4814","https://orcid.org/0000-0001-7998-1996"]},"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"]},{"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":"Zhang, Jiajun","raw_affiliation_strings":["Institute of Automation Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004875850","display_name":"Bowen Zhou","orcid":"https://orcid.org/0000-0003-4421-9787","observed_orcids":["https://orcid.org/0000-0003-4421-9787"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"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":"Zhou, Bowen","raw_affiliation_strings":["Shanghai AI Lab","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Lab","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040302008","display_name":"David Andrew Clifton","orcid":"https://orcid.org/0000-0002-9848-8555","observed_orcids":["https://orcid.org/0000-0002-9848-8555"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Clifton, David","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001254143","display_name":"Luc Van Gool","orcid":"https://orcid.org/0000-0002-3445-5711","observed_orcids":["https://orcid.org/0000-0002-3445-5711"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Gool, Luc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"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":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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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":0.0,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9959999918937683},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.8069999814033508},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.7110000252723694},{"id":"https://openalex.org/keywords/compositional-reasoning","display_name":"compositional reasoning","score":0.8769999742507935},{"id":"https://openalex.org/keywords/image-perception","display_name":"image perception","score":0.5289999842643738},{"id":"https://openalex.org/keywords/multi-level-evaluation","display_name":"multi-level evaluation","score":0.5350000262260437},{"id":"https://openalex.org/keywords/image-annotation","display_name":"image annotation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/social-media-images","display_name":"social media images","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261999845504761},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6377000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6223999857902527},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.45210000872612},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.15616","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.15616","pdf_url":"https://arxiv.org/pdf/2505.15616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15616","doi":"https://doi.org/10.48550/arxiv.2505.15616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15616","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15616","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.15616","pdf_url":"https://arxiv.org/pdf/2505.15616","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329133.pdf","grobid_xml":"https://content.openalex.org/works/W4415329133.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416131331","https://openalex.org/W7162606446","https://openalex.org/W7133321700","https://openalex.org/W6891885324","https://openalex.org/W4415797496","https://openalex.org/W4406273444","https://openalex.org/W4409538845","https://openalex.org/W4405882635","https://openalex.org/W4417286102","https://openalex.org/W4416517509"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"achieved":[6],"significant":[7],"advances":[8],"in":[9,33,54,144,188],"integrating":[10],"visual":[11],"and":[12,22,80,87,99,163,168,178],"linguistic":[13],"information,":[14],"yet":[15],"their":[16],"ability":[17],"to":[18,120,123,130],"reason":[19],"about":[20],"complex":[21],"real-world":[23],"scenarios":[24],"remains":[25],"limited.":[26],"The":[27],"existing":[28],"benchmarks":[29],"are":[30,137,172],"usually":[31],"constructed":[32],"the":[34,45,56,141,189],"task-oriented":[35],"manner":[36],"without":[37],"guarantee":[38],"that":[39,104],"different":[40],"task":[41,94],"samples":[42],"come":[43],"from":[44,127,140],"same":[46],"data":[47],"distribution,":[48],"thus":[49],"they":[50],"often":[51],"fall":[52],"short":[53],"evaluating":[55],"synergistic":[57],"effects":[58],"of":[59,180],"lower-level":[60],"perceptual":[61],"capabilities":[62],"on":[63],"higher-order":[64],"reasoning.":[65,100,132],"To":[66],"lift":[67],"this":[68,116],"limitation,":[69],"we":[70],"contribute":[71],"Lens,":[72],"a":[73],"multi-level":[74],"benchmark":[75],"with":[76,109],"3.4K":[77],"contemporary":[78],"images":[79,136],"60K+":[81],"human-authored":[82],"questions":[83],"covering":[84],"eight":[85],"tasks":[86],"12":[88],"daily":[89],"scenarios,":[90],"forming":[91],"three":[92],"progressive":[93],"tiers,":[95],"i.e.,":[96],"perception,":[97],"understanding,":[98],"One":[101],"feature":[102],"is":[103,107],"each":[105],"image":[106],"equipped":[108],"rich":[110],"annotations":[111],"for":[112],"all":[113],"tasks.":[114,191],"Thus,":[115],"dataset":[117],"intrinsically":[118],"supports":[119],"evaluate":[121,154],"MLLMs":[122,157],"handle":[124],"image-invariable":[125],"prompts,":[126],"basic":[128],"perception":[129],"compositional":[131],"In":[133],"addition,":[134],"our":[135],"manully":[138],"collected":[139],"social":[142],"media,":[143],"which":[145],"53%":[146],"were":[147],"published":[148],"later":[149,174],"than":[150,175,186],"Jan.":[151],"2025.":[152],"We":[153],"15+":[155],"frontier":[156],"such":[158],"as":[159],"Qwen2.5-VL-72B,":[160],"InternVL3-78B,":[161],"GPT-4o":[162],"two":[164],"reasoning":[165,190],"models":[166,171],"QVQ-72B-preview":[167],"Kimi-VL.":[169],"These":[170],"released":[173],"Dec.":[176],"2024,":[177],"none":[179],"them":[181],"achieve":[182],"an":[183],"accuracy":[184],"greater":[185],"60%":[187],"Project":[192],"page:":[193,198],"https://github.com/Lens4MLLMs/lens.":[194],"ICCV":[195],"2025":[196],"workshop":[197],"https://lens4mllms.github.io/mars2-workshop-iccv2025/":[199]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-19T00:00:00"}
