{"id":"https://openalex.org/W4406448939","doi":"https://doi.org/10.1109/iccv51701.2025.01714","title":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","display_name":"Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406448939","doi":"https://doi.org/10.1109/iccv51701.2025.01714"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01714","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.07730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113319881","display_name":"Dongwon Kim","orcid":"https://orcid.org/0000-0002-9635-1491"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dongwon Kim","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101082644","display_name":"Ju He","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Ju He","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091431342","display_name":"Qihang Yu","orcid":"https://orcid.org/0000-0002-3994-5613"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Qihang Yu","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101879663","display_name":"Chenglin Yang","orcid":"https://orcid.org/0000-0002-0834-5164"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Chenglin Yang","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103004309","display_name":"Xiaohui Shen","orcid":"https://orcid.org/0009-0005-0667-1758"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Xiaohui Shen","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060343759","display_name":"Suha Kwak","orcid":"https://orcid.org/0000-0002-4567-9091"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I2799891827","display_name":"Korea Post","ror":"https://ror.org/00p45d091","country_code":"KR","type":"government","lineage":["https://openalex.org/I2799891827","https://openalex.org/I2801339556","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Suha Kwak","raw_affiliation_strings":["POSTECH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH","institution_ids":["https://openalex.org/I2799891827","https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070707237","display_name":"Liang-Chieh Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Liang-Chieh Chen","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.1005,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95823639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"18442","last_page":"18452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.8984000086784363,"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"}},"topics":[{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.8984000086784363,"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/generative-grammar","display_name":"Generative grammar","score":0.6753960847854614},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6531558632850647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6277555227279663},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47361159324645996},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39724037051200867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33297330141067505}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6753960847854614},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6531558632850647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6277555227279663},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47361159324645996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39724037051200867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33297330141067505}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01714","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:2501.07730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07730","pdf_url":"https://arxiv.org/pdf/2501.07730","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2501.07730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.07730","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.07730","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07730","pdf_url":"https://arxiv.org/pdf/2501.07730","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W3204019825","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071"],"abstract_inverted_index":{"Image":[0],"tokenizers":[1,144],"form":[2],"the":[3,63,86,89,140,146,157],"foundation":[4],"of":[5,114,159],"modern":[6],"text-to-image":[7,19,115,160],"generative":[8,162],"models":[9,20,130,150],"but":[10],"are":[11],"notoriously":[12],"difficult":[13],"to":[14,30,104,129,137,151],"train.":[15],"Furthermore,":[16],"most":[17],"existing":[18],"rely":[21],"on":[22,108,122,132],"large-scale,":[23],"high-quality":[24],"private":[25,133],"datasets,":[26],"making":[27],"them":[28],"challenging":[29],"replicate.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,110],"introduce":[36,111],"Text-Aware":[37],"Transformer-based":[38],"1-Dimensional":[39],"Tokenizer":[40],"(TA-TiTok),":[41],"an":[42],"efficient":[43],"and":[44,71,145,155],"powerful":[45],"image":[46],"tokenizer":[47,64],"that":[48],"can":[49],"utilize":[50],"either":[51],"discrete":[52],"or":[53],"continuous":[54],"1-dimensional":[55,96],"tokens.":[56],"TA-TiTok":[57,74,143],"uniquely":[58],"integrates":[59],"textual":[60],"information":[61],"during":[62],"decoding":[65],"stage":[66],"(i.e.,":[67],"de-tokenization),":[68],"accelerating":[69],"convergence":[70],"enhancing":[72],"performance.":[73],"also":[75],"benefits":[76],"from":[77],"a":[78,112],"simplified,":[79],"yet":[80],"effective,":[81],"one-stage":[82],"training":[83],"process,":[84],"eliminating":[85],"need":[87],"for":[88,101],"complex":[90],"two-stage":[91],"distillation":[92],"used":[93],"in":[94],"previous":[95],"tokenizers.":[97],"This":[98],"design":[99],"allows":[100],"seamless":[102],"scalability":[103],"large":[105],"datasets.":[106],"Building":[107],"this,":[109],"family":[113],"Masked":[116],"Generative":[117],"Models":[118],"(MaskGen),":[119],"trained":[120,131],"exclusively":[121],"open":[123],"data":[124],"while":[125],"achieving":[126],"comparable":[127],"performance":[128],"data.":[134],"We":[135],"aim":[136],"release":[138],"both":[139],"efficient,":[141],"strong":[142],"open-data,":[147],"open-weight":[148],"MaskGen":[149],"promote":[152],"broader":[153],"access":[154],"democratize":[156],"field":[158],"masked":[161],"models.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}