{"id":"https://openalex.org/W4413145497","doi":"https://doi.org/10.1109/cvpr52734.2025.01210","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","display_name":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145497","doi":"https://doi.org/10.1109/cvpr52734.2025.01210"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113173055","display_name":"Chengyue Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chengyue Wu","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412833","display_name":"Xiaokang Chen","orcid":"https://orcid.org/0000-0002-6188-5821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaokang Chen","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108135671","display_name":"Zhiyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyu Wu","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046684555","display_name":"Yiyang Ma","orcid":"https://orcid.org/0000-0002-6218-8593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiyang Ma","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024864770","display_name":"Xingchao Liu","orcid":"https://orcid.org/0009-0005-5592-5128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingchao Liu","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104206167","display_name":"Zizheng Pan","orcid":"https://orcid.org/0000-0002-1717-7844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zizheng Pan","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628490","display_name":"Liu Wen","orcid":"https://orcid.org/0000-0001-7303-3792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Liu","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112985153","display_name":"Zhenda Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenda Xie","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608388","display_name":"Xingkai Yu","orcid":"https://orcid.org/0000-0002-7422-7406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingkai Yu","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019374810","display_name":"Chong Ruan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Ruan","raw_affiliation_strings":["DeepSeek-Ai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepSeek-Ai","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101643492","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-8167-1900"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5113173055"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.7919,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.99526312,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12966","last_page":"12977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9521999955177307,"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":0.9521999955177307,"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/janus","display_name":"Janus","score":0.713873028755188},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.7086045742034912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6768320798873901},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6691591739654541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.381816565990448},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35891616344451904},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1116599440574646},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10273656249046326},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.059774309396743774}],"concepts":[{"id":"https://openalex.org/C2779290492","wikidata":"https://www.wikidata.org/wiki/Q6155940","display_name":"Janus","level":2,"score":0.713873028755188},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.7086045742034912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6768320798873901},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6691591739654541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.381816565990448},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35891616344451904},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1116599440574646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10273656249046326},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.059774309396743774}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"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/W3127131576","https://openalex.org/W4401226765","https://openalex.org/W993170344","https://openalex.org/W3045240077","https://openalex.org/W3206580251","https://openalex.org/W2944172132","https://openalex.org/W3101598353","https://openalex.org/W4297129665","https://openalex.org/W4220908867","https://openalex.org/W2546361732"],"abstract_inverted_index":{"We":[0],"introduce":[1],"Janus,":[2],"an":[3],"autoregressive":[4],"framework":[5],"that":[6,115],"unifies":[7],"multimodal":[8,38,51,146],"understanding":[9,39,87,101],"and":[10,40,88,102,121,134],"generation.":[11],"Prior":[12],"research":[13],"often":[14],"relies":[15],"on":[16],"a":[17,67,140],"single":[18],"visual":[19,59,83],"encoder":[20],"for":[21,72,143],"both":[22,98],"tasks,":[23],"such":[24],"as":[25],"Chameleon.":[26],"However,":[27],"due":[28],"to":[29,46],"the":[30,79,82,93,99,125],"differing":[31],"levels":[32],"of":[33,127,136],"information":[34],"granularity":[35],"required":[36],"by":[37],"generation,":[41,89],"this":[42,55],"approach":[43],"can":[44,105],"lead":[45],"suboptimal":[47],"performance,":[48],"particularly":[49],"in":[50,86],"understanding.":[52],"To":[53],"address":[54],"issue,":[56],"we":[57],"decouple":[58],"encoding":[60,111],"into":[61],"separate":[62],"pathways,":[63],"while":[64],"still":[65],"leveraging":[66],"single,":[68],"unified":[69,119,145],"transformer":[70],"architecture":[71],"processing.":[73],"The":[74,130,148],"decoupling":[75],"not":[76],"only":[77],"alleviates":[78],"conflict":[80],"between":[81],"encoder\u2019s":[84],"roles":[85],"but":[90],"also":[91],"enhances":[92],"framework\u2019s":[94],"flexibility.":[95],"For":[96],"instance,":[97],"multi-modal":[100],"generation":[103],"components":[104],"independently":[106],"select":[107],"their":[108],"most":[109],"suitable":[110],"methods.":[112],"Experiments":[113],"show":[114],"Janus":[116,137],"surpasses":[117],"previous":[118],"model":[120],"matches":[122],"or":[123],"exceeds":[124],"performance":[126],"task-specific":[128],"models.":[129,147],"simplicity,":[131],"high":[132],"flexibility,":[133],"effectiveness":[135],"make":[138],"it":[139],"strong":[141],"candidate":[142],"next-generation":[144],"code":[149],"will":[150],"be":[151],"made":[152],"available.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":12}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
