{"id":"https://openalex.org/W7137849887","doi":"https://doi.org/10.1609/aaai.v40i10.37736","title":"TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering","display_name":"TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137849887","doi":"https://doi.org/10.1609/aaai.v40i10.37736"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37736","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37736","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37736/41698","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37736/41698","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081885517","display_name":"Dongxing Mao","orcid":"https://orcid.org/0000-0003-2829-7830"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongxing Mao","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710857","display_name":"Yilin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129726867","display_name":"Linjie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672414","display_name":"Zhengyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129693155","display_name":"Alex Jinpeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Alex Jinpeng Wang","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":2,"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":"40","issue":"10","first_page":"7918","last_page":"7926"},"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":0.5300999879837036,"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":0.5300999879837036,"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":0.15889999270439148,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.08129999786615372,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/inference","display_name":"Inference","score":0.5917999744415283},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4997999966144562},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4350999891757965},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.41659998893737793},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.40310001373291016},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3952000141143799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223000168800354},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4401000142097473},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38679999113082886},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2883000075817108},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25459998846054077}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v40i10.37736","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37736","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37736/41698","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"},{"id":"pmh:oai:arXiv.org:2604.24459","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.24459","pdf_url":"https://arxiv.org/pdf/2604.24459","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/37736","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37736","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37736","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37736/41698","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137849887.pdf","grobid_xml":"https://content.openalex.org/works/W7137849887.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,19,44,81,140,159,173],"text-to-image":[4],"(T2I)":[5],"generation,":[6],"models":[7,109,139,166],"still":[8],"struggle":[9],"to":[10,133,151],"accurately":[11],"render":[12],"prompt-specified":[13],"text":[14,40,79,95,160,174],"with":[15,37,77,129],"correct":[16],"spatial":[17,157,176],"layout\u2014especially":[18],"multi-span,":[20],"structured":[21],"settings.":[22],"This":[23,88],"challenge":[24],"is":[25],"driven":[26],"not":[27],"only":[28],"by":[29,49],"the":[30,38,45,50,82,153,182],"lack":[31,155],"of":[32,52,69,156,184],"datasets":[33],"that":[34,110,165],"align":[35],"prompts":[36],"exact":[39],"and":[41,84,137,178],"layout":[42,57,131,186],"expected":[43],"image,":[46],"but":[47],"also":[48],"absence":[51],"effective":[53],"metrics":[54,150],"for":[55,92,106,188],"evaluating":[56],"quality.":[58],"To":[59],"address":[60,152],"these":[61],"issues,":[62],"we":[63,100,146],"introduce":[64,147],"TextGround4M,":[65],"a":[66,102,127,141],"large-scale":[67],"dataset":[68],"over":[70],"4":[71],"million":[72],"prompt-image":[73],"pairs,":[74],"each":[75],"annotated":[76],"span-level":[78],"grounded":[80,189],"prompt":[83,179],"corresponding":[85],"bounding":[86],"boxes.":[87],"enables":[89],"fine-grained":[90,185],"supervision":[91,187],"layout-aware,":[93],"prompt-grounded":[94],"rendering.":[96,161],"Building":[97],"on":[98,168],"this,":[99],"propose":[101],"lightweight":[103],"training":[104],"strategy":[105],"autoregressive":[107],"T2I":[108,190],"appends":[111],"layout-aware":[112,149],"span":[113],"tokens":[114],"during":[115],"training,":[116],"without":[117],"altering":[118],"model":[119],"architecture":[120],"or":[121],"inference":[122],"behavior.":[123],"We":[124],"further":[125],"construct":[126],"benchmark":[128],"stratified":[130],"complexity":[132],"evaluate":[134],"both":[135],"open-source":[136],"proprietary":[138],"zero-shot":[142],"setting.":[143],"In":[144],"addition,":[145],"two":[148],"long-standing":[154],"evaluation":[158],"Our":[162],"results":[163],"show":[164],"trained":[167],"TextGround4M":[169],"outperform":[170],"strong":[171],"baselines":[172],"fidelity,":[175],"accuracy,":[177],"consistency,":[180],"highlighting":[181],"importance":[183],"generation.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}