{"id":"https://openalex.org/W7138163625","doi":"https://doi.org/10.1609/aaai.v40i4.37308","title":"HybriDLA: Hybrid Generation for Document Layout Analysis","display_name":"HybriDLA: Hybrid Generation for Document Layout Analysis","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138163625","doi":"https://doi.org/10.1609/aaai.v40i4.37308"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i4.37308","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37308","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37308/41270","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://ojs.aaai.org/index.php/AAAI/article/download/37308/41270","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129747406","display_name":"Yufan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yufan Chen","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053010867","display_name":"Omar Moured","orcid":"https://orcid.org/0000-0003-4227-8417"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Omar Moured","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129701015","display_name":"Ruiping Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ruiping Liu","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685426","display_name":"Junwei Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Junwei Zheng","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017521271","display_name":"Kunyu Peng","orcid":"https://orcid.org/0000-0002-5419-9292"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kunyu Peng","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691257","display_name":"Jiaming Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhang","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129736998","display_name":"Rainer Stiefelhagen","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rainer Stiefelhagen","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42592593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"3147","last_page":"3155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9413999915122986,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9413999915122986,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.013000000268220901,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00930000003427267,"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/component","display_name":"Component (thermodynamics)","score":0.6808000206947327},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5748999714851379},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5580000281333923},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5407000184059143},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5322999954223633},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5056999921798706},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46309998631477356},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.413100004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5580000281333923},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5322999954223633},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442000091075897},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.413100004196167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.362199991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i4.37308","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37308","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37308/41270","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:ojs.aaai.org:article/37308","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37308","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/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37308","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37308","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37308/41270","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6576533317565918,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1244305882","display_name":null,"funder_award_id":"INST 35/1597-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4707917552","display_name":null,"funder_award_id":"35/1597-1 FUGG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6967875139","display_name":null,"funder_award_id":"35/1597-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7057933568","display_name":null,"funder_award_id":"INST 35/1597-1 FUGG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138163625.pdf","grobid_xml":"https://content.openalex.org/works/W7138163625.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"document":[1],"layout":[2],"analysis":[3],"(DLA)":[4],"traditionally":[5],"depends":[6],"on":[7,130],"empirical":[8],"priors":[9],"or":[10],"a":[11,19,29,60,71,106,140],"fixed":[12],"set":[13],"of":[14,33],"learnable":[15],"queries":[16],"executed":[17],"in":[18,95],"single":[20,72],"forward":[21],"pass.":[22],"While":[23],"sufficient":[24],"for":[25],"early-generation":[26],"documents":[27],"with":[28,38],"small,":[30],"predetermined":[31],"number":[32],"regions,":[34],"this":[35],"paradigm":[36],"struggles":[37],"contemporary":[39],"documents,":[40,56],"which":[41],"exhibit":[42],"diverse":[43],"element":[44],"counts":[45],"and":[46,67,87,114,133],"increasingly":[47],"complex":[48],"layouts.":[49,98],"To":[50,99],"address":[51],"challenges":[52],"posed":[53],"by":[54],"modern":[55],"we":[57,104],"present":[58],"HybriDLA,":[59],"novel":[61],"generative":[62],"framework":[63],"that":[64,110,137],"unifies":[65],"diffusion":[66,75],"autoregressive":[68,83],"decoding":[69],"within":[70],"layer.":[73],"The":[74],"component":[76,84],"iteratively":[77],"refines":[78],"bounding-box":[79],"hypotheses,":[80],"whereas":[81],"the":[82,131],"injects":[85],"semantic":[86],"contextual":[88],"awareness,":[89],"enabling":[90],"precise":[91],"region":[92],"prediction":[93],"even":[94],"highly":[96],"varied":[97],"further":[100],"enhance":[101],"detection":[102],"quality,":[103],"design":[105],"multi-scale":[107],"feature-fusion":[108],"encoder":[109],"captures":[111],"both":[112],"fine-grained":[113],"high-level":[115],"visual":[116],"cues.":[117],"This":[118],"architecture":[119],"elevates":[120],"performance":[121],"to":[122],"83.5%":[123],"mean":[124],"Average":[125],"Precision":[126],"(mAP).":[127],"Extensive":[128],"experiments":[129],"DocLayNet":[132],"M6Doc":[134],"benchmarks":[135],"demonstrate":[136],"HybriDLA":[138],"sets":[139],"state-of-the-art":[141],"performance,":[142],"outperforming":[143],"previous":[144],"approaches.":[145]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}