{"id":"https://openalex.org/W4379086815","doi":"https://doi.org/10.48550/arxiv.2305.19327","title":"Cones 2: Customizable Image Synthesis with Multiple Subjects","display_name":"Cones 2: Customizable Image Synthesis with Multiple Subjects","publication_year":2023,"publication_date":"2023-05-30","ids":{"openalex":"https://openalex.org/W4379086815","doi":"https://doi.org/10.48550/arxiv.2305.19327"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.19327","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19327","pdf_url":"https://arxiv.org/pdf/2305.19327","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.19327","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100772092","display_name":"Zhiheng Liu","orcid":"https://orcid.org/0000-0001-6711-4801"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Zhiheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100386940","display_name":"Yifei Zhang","orcid":"https://orcid.org/0000-0002-9168-9231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yifei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103003762","display_name":"Yujun Shen","orcid":"https://orcid.org/0000-0003-3801-6705"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yujun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087247298","display_name":"Kecheng Zheng","orcid":"https://orcid.org/0000-0002-3450-400X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Kecheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013538892","display_name":"K. J. Zhu","orcid":"https://orcid.org/0000-0002-4365-8043"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Kai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101641441","display_name":"Ruili Feng","orcid":"https://orcid.org/0000-0001-9463-8045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Ruili","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102513637","display_name":"Yu Liu","orcid":"https://orcid.org/0009-0006-7055-6524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911374","display_name":"Deli Zhao","orcid":"https://orcid.org/0000-0002-8838-578X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Deli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082946615","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0002-6424-8633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100772092"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9948999881744385,"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":0.9948999881744385,"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":0.9677000045776367,"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":0.9495999813079834,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720528841018677},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.7173078656196594},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.6867074370384216},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5972186326980591},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5944781303405762},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5671283602714539},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5063091516494751},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4701055884361267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46009179949760437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42990612983703613},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3625686466693878},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3423492908477783},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12584936618804932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720528841018677},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.7173078656196594},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6867074370384216},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5972186326980591},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5944781303405762},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5671283602714539},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5063091516494751},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4701055884361267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46009179949760437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42990612983703613},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3625686466693878},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3423492908477783},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12584936618804932},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.19327","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19327","pdf_url":"https://arxiv.org/pdf/2305.19327","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.19327","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.19327","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:2305.19327","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19327","pdf_url":"https://arxiv.org/pdf/2305.19327","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2109940557","https://openalex.org/W2997152889","https://openalex.org/W2466832359"],"abstract_inverted_index":{"Synthesizing":[0],"images":[1],"with":[2,34,43],"user-specified":[3],"subjects":[4,45,156],"has":[5],"received":[6],"growing":[7],"attention":[8],"due":[9],"to":[10,53,63,106,112,123],"its":[11],"practical":[12],"applications.":[13],"Despite":[14],"the":[15,47,71,75,101,109,113,133,141,144,147,152,158,162],"recent":[16],"success":[17,31],"in":[18,143,157],"single":[19],"subject":[20,58,76,111,115,137],"customization,":[21],"existing":[22],"algorithms":[23],"suffer":[24],"from":[25],"high":[26],"training":[27],"cost":[28],"and":[29,129,150,168],"low":[30],"rate":[32],"along":[33],"increased":[35],"number":[36],"of":[37,100,154,181],"subjects.":[38,67],"Towards":[39],"controllable":[40],"image":[41],"synthesis":[42],"multiple":[44],"as":[46,59,61,80,132],"constraints,":[48],"this":[49],"work":[50],"studies":[51],"how":[52,62],"efficiently":[54],"represent":[55],"a":[56,81,96,126,179],"particular":[57],"well":[60],"appropriately":[64],"compose":[65],"different":[66,155],"We":[68,120],"find":[69],"that":[70,86],"text":[72,118],"embedding":[73],"regarding":[74],"token":[77],"already":[78],"serves":[79],"simple":[82],"yet":[83],"effective":[84],"representation":[85],"supports":[87],"arbitrary":[88],"combinations":[89],"without":[90],"any":[91],"model":[92],"tuning.":[93],"Through":[94],"learning":[95],"residual":[97],"on":[98],"top":[99],"base":[102],"embedding,":[103],"we":[104],"manage":[105],"robustly":[107],"shift":[108],"raw":[110],"customized":[114],"given":[116],"various":[117],"conditions.":[119],"then":[121],"propose":[122],"employ":[124],"layout,":[125],"very":[127],"abstract":[128],"easy-to-obtain":[130],"prior,":[131],"spatial":[134],"guidance":[135],"for":[136,183],"arrangement.":[138],"By":[139],"rectifying":[140],"activations":[142],"cross-attention":[145],"map,":[146],"layout":[148],"appoints":[149],"separates":[151],"location":[153],"image,":[159],"significantly":[160],"alleviating":[161],"interference":[163],"across":[164],"them.":[165],"Both":[166],"qualitative":[167],"quantitative":[169],"experimental":[170],"results":[171],"demonstrate":[172],"our":[173],"superiority":[174],"over":[175],"state-of-the-art":[176],"alternatives":[177],"under":[178],"variety":[180],"settings":[182],"multi-subject":[184],"customization.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}