{"id":"https://openalex.org/W7212949815","doi":"https://doi.org/10.48550/arxiv.2609.12397","title":"UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation","display_name":"UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7212949815","doi":"https://doi.org/10.48550/arxiv.2609.12397"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.12397","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12397","pdf_url":"https://arxiv.org/pdf/2609.12397","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.12397","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009445787","display_name":"Danning Zhang","orcid":"https://orcid.org/0009-0006-1166-949X","observed_orcids":["https://orcid.org/0009-0006-1166-949X"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Danning","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151650331","display_name":"Yijing Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Yijing","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006940105","display_name":"Shuhan Zhuang","orcid":"https://orcid.org/0000-0001-8579-3924","observed_orcids":["https://orcid.org/0000-0001-8579-3924"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang, Shuhan","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124759567","display_name":"Mengqi Huang","orcid":"https://orcid.org/0000-0001-9449-4491","observed_orcids":["https://orcid.org/0000-0001-9449-4491"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Mengqi","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091315837","display_name":"Shaojin Wu","orcid":"https://orcid.org/0000-0002-7899-0863","observed_orcids":["https://orcid.org/0000-0002-7899-0863"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Shaojin","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008604905","display_name":"Shancheng Fang","orcid":"https://orcid.org/0000-0002-3100-3664","observed_orcids":["https://orcid.org/0000-0002-3100-3664"]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang, Shancheng","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126","observed_orcids":["https://orcid.org/0000-0001-5739-8126"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao, Zhendong","raw_affiliation_strings":["Institute of Artificial Intelligence","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7954000234603882,"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":0.7954000234603882,"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":0.20340000092983246,"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":9.999999747378752e-05,"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/evaluation-benchmark","display_name":"evaluation benchmark","score":0.49799999594688416},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.7129999995231628},{"id":"https://openalex.org/keywords/human-evaluation-correlation","display_name":"human evaluation correlation","score":0.4959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160000205039978},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6521999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5918999910354614},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46000000834465027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45899999141693115},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C2776196576","wikidata":"https://www.wikidata.org/wiki/Q196113","display_name":"Camouflage","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32409998774528503},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.12397","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12397","pdf_url":"https://arxiv.org/pdf/2609.12397","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.2609.12397","doi":"https://doi.org/10.48550/arxiv.2609.12397","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.12397","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:2609.12397","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.12397","pdf_url":"https://arxiv.org/pdf/2609.12397","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":[{"id":"https://openalex.org/G7336938272","display_name":null,"funder_award_id":"JYB2025XDXM103","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G818119199","display_name":null,"funder_award_id":"623B2094","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/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212949815.pdf","grobid_xml":"https://content.openalex.org/works/W7212949815.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W4221146106","https://openalex.org/W4381826954","https://openalex.org/W4387355666","https://openalex.org/W4400024881","https://openalex.org/W4407385068","https://openalex.org/W4409696757","https://openalex.org/W4414577807","https://openalex.org/W4414758720","https://openalex.org/W4416190349","https://openalex.org/W4417357119","https://openalex.org/W6948058629","https://openalex.org/W6948505238","https://openalex.org/W6966874861","https://openalex.org/W7131079003"],"related_works":["https://openalex.org/W4416045922","https://openalex.org/W7128535782","https://openalex.org/W4400024366","https://openalex.org/W7126225613","https://openalex.org/W4387355666","https://openalex.org/W4416251412","https://openalex.org/W7131381227","https://openalex.org/W4412945353","https://openalex.org/W7090810222","https://openalex.org/W4400517494"],"abstract_inverted_index":{"Multi-modal":[0,30],"image":[1,52],"generation,":[2,53],"particularly":[3],"subject-driven":[4],"customization,":[5],"has":[6],"garnered":[7],"growing":[8],"attention":[9],"in":[10,41],"recent":[11],"years.":[12],"Despite":[13],"the":[14,45,68,129,153,160],"rapid":[15],"advancement":[16],"of":[17,50,95,119,140,155,164],"generative":[18],"models,":[19],"their":[20],"evaluation":[21,134],"remains":[22],"largely":[23],"lagging.":[24],"Existing":[25],"methods,":[26],"whether":[27],"embedding-based":[28],"or":[29,112],"Large":[31],"Language":[32],"Model":[33],"(MLLM)-based,":[34],"evaluate":[35,152],"alignment":[36,48,74,90],"with":[37,58,132],"each":[38],"modal":[39],"condition":[40,47],"isolation,":[42],"which":[43],"contradicts":[44],"simultaneous":[46,75],"objective":[49],"multi-modal":[51],"leading":[54],"to":[55,150],"poor":[56],"consistency":[57],"human":[59,133],"judgments.":[60],"To":[61],"address":[62],"this":[63],"challenge,":[64],"we":[65,143],"propose":[66],"UFO,":[67],"first":[69,87],"unified":[70],"framework":[71],"for":[72,116],"omni-condition":[73,89],"evaluation.":[76],"Specifically,":[77],"UFO":[78,127],"introduces":[79],"a":[80,92,146],"novel":[81],"Atomized":[82],"Chain-of-Evaluation":[83],"paradigm,":[84],"i.e.,":[85],"it":[86],"decomposes":[88],"into":[91,104],"sequential":[93],"chain":[94],"fine-grained,":[96],"disentangled":[97],"Atomic":[98],"Evaluation":[99],"Units":[100],"(AEUs),":[101],"categorizes":[102],"them":[103],"distinct":[105],"modality-relevance":[106],"classes,":[107],"and":[108,166],"then":[109],"employs":[110],"general":[111],"dedicated":[113,147],"functional":[114],"calls":[115],"accurate":[117],"verification":[118],"different":[120],"AEU":[121],"types.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"that":[126],"achieves":[128],"highest":[130],"correlation":[131],"preferences,":[135],"delivering":[136],"an":[137],"average":[138],"improvement":[139],"15.25%.":[141],"Furthermore,":[142],"present":[144],"UFO-Bench,":[145],"benchmark":[148],"designed":[149],"holistically":[151],"performance":[154],"existing":[156],"customization":[157],"models":[158],"under":[159],"diverse":[161],"mutual":[162],"interactions":[163],"textual":[165],"visual":[167],"conditions.":[168]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-15T00:00:00"}