{"id":"https://openalex.org/W4415161210","doi":"https://doi.org/10.1109/iccv51701.2025.01697","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","display_name":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415161210","doi":"https://doi.org/10.1109/iccv51701.2025.01697"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01697","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/2504.10483","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114090104","display_name":"Xingjian Leng","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Xingjian Leng","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042216551","display_name":"Jaskirat Singh","orcid":"https://orcid.org/0000-0002-2531-7878"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jaskirat Singh","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039887984","display_name":"Yunzhong Hou","orcid":"https://orcid.org/0000-0002-6916-4789"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yunzhong Hou","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028641941","display_name":"Zhenchang Xing","orcid":"https://orcid.org/0000-0001-7663-1421"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenchang Xing","raw_affiliation_strings":["Data61, CSIRO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data61, CSIRO","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102416863","display_name":"Saining Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saining Xie","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709340","display_name":"Liang Zheng","orcid":"https://orcid.org/0000-0002-1464-9500"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liang Zheng","raw_affiliation_strings":["Australian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114090104"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14190483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18262","last_page":"18272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9793000221252441,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9793000221252441,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9541000127792358,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9491000175476074,"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","display_name":"Diffusion","score":0.6191999912261963},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.600600004196167},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5376999974250793},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42590001225471497},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3917999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370999813079834},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.600600004196167},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3917999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.260699987411499}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01697","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:2504.10483","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10483","pdf_url":"https://arxiv.org/pdf/2504.10483","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.2504.10483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.10483","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:2504.10483","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10483","pdf_url":"https://arxiv.org/pdf/2504.10483","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/G1365665483","display_name":null,"funder_award_id":"IIS-2443404","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3759145028","display_name":null,"funder_award_id":"DP210102801,FT240100820","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G5704809196","display_name":null,"funder_award_id":"RS-2024-00457882","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415161210.pdf","grobid_xml":"https://content.openalex.org/works/W4415161210.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,148],"this":[1],"paper":[2],"we":[3,9,126],"tackle":[4],"a":[5,59,156],"fundamental":[6],"question:":[7],"\"Can":[8],"train":[10],"latent":[11,39,141],"diffusion":[12,40,68,87,110],"models":[13],"together":[14],"with":[15,131,165],"the":[16,78,94,100,135],"variational":[17],"auto-encoder":[18],"(VAE)":[19],"tokenizer":[20],"in":[21,61],"an":[22],"end-to-end":[23,30,46,72,129],"manner?\"":[24],"Traditional":[25],"deep-learning":[26],"wisdom":[27],"dictates":[28],"that":[29,45,66,128],"training":[31,47,73,95,102,112,122],"is":[32,43,55,70,176],"often":[33],"preferable":[34],"when":[35],"possible.":[36],"However,":[37],"for":[38],"transformers,":[41],"it":[42],"observed":[44],"both":[48,84],"VAE":[49,85,136],"and":[50,86,116,120,144,163,166],"diffusion-model":[51],"using":[52],"standard":[53],"diffusion-loss":[54],"ineffective,":[56,71],"even":[57],"causing":[58],"degradation":[60],"final":[62,151],"performance.":[63,147],"We":[64],"show":[65],"while":[67],"loss":[69,81],"can":[74],"be":[75,90],"unlocked":[76],"through":[77],"representation-alignment":[79],"(REPA)":[80],"--":[82],"allowing":[83],"model":[88,111],"to":[89,139],"jointly":[91],"tuned":[92],"during":[93],"process.":[96],"Despite":[97],"its":[98],"simplicity,":[99],"proposed":[101],"recipe":[103],"(REPA-E)":[104],"shows":[105],"remarkable":[106],"performance;":[107],"speeding":[108],"up":[109],"by":[113],"over":[114,118],"17x":[115],"45x":[117],"REPA":[119],"vanilla":[121],"recipes,":[123],"respectively.":[124],"Interestingly,":[125],"observe":[127],"tuning":[130],"REPA-E":[132],"also":[133],"improves":[134],"itself;":[137],"leading":[138],"improved":[140],"space":[142],"structure":[143],"downstream":[145],"generation":[146],"terms":[149],"of":[150,161],"performance,":[152],"our":[153],"approach":[154],"sets":[155],"new":[157],"state-of-the-art;":[158],"achieving":[159],"FID":[160],"1.12":[162],"1.69":[164],"without":[167],"classifier-free":[168],"guidance":[169],"on":[170],"ImageNet":[171],"256":[172],"x":[173],"256.":[174],"Code":[175],"available":[177],"at":[178],"https://end2end-diffusion.github.io.":[179]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-14T00:00:00"}