{"id":"https://openalex.org/W7138207282","doi":"https://doi.org/10.1609/aaai.v40i9.37697","title":"EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering","display_name":"EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138207282","doi":"https://doi.org/10.1609/aaai.v40i9.37697"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i9.37697","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37697","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37697","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078756381","display_name":"Runnan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Runnan Lu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129674435","display_name":"Yuxuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxuan Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700512","display_name":"Jiaming Liu Jiaming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaming Liu","raw_affiliation_strings":["Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129742923","display_name":"Haofan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148930","display_name":"Liberating Technologies (United States)","ror":"https://ror.org/04erqh270","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haofan Wang","raw_affiliation_strings":["Liblib AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Liblib AI","institution_ids":["https://openalex.org/I4210148930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129724835","display_name":"Yiren Song","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiren Song","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7565","last_page":"7573"},"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":0.5679000020027161,"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":0.5679000020027161,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.10599999874830246,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.09220000356435776,"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/rendering","display_name":"Rendering (computer graphics)","score":0.7788000106811523},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4674000144004822},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4562999904155731},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.3447999954223633},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.33399999141693115},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.3181999921798706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983999848365784},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7788000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5478000044822693},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4674000144004822},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4562999904155731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.3447999954223633},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C32717103","wikidata":"https://www.wikidata.org/wiki/Q184759","display_name":"Character encoding","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i9.37697","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37697","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37697","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37697","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4514630436897278}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"accurate":[1],"multilingual":[2,53,89,123],"text":[3,21,40,75,83,124,130],"with":[4,52,86],"diffusion":[5],"models":[6],"has":[7],"long":[8],"been":[9],"desired":[10],"but":[11,26],"remains":[12],"challenging.":[13],"Recent":[14],"methods":[15],"have":[16],"made":[17],"progress":[18],"in":[19,22,122],"rendering":[20,27,41],"a":[23,39,80,95],"single":[24],"language,":[25],"arbitrary":[28],"languages":[29],"is":[30],"still":[31],"an":[32],"under-explored":[33],"area.":[34],"This":[35],"paper":[36],"introduces":[37],"EasyText,":[38],"framework":[42],"based":[43],"on":[44],"DiT":[45],"(Diffusion":[46],"Transformer),":[47],"which":[48,102],"connects":[49],"denoising":[50],"latents":[51],"character":[54,58,62],"tokens":[55],"encoded":[56],"as":[57,92,94],"tokens.":[59],"We":[60],"propose":[61],"positioning":[63],"encoding":[64,67],"and":[65,73,107,112,117,128],"position":[66],"interpolation":[68],"techniques":[69],"to":[70],"achieve":[71],"controllable":[72],"precise":[74],"rendering.":[76],"Additionally,":[77],"we":[78],"construct":[79],"large-scale":[81],"synthetic":[82],"image":[84],"dataset":[85,97],"1":[87],"million":[88],"image-text":[90],"annotations":[91],"well":[93],"high-quality":[96],"of":[98,119],"20K":[99],"annotated":[100],"images,":[101],"are":[103],"used":[104],"for":[105],"pretraining":[106],"fine-tuning":[108],"respectively.":[109],"Extensive":[110],"experiments":[111],"evaluations":[113],"demonstrate":[114],"the":[115],"effectiveness":[116],"advancement":[118],"our":[120],"approach":[121],"rendering,":[125],"visual":[126],"quality,":[127],"layout-aware":[129],"integration.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
