{"id":"https://openalex.org/W4415536684","doi":"https://doi.org/10.1145/3746027.3755420","title":"Multimodal Markup Document Models for Graphic Design Completion","display_name":"Multimodal Markup Document Models for Graphic Design Completion","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536684","doi":"https://doi.org/10.1145/3746027.3755420"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052366179","display_name":"Kotaro Kikuchi","orcid":"https://orcid.org/0000-0003-1747-5945"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kotaro Kikuchi","raw_affiliation_strings":["CyberAgent, Shibuya-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071438625","display_name":"Ukyo Honda","orcid":"https://orcid.org/0000-0002-4894-9886"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ukyo Honda","raw_affiliation_strings":["CyberAgent, Shibuya-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058832609","display_name":"Naoto Inoue","orcid":"https://orcid.org/0000-0002-1969-2006"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Inoue","raw_affiliation_strings":["CyberAgent, Shibuya-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035903147","display_name":"Mayu Otani","orcid":"https://orcid.org/0000-0001-9923-2669"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mayu Otani","raw_affiliation_strings":["CyberAgent, Shibuya-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061430475","display_name":"Edgar Simo\u2010Serra","orcid":"https://orcid.org/0000-0003-2544-8592"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Edgar Simo-Serra","raw_affiliation_strings":["Waseda University, Shinjuku-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Shinjuku-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065025107","display_name":"Kota Yamaguchi","orcid":"https://orcid.org/0000-0002-3597-2913"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kota Yamaguchi","raw_affiliation_strings":["CyberAgent, Shibuya-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"CyberAgent, Shibuya-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052366179"],"corresponding_institution_ids":["https://openalex.org/I4210089607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45930247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11022","last_page":"11031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12601","display_name":"Web Applications and Data Management","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12601","display_name":"Web Applications and Data Management","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/markup-language","display_name":"Markup language","score":0.8730000257492065},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6141999959945679},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5889000296592712},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.4383000135421753},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4311000108718872},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4246000051498413}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.8730000257492065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410000205039978},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6141999959945679},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5889000296592712},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.4383000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43790000677108765},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4142000079154968},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3865000009536743},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.2791000008583069},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,100],"introduce":[1],"MarkupDM,":[2],"a":[3,62,77,92,138,173],"multimodal":[4,15,163],"markup":[5,20],"document":[6,16,64,168],"model":[7,55,81],"that":[8,28,114,162],"represents":[9],"graphic":[10],"design":[11,63,74,141,178],"as":[12,172],"an":[13,31],"interleaved":[14],"consisting":[17],"of":[18,61,130],"both":[19],"language":[21,164],"and":[22,42,109,112],"images.":[23],"Unlike":[24],"existing":[25],"holistic":[26],"approaches":[27],"rely":[29],"on":[30,103,137],"element-by-attribute":[32],"grid":[33],"representation,":[34],"our":[35,131,135,145,167],"representation":[36,169],"accommodates":[37],"variable-length":[38],"elements,":[39],"type-dependent":[40],"attributes,":[41],"text":[43,110],"content.":[44],"Inspired":[45],"by":[46,86],"fill-in-the-middle":[47],"training":[48],"in":[49,76,156],"code":[50],"generation,":[51],"we":[52,133],"train":[53],"the":[54,58,122,128],"to":[56,71,150],"complete":[57],"missing":[59],"part":[60],"from":[65],"its":[66],"surrounding":[67],"context,":[68],"allowing":[69],"it":[70,115],"treat":[72],"various":[73],"tasks":[75],"unified":[78],"manner.":[79],"Our":[80],"also":[82],"supports":[83],"image":[84,89,98,152],"generation":[85],"predicting":[87],"discrete":[88],"tokens":[90],"through":[91],"specialized":[93],"tokenizer":[94],"with":[95,121,166],"support":[96],"for":[97,176],"transparency.":[99],"evaluate":[101,134],"MarkupDM":[102,147],"three":[104],"tasks,":[105],"attribute":[106],"value,":[107],"image,":[108],"completion,":[111],"demonstrate":[113],"can":[116,170],"produce":[117],"plausible":[118],"designs":[119],"consistent":[120],"given":[123],"context.":[124],"To":[125],"further":[126],"illustrate":[127],"flexibility":[129],"approach,":[132],"approach":[136],"new":[139],"instruction-guided":[140],"completion":[142],"task":[143],"where":[144],"instruction-tuned":[146],"compares":[148],"favorably":[149],"state-of-the-art":[151],"editing":[153],"models,":[154],"especially":[155],"textual":[157],"completion.":[158],"These":[159],"findings":[160],"suggest":[161],"models":[165],"serve":[171],"versatile":[174],"foundation":[175],"broad":[177],"automation.":[179]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-25T00:00:00"}