{"id":"https://openalex.org/W4416038700","doi":"https://doi.org/10.1109/iccv51701.2025.01686","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","display_name":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416038700","doi":"https://doi.org/10.1109/iccv51701.2025.01686"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101275668","display_name":"Runze He","orcid":null},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Runze He","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035038002","display_name":"Bo Cheng","orcid":"https://orcid.org/0000-0002-1992-1147"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo cheng","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052491096","display_name":"Yuhang Ma","orcid":"https://orcid.org/0000-0002-4734-1019"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhang Ma","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110148042","display_name":"Qingxiang Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingxiang Jia","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049393909","display_name":"Shanyuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanyuan Liu","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048539110","display_name":"Ao Ma","orcid":"https://orcid.org/0009-0003-6680-7675"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ao Ma","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357651","display_name":"Xiaoyu Wu","orcid":"https://orcid.org/0000-0003-3481-7820"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wu","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047587238","display_name":"Lifang Wu","orcid":"https://orcid.org/0000-0003-3334-2923"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liebucha Wu","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048962204","display_name":"Dawei Leng","orcid":"https://orcid.org/0009-0000-5461-1681"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawei Leng","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100605634","display_name":"Yuhui Yin","orcid":"https://orcid.org/0000-0002-2151-4583"},"institutions":[{"id":"https://openalex.org/I2799847335","display_name":"Art Institute of Portland","ror":"https://ror.org/01cb0jg64","country_code":"US","type":"education","lineage":["https://openalex.org/I2799847335","https://openalex.org/I2799969541"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhui Yin","raw_affiliation_strings":["360 AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"360 AI Research","institution_ids":["https://openalex.org/I2799847335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101275668"],"corresponding_institution_ids":["https://openalex.org/I2799847335"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30946131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18143","last_page":"18154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5407999753952026,"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":0.5407999753952026,"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":0.3138999938964844,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.03539999946951866,"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/page-layout","display_name":"Page layout","score":0.5468000173568726},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.49540001153945923},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4239000082015991},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4142000079154968},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4068000018596649},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4034999907016754},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38960000872612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773000001907349},{"id":"https://openalex.org/C188985296","wikidata":"https://www.wikidata.org/wiki/Q868954","display_name":"Page layout","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.49540001153945923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4068000018596649},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3781999945640564},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C179145894","wikidata":"https://www.wikidata.org/wiki/Q5264353","display_name":"Design layout record","level":5,"score":0.3463999927043915},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C5546195","wikidata":"https://www.wikidata.org/wiki/Q5969842","display_name":"IC layout editor","level":5,"score":0.34450000524520874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C23746413","wikidata":"https://www.wikidata.org/wiki/Q1141379","display_name":"Seam carving","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.25130000710487366},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10127","pdf_url":"https://arxiv.org/pdf/2503.10127","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.48550/arxiv.2503.10127","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10127","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10127","pdf_url":"https://arxiv.org/pdf/2503.10127","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"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":{"In":[0,109],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"unified":[6],"layout":[7,18,29,53,81,101,106,132],"planning":[8,30],"and":[9,31,67,130],"image":[10,105,118],"generation":[11],"model,":[12],"PlanGen,":[13],"which":[14,71],"can":[15,112],"pre-plan":[16],"spatial":[17],"conditions":[19,54],"before":[20],"generating":[21],"images.":[22],"Unlike":[23],"previous":[24,77],"diffusion-based":[25],"models":[26,39],"that":[27],"treat":[28],"layout-to-image":[32,103],"as":[33,58],"two":[34,41],"separate":[35],"models,":[36],"PlanGen":[37,51,92,111,141],"jointly":[38],"the":[40,56,76,122,137],"tasks":[42],"into":[43,55],"one":[44],"autoregressive":[45],"transformer":[46],"using":[47],"only":[48],"next-token":[49],"prediction.":[50],"integrates":[52],"model":[57],"context":[59],"without":[60],"requiring":[61],"specialized":[62],"encoding":[63],"of":[64,139],"local":[65],"captions":[66],"bounding":[68],"box":[69],"coordinates,":[70],"provides":[72],"significant":[73],"advantages":[74],"over":[75],"embed-and-pool":[78],"operations":[79],"on":[80],"conditions,":[82],"particularly":[83],"when":[84],"dealing":[85],"with":[86,125],"complex":[87],"layouts.":[88],"Unified":[89],"prompting":[90],"allows":[91],"to":[93,98,116,121],"perform":[94],"multitasking":[95],"training":[96],"related":[97],"layout,":[99],"including":[100],"planning,":[102],"generation,":[104],"understanding,":[107],"etc.":[108],"addition,":[110],"be":[113],"seamlessly":[114],"expanded":[115],"layout-guided":[117],"manipulation":[119,128],"thanks":[120],"well-designed":[123],"modeling,":[124],"teacher-forcing":[126],"content":[127],"policy":[129],"negative":[131],"guidance.":[133],"Extensive":[134],"experiments":[135],"verify":[136],"effectiveness":[138],"our":[140],"in":[142],"multiple":[143],"layoutrelated":[144],"tasks,":[145],"showing":[146],"its":[147],"great":[148],"potential.":[149],"Code":[150],"is":[151],"available":[152],"at:":[153],"https://360cvgroup.github.io/PlanGen.":[154]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}