{"id":"https://openalex.org/W7108203365","doi":"https://doi.org/10.48550/arxiv.2511.22989","title":"MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation","display_name":"MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation","publication_year":2025,"publication_date":"2025-11-28","ids":{"openalex":"https://openalex.org/W7108203365","doi":"https://doi.org/10.48550/arxiv.2511.22989"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.22989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22989","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2511.22989","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Oshima, Yuta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oshima, Yuta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Miyake, Daiki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miyake, Daiki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Matsutani, Kohsei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matsutani, Kohsei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Iwasawa, Yusuke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iwasawa, Yusuke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Suzuki, Masahiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzuki, Masahiro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Matsuo, Yutaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matsuo, Yutaka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Furuta, Hiroki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furuta, Hiroki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6460999846458435,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6460999846458435,"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":0.164900004863739,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8289999961853027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5392000079154968},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5382999777793884},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5113999843597412},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.451200008392334},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4341000020503998}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8289999961853027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921000123023987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5392000079154968},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5113999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4553999900817871},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.39750000834465027},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.390500009059906},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C150189527","wikidata":"https://www.wikidata.org/wiki/Q356674","display_name":"Reference model","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.22989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22989","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.22989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22989","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"text-to-image":[1,175],"generation":[2,10,38],"models":[3,176],"have":[4],"acquired":[5],"the":[6,17,95,114,129,197],"ability":[7],"of":[8,19,66,116,131,174],"multi-reference":[9,125,208],"and":[11,25,90,150,162,184,199,213],"editing;":[12],"that":[13],"is,":[14],"to":[15,77,82,93,112,124,134,195],"inherit":[16],"appearance":[18],"subjects":[20],"from":[21,50],"multiple":[22],"reference":[23,45,149],"images":[24],"re-render":[26],"them":[27],"in":[28,53,98,207],"new":[29],"contexts.":[30],"However,":[31],"existing":[32],"benchmark":[33,194],"datasets":[34],"often":[35],"focus":[36],"on":[37],"using":[39],"a":[40,43,63,159,172,201],"single":[41],"or":[42,56,84],"few":[44],"images,":[46],"which":[47,109],"prevents":[48],"us":[49],"measuring":[51],"progress":[52],"model":[54,117],"performance":[55],"identifying":[57],"weaknesses":[58],"when":[59],"following":[60],"instructions":[61],"with":[62],"larger":[64],"number":[65,130],"references.":[67,101],"In":[68],"addition,":[69],"their":[70,178],"task":[71],"definitions":[72],"are":[73,88,215],"still":[74],"vague,":[75],"limited":[76],"axes":[78],"such":[79],"as":[80,191],"``what":[81],"edit''":[83],"``how":[85],"many":[86],"references":[87,132,140,154,166],"given'',":[89],"therefore":[91],"fail":[92],"capture":[94],"challenges":[96],"inherent":[97],"combining":[99],"heterogeneous":[100],"To":[102],"address":[103],"this":[104],"gap,":[105],"we":[106],"introduce":[107],"MultiBanana,":[108],"is":[110,189],"designed":[111],"assess":[113],"edge":[115],"capabilities":[118],"by":[119],"widely":[120],"covering":[121],"problems":[122],"specific":[123],"settings:":[126],"(1)":[127],"varying":[128],"(up":[133],"8),":[135],"(2)":[136],"domain":[137],"mismatch":[138,147],"among":[139,171],"(e.g.,":[141,158],"photo":[142],"vs.":[143],"anime),":[144],"(3)":[145],"scale":[146],"between":[148],"target":[151],"scenes,":[152],"(4)":[153],"containing":[155],"rare":[156],"concepts":[157],"red":[160],"banana),":[161],"(5)":[163],"multilingual":[164],"textual":[165],"for":[167,186,204],"rendering.":[168],"Our":[169,211],"analysis":[170],"variety":[173],"reveals":[177],"respective":[179],"performances,":[180],"typical":[181],"failure":[182],"modes,":[183],"areas":[185],"improvement.":[187],"MultiBanana":[188],"released":[190],"an":[192],"open":[193],"push":[196],"boundaries":[198],"establish":[200],"standardized":[202],"basis":[203],"fair":[205],"comparison":[206],"image":[209],"generation.":[210],"data":[212],"code":[214],"available":[216],"at":[217],"https://github.com/matsuolab/multibanana":[218],".":[219]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-03T00:00:00"}