{"id":"https://openalex.org/W7137832619","doi":"https://doi.org/10.1609/aaai.v40i36.40286","title":"DiagramGPT-Llama3:Enabling Editable, High-Fidelity Diagram Generation with Vision Large Language Models","display_name":"DiagramGPT-Llama3:Enabling Editable, High-Fidelity Diagram Generation with Vision Large Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137832619","doi":"https://doi.org/10.1609/aaai.v40i36.40286"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i36.40286","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40286","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i36.40286","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129649882","display_name":"Yongyuan Chen","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":true,"raw_author_name":"Yongyuan Chen","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114213524","display_name":"Minjie Hong","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":"Minjie Hong","raw_affiliation_strings":["School of Software Technology, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122378663","display_name":"Boxi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161972","display_name":"Technological University Dawei","ror":"https://ror.org/009t1k130","country_code":"MM","type":"education","lineage":["https://openalex.org/I4210161972"]}],"countries":["MM"],"is_corresponding":false,"raw_author_name":"Boxi Wu","raw_affiliation_strings":["School of Software Technology, Zhejiang University\nDaerwen AI"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University\nDaerwen AI","institution_ids":["https://openalex.org/I4210161972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129696221","display_name":"Xicheng Han","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":"Xicheng Han","raw_affiliation_strings":["School of Software Technology, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129649882"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05223881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"36","first_page":"30341","last_page":"30349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8016999959945679,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8016999959945679,"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/T10799","display_name":"Data Visualization and Analytics","score":0.0674000009894371,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.026100000366568565,"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/class-diagram","display_name":"Class diagram","score":0.6255999803543091},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.6247000098228455},{"id":"https://openalex.org/keywords/communication-diagram","display_name":"Communication diagram","score":0.6201000213623047},{"id":"https://openalex.org/keywords/block-diagram","display_name":"Block diagram","score":0.536300003528595},{"id":"https://openalex.org/keywords/use-case-diagram","display_name":"Use Case Diagram","score":0.5203999876976013},{"id":"https://openalex.org/keywords/diagram","display_name":"Diagram","score":0.47839999198913574},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4108000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7067999839782715},{"id":"https://openalex.org/C202446494","wikidata":"https://www.wikidata.org/wiki/Q664166","display_name":"Class diagram","level":4,"score":0.6255999803543091},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.6247000098228455},{"id":"https://openalex.org/C48419115","wikidata":"https://www.wikidata.org/wiki/Q950859","display_name":"Communication diagram","level":5,"score":0.6201000213623047},{"id":"https://openalex.org/C149227320","wikidata":"https://www.wikidata.org/wiki/Q884718","display_name":"Block diagram","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C161756209","wikidata":"https://www.wikidata.org/wiki/Q613423","display_name":"Use Case Diagram","level":5,"score":0.5203999876976013},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C91597405","wikidata":"https://www.wikidata.org/wiki/Q446366","display_name":"System context diagram","level":3,"score":0.3953000009059906},{"id":"https://openalex.org/C181844469","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster graphics","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C16671368","wikidata":"https://www.wikidata.org/wiki/Q230885","display_name":"State diagram","level":3,"score":0.36820000410079956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36419999599456787},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C153185123","wikidata":"https://www.wikidata.org/wiki/Q1391624","display_name":"Sequence diagram","level":4,"score":0.30239999294281006},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C103593891","wikidata":"https://www.wikidata.org/wiki/Q624546","display_name":"Entity\u2013relationship model","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C72041958","wikidata":"https://www.wikidata.org/wiki/Q185092","display_name":"Flowchart","level":2,"score":0.26030001044273376}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i36.40286","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40286","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.v40i36.40286","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40286","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"automation":[1],"of":[2],"diagram":[3,55,106],"generation":[4],"has":[5],"gained":[6],"significant":[7],"attention":[8],"in":[9,60,117],"recent":[10],"years.":[11],"Previous":[12],"studies":[13],"mainly":[14],"focused":[15],"on":[16],"generating":[17,37],"diagrams":[18,40,116],"from":[19,41],"natural":[20],"language,":[21],"but":[22],"often":[23],"lacked":[24],"support":[25],"for":[26],"user-friendly":[27],"editing":[28],"like":[29],"drag-and-drop.":[30],"This":[31],"paper":[32],"proposes":[33],"a":[34,109],"novel":[35],"task:":[36],"editable,":[38],"high-fidelity":[39],"either":[42],"text":[43],"or":[44],"raster":[45],"images.":[46],"It":[47],"is":[48],"also":[49],"among":[50],"the":[51,68,99],"first":[52],"to":[53,114],"introduce":[54],"restoration":[56],"and":[57,75,88,98],"style":[58,76],"transfer":[59],"this":[61],"setting.To":[62],"tackle":[63],"these":[64],"tasks,":[65],"we":[66],"constructed":[67],"Diagram-mxGraph":[69],"dataset,":[70],"covering":[71],"restoration,":[72],"text-to-diagram":[73],"generation,":[74],"transfer.":[77],"We":[78],"propose":[79],"two":[80],"core":[81],"innovations:":[82],"Fine-grained":[83],"Adaptive":[84,90],"Background":[85],"Suppression":[86],"(FABS)":[87],"Component-Aware":[89],"Loss":[91],"(CAAL).":[92],"Leveraging":[93],"pre-trained":[94],"Vision":[95],"Transformers":[96],"(ViTs)":[97],"Diagram":[100],"Adapter":[101],"module,":[102],"our":[103],"method":[104],"aligns":[105],"features":[107],"with":[108],"Large":[110],"Language":[111],"Model":[112],"(LLM)":[113],"output":[115],"editable":[118],"mxGraph":[119],"format.":[120]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}