{"id":"https://openalex.org/W7123350832","doi":"https://doi.org/10.1109/access.2026.3651887","title":"UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation","display_name":"UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123350832","doi":"https://doi.org/10.1109/access.2026.3651887"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3651887","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3651887","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3651887","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000868881","display_name":"Wonjun Kang","orcid":"https://orcid.org/0000-0001-5369-6011"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjun Kang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0009-6198-7906","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038165118","display_name":"Byeongkeun Ahn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095123","display_name":"The Seoul Institute","ror":"https://ror.org/00pnt8b91","country_code":"KR","type":"government","lineage":["https://openalex.org/I2801402630","https://openalex.org/I4210095123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeongkeun Ahn","raw_affiliation_strings":["Independent Researcher, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-8517-6177","affiliations":[{"raw_affiliation_string":"Independent Researcher, Seoul, South Korea","institution_ids":["https://openalex.org/I4210095123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122852826","display_name":"Minjae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133515","display_name":"International Association of Korean Literary and Cultural Studies","ror":"https://ror.org/03nwyka65","country_code":"KR","type":"other","lineage":["https://openalex.org/I4210133515"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minjae Lee","raw_affiliation_strings":["FuriosaAI, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FuriosaAI, Seoul, South Korea","institution_ids":["https://openalex.org/I4210133515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020064757","display_name":"Kevin Galim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133515","display_name":"International Association of Korean Literary and Cultural Studies","ror":"https://ror.org/03nwyka65","country_code":"KR","type":"other","lineage":["https://openalex.org/I4210133515"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kevin Galim","raw_affiliation_strings":["FuriosaAI, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FuriosaAI, Seoul, South Korea","institution_ids":["https://openalex.org/I4210133515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122864981","display_name":"Seunghyuk Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133515","display_name":"International Association of Korean Literary and Cultural Studies","ror":"https://ror.org/03nwyka65","country_code":"KR","type":"other","lineage":["https://openalex.org/I4210133515"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghyuk Oh","raw_affiliation_strings":["FuriosaAI, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FuriosaAI, Seoul, South Korea","institution_ids":["https://openalex.org/I4210133515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122865999","display_name":"Hyung Il Koo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133515","display_name":"International Association of Korean Literary and Cultural Studies","ror":"https://ror.org/03nwyka65","country_code":"KR","type":"other","lineage":["https://openalex.org/I4210133515"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Il Koo","raw_affiliation_strings":["FuriosaAI, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6955-8083","affiliations":[{"raw_affiliation_string":"FuriosaAI, Seoul, South Korea","institution_ids":["https://openalex.org/I4210133515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101099625","display_name":"Nam Ik Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Ik Cho","raw_affiliation_strings":["Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-5297-4649","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, INMC, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04243578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"6566","last_page":"6582"},"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":0.9448999762535095,"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":0.9448999762535095,"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":0.010400000028312206,"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":0.0035000001080334187,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7462999820709229},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7049000263214111},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6477000117301941},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6396999955177307},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5677000284194946},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5396999716758728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131999969482422},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7462999820709229},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7049000263214111},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6396999955177307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5931000113487244},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5396999716758728},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46309998631477356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2919999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3651887","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3651887","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3651887","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3651887","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6131229400634766,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W4311415873","https://openalex.org/W4312933868","https://openalex.org/W4313021454","https://openalex.org/W4313120002","https://openalex.org/W4385270985","https://openalex.org/W4386075870","https://openalex.org/W4386076458","https://openalex.org/W4390874130","https://openalex.org/W4402754185","https://openalex.org/W4402951568","https://openalex.org/W4405003291","https://openalex.org/W4409264082","https://openalex.org/W4413146329"],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"(T2I)":[1],"generation":[2,52],"has":[3],"been":[4,75,90],"actively":[5],"studied":[6,77],"using":[7],"Diffusion":[8,58,72],"Models":[9,25,59,73],"and":[10,34,40,45,66,135,141],"Autoregressive":[11,24],"Models.":[12],"Recently,":[13],"Masked":[14,81],"Generative":[15,82],"Transformers":[16,83],"have":[17,74,88],"gained":[18],"attention":[19,33,39,115],"as":[20,55],"an":[21],"alternative":[22],"to":[23,26,62,117],"overcome":[27],"the":[28,119],"inherent":[29],"limitations":[30,86],"of":[31,121],"causal":[32],"autoregressive":[35],"decoding":[36],"through":[37],"bidirectional":[38],"parallel":[41],"decoding,":[42],"enabling":[43],"efficient":[44],"high-quality":[46],"image":[47],"generation.":[48],"However,":[49],"compositional":[50,111],"T2I":[51],"remains":[53],"challenging,":[54],"even":[56],"state-of-the-art":[57],"often":[60],"fail":[61],"accurately":[63],"bind":[64],"attributes":[65],"achieve":[67],"proper":[68],"text-image":[69],"alignment.":[70],"While":[71],"extensively":[76],"for":[78],"this":[79,93],"issue,":[80],"exhibit":[84],"similar":[85],"but":[87],"not":[89],"explored":[91],"in":[92,132],"context.":[94],"To":[95],"address":[96],"this,":[97],"we":[98],"proposeUnmasking":[99],"with":[100,143],"Contrastive":[101],"Attention":[102],"Guidance":[103],"(UNCAGE),":[104],"a":[105],"novel":[106],"training-free":[107],"method":[108],"that":[109,123],"improves":[110,130],"fidelity":[112],"by":[113],"leveraging":[114],"maps":[116],"prioritize":[118],"unmasking":[120],"tokens":[122],"clearly":[124],"represent":[125],"individual":[126],"objects.":[127],"UNCAGE":[128],"consistently":[129],"performance":[131],"both":[133],"quantitative":[134],"qualitative":[136],"evaluations":[137],"across":[138],"multiple":[139],"benchmarks":[140],"metrics,":[142],"negligible":[144],"inference":[145],"overhead.":[146]},"counts_by_year":[],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-01-14T00:00:00"}