{"id":"https://openalex.org/W4409696757","doi":"https://doi.org/10.1109/iccv51701.2025.01736","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","display_name":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4409696757","doi":"https://doi.org/10.1109/iccv51701.2025.01736"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01736","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.02160","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091315837","display_name":"Shaojin Wu","orcid":"https://orcid.org/0000-0002-7899-0863"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shaojin Wu","raw_affiliation_strings":["ByteDance,Intelligent Creation Team,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Intelligent Creation Team,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003901639","display_name":"Mengqi Huang","orcid":"https://orcid.org/0000-0002-1057-1179"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mengqi Huang","raw_affiliation_strings":["ByteDance,Intelligent Creation Team,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Intelligent Creation Team,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015573734","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0001-6838-4993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxu Wu","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070000469","display_name":"Yufeng Cheng","orcid":"https://orcid.org/0000-0003-1466-3115"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yufeng Cheng","raw_affiliation_strings":["ByteDance,Intelligent Creation Team,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Intelligent Creation Team,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425803","display_name":"Fei Ding","orcid":"https://orcid.org/0000-0001-8619-2696"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fei Ding","raw_affiliation_strings":["ByteDance,Intelligent Creation Team,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Intelligent Creation Team,China","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067169952","display_name":"Qian He","orcid":"https://orcid.org/0000-0001-9401-8508"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qian He","raw_affiliation_strings":["ByteDance,Intelligent Creation Team,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,Intelligent Creation Team,China","institution_ids":["https://openalex.org/I4210153682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05738037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18682","last_page":"18692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.590399980545044,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.590399980545044,"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":0.5781999826431274,"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/controllability","display_name":"Controllability","score":0.9027073979377747},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.846074640750885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7090507745742798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45624154806137085},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3411659002304077},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.20365694165229797},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.08119127154350281},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.052343785762786865},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.03855225443840027}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.9027073979377747},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.846074640750885},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7090507745742798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45624154806137085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3411659002304077},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.20365694165229797},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.08119127154350281},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.052343785762786865},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.03855225443840027}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01736","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:2504.02160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02160","pdf_url":"https://arxiv.org/pdf/2504.02160","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.2504.02160","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.02160","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.02160","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.02160","pdf_url":"https://arxiv.org/pdf/2504.02160","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":[{"id":"https://openalex.org/G818119199","display_name":null,"funder_award_id":"623B2094","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W2036697162","https://openalex.org/W2140812588","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902"],"abstract_inverted_index":{"Although":[0],"subject-driven":[1],"generation":[2,9,83],"has":[3,17],"been":[4],"extensively":[5],"explored":[6],"in":[7,19,135],"image":[8],"due":[10],"to":[11,34,56,73],"its":[12],"wide":[13],"applications,":[14],"it":[15,54],"still":[16],"challenges":[18],"data":[20,70],"scalability":[21],"and":[22,37,88,104,138],"subject":[23],"expansibility.":[24],"For":[25,43],"the":[26,44,80],"first":[27],"challenge,":[28],"moving":[29],"from":[30,118],"curating":[31],"single-subject":[32,51,137],"datasets":[33],"multiple-subject":[35],"ones":[36],"scaling":[38],"them":[39],"is":[40,110],"particularly":[41],"difficult.":[42],"second,":[45],"most":[46],"recent":[47],"methods":[48],"center":[49],"on":[50],"generation,":[52],"making":[53],"hard":[55],"apply":[57],"when":[58],"dealing":[59],"with":[60],"multi-subject":[61,91,139],"scenarios.":[62],"In":[63],"this":[64,75],"study,":[65],"we":[66,95],"propose":[67],"a":[68,111,119],"highly-consistent":[69],"synthesis":[71],"pipeline":[72,78],"tackle":[74],"challenge.":[76],"This":[77],"harnesses":[79],"intrinsic":[81],"in-context":[82],"capabilities":[84],"of":[85,100],"diffusion":[86],"transformers":[87],"generates":[89],"high-consistency":[90],"paired":[92],"data.":[93],"Additionally,":[94],"introduce":[96],"UNO,":[97],"which":[98],"consists":[99],"progressive":[101],"cross-modal":[102],"alignment":[103],"universal":[105],"rotary":[106],"position":[107],"embedding.":[108],"It":[109],"multi-image":[112],"conditioned":[113],"subject-to-image":[114],"model":[115],"iteratively":[116],"trained":[117],"text-to-image":[120],"model.":[121],"Extensive":[122],"experiments":[123],"show":[124],"that":[125],"our":[126],"method":[127],"can":[128],"achieve":[129],"high":[130],"consistency":[131],"while":[132],"ensuring":[133],"controllability":[134],"both":[136],"driven":[140],"generation.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}