{"id":"https://openalex.org/W4414828366","doi":"https://doi.org/10.1109/iccv51701.2025.01608","title":"LMM4LMM: Benchmarking and Evaluating Large-Multimodal Image Generation With LMMs","display_name":"LMM4LMM: Benchmarking and Evaluating Large-Multimodal Image Generation With LMMs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414828366","doi":"https://doi.org/10.1109/iccv51701.2025.01608"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.08358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100639360","display_name":"Jiarui Wang","orcid":"https://orcid.org/0000-0003-4098-2443"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarui Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015291775","display_name":"Huiyu Duan","orcid":"https://orcid.org/0000-0002-6519-4067"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082631944","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0001-9025-2014"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110935260","display_name":"Juntong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juntong Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087550523","display_name":"Guangtao Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17312","last_page":"17323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9549000263214111,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9549000263214111,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9345999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7688999772071838},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7519999742507935},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6912000179290771},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6628999710083008},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5464000105857849},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5338000059127808},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44839999079704285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43140000104904175}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7688999772071838},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7519999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7171000242233276},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6847000122070312},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6345000267028809},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35179999470710754},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.08358","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.08358","pdf_url":"https://arxiv.org/pdf/2504.08358","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.08358","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.08358","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.08358","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.08358","pdf_url":"https://arxiv.org/pdf/2504.08358","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7794367482","display_name":null,"funder_award_id":"BX20250411,2025M773473","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8614732932","display_name":null,"funder_award_id":"62271312,62401365,62225112,62132006,U24A20220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"in":[2],"large":[3,117],"multimodal":[4,118],"models":[5],"(LMMs)":[6],"have":[7],"significantly":[8],"advanced":[9],"both":[10,158],"text-to-image":[11],"(T2I)":[12],"generation":[13,120],"and":[14,30,37,61,82,92,128,142,162,167],"image-to-text":[15],"(I2T)":[16],"interpretation.":[17],"However,":[18],"many":[19],"generated":[20,101],"images":[21,100],"still":[22],"suffer":[23],"from":[24,102,121],"issues":[25],"related":[26],"to":[27],"perceptual":[28],"quality":[29],"text-image":[31,126],"alignment.":[32],"Given":[33],"the":[34,155,159],"high":[35],"cost":[36],"inefficiency":[38],"of":[39,157],"manual":[40],"evaluation,":[41],"an":[42,112],"automatic":[43],"metric":[44,114],"that":[45,135],"aligns":[46],"with":[47],"human":[48],"preferences":[49],"is":[50],"desirable.":[51],"To":[52],"this":[53],"end,":[54],"we":[55,109],"present":[56],"EvalMi-50K,":[57,108,141],"a":[58],"comprehensive":[59,71],"dataset":[60,161],"benchmark":[62,152],"for":[63,115],"evaluating":[64,116],"large-multimodal":[65],"image":[66,150],"generation,":[67],"which":[68],"features":[69],"(i)":[70],"tasks,":[72],"encompassing":[73],"2,100":[74],"extensive":[75],"prompts":[76],"across":[77],"20":[78],"fine-grained":[79],"task":[80],"dimensions,":[81],"(ii)":[83],"large-scale":[84],"human-preference":[85],"annotations,":[86],"including":[87,124],"100K":[88],"mean-opinion":[89],"scores":[90],"(MOSs)":[91],"50K":[93],"question-answering":[94],"(QA)":[95],"pairs":[96],"annotated":[97],"on":[98,107,140,147],"50,400":[99],"24":[103],"T2I":[104,119],"models.":[105],"Based":[106],"propose":[110],"LMM4LMM,":[111],"LMM-based":[113],"multiple":[122],"dimensions":[123],"perception,":[125],"correspondence,":[127],"task-specific":[129],"accuracy.":[130],"Extensive":[131],"experimental":[132],"results":[133],"show":[134],"LMM4LMM":[136,163,168],"achieves":[137],"state-of-the-art":[138],"performance":[139],"exhibits":[143],"strong":[144],"generalization":[145],"ability":[146],"other":[148],"AI-generated":[149],"evaluation":[151],"datasets,":[153],"manifesting":[154],"generality":[156],"EvalMi-50K":[160,166],"metric.":[164],"Both":[165],"will":[169],"be":[170],"released":[171],"at":[172],"https://github.com/IntMeGroup/LMM4LMM.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}