{"id":"https://openalex.org/W4404355664","doi":"https://doi.org/10.48550/arxiv.2410.23775","title":"In-Context LoRA for Diffusion Transformers","display_name":"In-Context LoRA for Diffusion Transformers","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4404355664","doi":"https://doi.org/10.48550/arxiv.2410.23775"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.23775","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23775","pdf_url":"https://arxiv.org/pdf/2410.23775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.23775","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109146261","display_name":"Lianghua Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Lianghua","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Wei","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109695756","display_name":"Zhi-Fan Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Zhi-Fan","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shi, Yupeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi, Yupeng","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000675851","display_name":"Huanzhang Dou","orcid":"https://orcid.org/0000-0002-3277-5906","observed_orcids":["https://orcid.org/0000-0002-3277-5906"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dou, Huanzhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034901029","display_name":"Chen Liang","orcid":"https://orcid.org/0000-0003-1284-7607","observed_orcids":["https://orcid.org/0000-0003-1284-7607"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang, Chen","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101537012","display_name":"Yutong Feng","orcid":"https://orcid.org/0000-0003-0575-6790","observed_orcids":["https://orcid.org/0000-0003-0575-6790"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Yutong","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588064","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0003-1337-2527","observed_orcids":["https://orcid.org/0000-0003-1337-2527"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yu","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634","observed_orcids":["https://orcid.org/0000-0002-4220-2634"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":171,"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":0.9984999895095825,"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":0.9984999895095825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0008999999845400453,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/diffusion-transformer","display_name":"diffusion transformer","score":0.9670000076293945},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.7419999837875366},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8259999752044678},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.8889999985694885},{"id":"https://openalex.org/keywords/image-captioning","display_name":"image captioning","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48581457138061523},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4684921205043793},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4605426490306854},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.37097305059432983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3557211458683014},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.23682618141174316},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23669642210006714},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14709728956222534},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13428005576133728},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.23775","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23775","pdf_url":"https://arxiv.org/pdf/2410.23775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.23775","doi":"https://doi.org/10.48550/arxiv.2410.23775","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.23775","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.23775","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23775","pdf_url":"https://arxiv.org/pdf/2410.23775","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404355664.pdf","grobid_xml":"https://content.openalex.org/works/W4404355664.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W3030163527","https://openalex.org/W4224035735","https://openalex.org/W4287029626","https://openalex.org/W4321473567","https://openalex.org/W4322718191","https://openalex.org/W4383472654","https://openalex.org/W4384918448","https://openalex.org/W4385848774","https://openalex.org/W4387322912","https://openalex.org/W4390872583","https://openalex.org/W4391014188","https://openalex.org/W4400488544","https://openalex.org/W4401306886","https://openalex.org/W4402427382","https://openalex.org/W4402727040","https://openalex.org/W4403662644","https://openalex.org/W4403799526","https://openalex.org/W4404088271","https://openalex.org/W4413158163","https://openalex.org/W4413794661","https://openalex.org/W4415795847","https://openalex.org/W7051896053","https://openalex.org/W7131098521"],"related_works":["https://openalex.org/W6979368870","https://openalex.org/W7127370116","https://openalex.org/W4406779555","https://openalex.org/W4403843284","https://openalex.org/W7165785421","https://openalex.org/W7214351812","https://openalex.org/W7106789420","https://openalex.org/W4392222316","https://openalex.org/W4413147381","https://openalex.org/W7133208075"],"abstract_inverted_index":{"Recent":[0],"research":[1,192],"arXiv:2410.15027":[2],"has":[3],"explored":[4],"the":[5,27,30,92,142,149,184],"use":[6],"of":[7,29,95,101,107,123,168],"diffusion":[8],"transformers":[9],"(DiTs)":[10],"for":[11,183,190],"task-agnostic":[12,174,195],"image":[13,157],"generation":[14,52,76,196],"by":[15,44],"simply":[16],"concatenating":[17],"attention":[18],"tokens":[19],"across":[20],"images.":[21],"However,":[22],"despite":[23],"substantial":[24],"computational":[25],"resources,":[26],"fidelity":[28],"generated":[31],"images":[32,99],"remains":[33,173],"suboptimal.":[34],"In":[35],"this":[36,42,82],"study,":[37],"we":[38,65,84],"reevaluate":[39],"and":[40,110,177,186,203],"streamline":[41],"framework":[43,172],"hypothesizing":[45],"that":[46,68,159],"text-to-image":[47,70],"DiTs":[48,71],"inherently":[49],"possess":[50],"in-context":[51,75,93],"capabilities,":[53],"requiring":[54],"only":[55,146],"minimal":[56],"tuning":[57,115,125,169],"to":[58,90,141,148,162],"activate":[59],"them.":[60],"Through":[61],"diverse":[62],"task":[63],"experiments,":[64],"qualitatively":[66],"demonstrate":[67],"existing":[69],"can":[72],"effectively":[73],"perform":[74,104],"without":[77],"any":[78],"tuning.":[79],"Building":[80],"on":[81,193],"insight,":[83],"propose":[85],"a":[86,180],"remarkably":[87],"simple":[88],"pipeline":[89,154],"leverage":[91],"abilities":[94],"DiTs:":[96],"(1)":[97],"concatenate":[98],"instead":[100,122],"tokens,":[102],"(2)":[103],"joint":[105],"captioning":[106],"multiple":[108],"images,":[109],"(3)":[111],"apply":[112],"task-specific":[113,165],"LoRA":[114,134],"using":[116],"small":[117],"datasets":[118],"(e.g.,":[119],"20~100":[120],"samples)":[121],"full-parameter":[124],"with":[126],"large":[127],"datasets.":[128],"We":[129,198],"name":[130],"our":[131,153,171,200],"models":[132,204],"In-Context":[133],"(IC-LoRA).":[135],"This":[136],"approach":[137],"requires":[138],"no":[139],"modifications":[140],"original":[143],"DiT":[144],"models,":[145],"changes":[147],"training":[150],"data.":[151],"Remarkably,":[152],"generates":[155],"high-fidelity":[156],"sets":[158],"better":[160],"adhere":[161],"prompts.":[163],"While":[164],"in":[166,175],"terms":[167],"data,":[170,202],"architecture":[176],"pipeline,":[178],"offering":[179],"powerful":[181],"tool":[182],"community":[185],"providing":[187],"valuable":[188],"insights":[189],"further":[191],"product-level":[194],"systems.":[197],"release":[199],"code,":[201],"at":[205],"https://github.com/ali-vilab/In-Context-LoRA":[206]},"counts_by_year":[{"year":2026,"cited_by_count":79},{"year":2025,"cited_by_count":88},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-11-15T00:00:00"}
