{"id":"https://openalex.org/W7138036991","doi":"https://doi.org/10.1609/aaai.v40i7.37425","title":"Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers","display_name":"Laytrol: Preserving Pretrained Knowledge in Layout Control for Multimodal Diffusion Transformers","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138036991","doi":"https://doi.org/10.1609/aaai.v40i7.37425"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37425","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37425","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37425/41387","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://ojs.aaai.org/index.php/AAAI/article/download/37425/41387","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111347273","display_name":"Sida Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sida Huang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University\nInstitute of Artificial Intelligence (TeleAI), China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University\nInstitute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087733012","display_name":"Siqi Huang","orcid":"https://orcid.org/0000-0002-6216-8648"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Siqi Huang","raw_affiliation_strings":["School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University\nInstitute of Artificial Intelligence (TeleAI), China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University\nInstitute of Artificial Intelligence (TeleAI), China Telecom","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652790","display_name":"Ping Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129706596","display_name":"Hongyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CA","HK"],"is_corresponding":false,"raw_author_name":"Hongyuan Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI), China Telecom\nThe University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI), China Telecom\nThe University of Hong Kong","institution_ids":["https://openalex.org/I4210164862","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.24042091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"7","first_page":"5113","last_page":"5121"},"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":0.963699996471405,"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":0.963699996471405,"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":0.006200000178068876,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0031999999191612005,"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/encoder","display_name":"Encoder","score":0.6866000294685364},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5974000096321106},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5753999948501587},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5527999997138977},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4302000105381012},{"id":"https://openalex.org/keywords/page-layout","display_name":"Page layout","score":0.41519999504089355},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.39980000257492065},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.38420000672340393},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418000102043152},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6866000294685364},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5753999948501587},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44929999113082886},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.41519999504089355},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.38420000672340393},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37425","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37425","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37425/41387","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.v40i7.37425","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37425","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37425/41387","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138036991.pdf","grobid_xml":"https://content.openalex.org/works/W7138036991.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,36,45,53,58,70,85,95,101,105,111,125,129,135,156,174,180,183,200,213],"development":[2],"of":[3,76,128,177,182,215],"diffusion":[4],"models,":[5],"enhancing":[6],"spatial":[7],"controllability":[8],"in":[9,116],"text-to-image":[10],"generation":[11,26],"has":[12],"become":[13],"a":[14,18,74,147,162],"vital":[15],"challenge.":[16],"As":[17],"representative":[19],"task":[20],"for":[21,151],"addressing":[22],"this":[23,81,154],"challenge,":[24],"layout-to-image":[25,41],"aims":[27],"to":[28,99,123,166,189,199,203],"generate":[29],"images":[30,60,92],"that":[31,168],"are":[32,119,187],"spatially":[33],"consistent":[34],"with":[35,69],"given":[37],"layout":[38,46,157,184,201],"condition.":[39],"Existing":[40],"methods":[42],"typically":[43],"introduce":[44],"condition":[47],"by":[48,94],"integrating":[49],"adapter":[50],"modules":[51],"into":[52],"base":[54,71,96,130],"generative":[55],"model.":[56,131],"However,":[57],"generated":[59],"often":[61],"exhibit":[62],"low":[63],"visual":[64],"quality":[65],"and":[66,138,209],"stylistic":[67],"inconsistency":[68],"model,":[72],"indicating":[73],"loss":[75],"pretrained":[77,126],"knowledge.":[78],"To":[79,132],"alleviate":[80],"issue,":[82],"we":[83,109,145,193],"construct":[84],"Layout":[86,112],"Synthesis":[87],"(LaySyn)":[88],"dataset,":[89],"which":[90,117],"leverages":[91],"synthesized":[93],"model":[97],"itself":[98],"mitigate":[100],"distribution":[102],"shift":[103],"from":[104,121,141],"pretraining":[106],"data.":[107],"Moreover,":[108],"propose":[110],"Control":[113],"(Laytrol)":[114],"Network,":[115],"parameters":[118,137],"inherited":[120],"MM-DiT":[122],"preserve":[124],"knowledge":[127],"effectively":[133],"activate":[134],"copied":[136],"avoid":[139],"disturbance":[140],"unstable":[142],"control":[143,185],"conditions,":[144],"adopt":[146],"dedicated":[148],"initialization":[149],"scheme":[150],"Laytrol.":[152],"In":[153,191],"scheme,":[155],"encoder":[158,165],"is":[159],"initialized":[160,188],"as":[161],"pure":[163],"text":[164],"ensure":[167],"its":[169],"output":[170],"tokens":[171,202],"remain":[172],"within":[173],"data":[175],"domain":[176],"MM-DiT.":[178],"Meanwhile,":[179],"outputs":[181],"network":[186],"zero.":[190],"addition,":[192],"apply":[194],"Object-level":[195],"Rotary":[196],"Position":[197],"Embedding":[198],"provide":[204],"coarse":[205],"positional":[206],"information.":[207],"Qualitative":[208],"quantitative":[210],"experiments":[211],"demonstrate":[212],"effectiveness":[214],"our":[216],"method.":[217]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2026-03-18T00:00:00"}