{"id":"https://openalex.org/W4414384363","doi":"https://doi.org/10.1109/iccv51701.2025.01615","title":"Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis","display_name":"Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414384363","doi":"https://doi.org/10.1109/iccv51701.2025.01615"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01615","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.01756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034481216","display_name":"Peng Zheng","orcid":"https://orcid.org/0000-0001-7749-3606"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zheng","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772955","display_name":"Junke Wang","orcid":"https://orcid.org/0000-0002-9570-9973"},"institutions":[{"id":"https://openalex.org/I4210139618","display_name":"Shanghai Key Laboratory of Trustworthy Computing","ror":"https://ror.org/030qbr085","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210139618"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junke Wang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI, Fudan University","institution_ids":["https://openalex.org/I4210139618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112265157","display_name":"Yi Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Chang","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108557359","display_name":"Yizhou Yu","orcid":"https://orcid.org/0000-0002-0470-5548"},"institutions":[{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Yizhou Yu","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kon","institution_ids":["https://openalex.org/I4210143490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101551878","display_name":"Rui Ma","orcid":"https://orcid.org/0000-0003-1728-0056"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Ma","raw_affiliation_strings":["School of Artificial Intelligence, Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026167547","display_name":"Zuxuan Wu","orcid":"https://orcid.org/0000-0002-8689-5807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17390","last_page":"17400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9319999814033508,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9319999814033508,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7972000241279602},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6187000274658203},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5741000175476074},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42410001158714294},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.42309999465942383},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.41179999709129333},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.40779998898506165}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7972000241279602},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5928999781608582},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5741000175476074},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48559999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4383000135421753},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.41179999709129333},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C10184394","wikidata":"https://www.wikidata.org/wiki/Q5165491","display_name":"Continuous modelling","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28540000319480896},{"id":"https://openalex.org/C74883015","wikidata":"https://www.wikidata.org/wiki/Q290467","display_name":"Autoregressive\u2013moving-average model","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01615","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:2507.01756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01756","pdf_url":"https://arxiv.org/pdf/2507.01756","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01756","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.01756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01756","pdf_url":"https://arxiv.org/pdf/2507.01756","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2241280911","display_name":null,"funder_award_id":"62202199","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,10,28,59,68],"large":[3],"language":[4],"models":[5,32],"(LLMs)":[6],"have":[7,47],"spurred":[8],"interests":[9],"encoding":[11],"images":[12],"as":[13,106],"discrete":[14,55,104,123],"tokens":[15,56,105],"and":[16,62,78],"leveraging":[17],"autoregressive":[18,155],"(AR)":[19],"frameworks":[20],"for":[21],"visual":[22,30],"generation.":[23],"However,":[24],"the":[25,80,88,115,127,136],"quantization":[26],"process":[27],"AR-based":[29],"generation":[31,111],"inherently":[33],"introduces":[34,93],"information":[35,137],"loss":[36,138],"that":[37,57,102],"degrades":[38],"image":[39],"fidelity.":[40],"To":[41],"mitigate":[42],"this":[43,91],"limitation,":[44],"recent":[45],"studies":[46],"explored":[48],"to":[49],"autoregressively":[50],"predict":[51],"continuous":[52,65,119,131],"tokens.":[53],"Unlike":[54],"reside":[58],"a":[60,99,144,158],"structured":[61],"bounded":[63],"space,":[64,72],"representations":[66,120],"exist":[67],"an":[69],"unbounded,":[70],"high-dimensional":[71],"making":[73],"density":[74],"estimation":[75],"more":[76],"challenging":[77],"increasing":[79],"risk":[81],"of":[82,118,130,147],"generating":[83],"out-of-distribution":[84],"artifacts.":[85],"Based":[86],"on":[87,122,149],"above":[89],"findings,":[90],"work":[92],"DisCon":[94,125,142],"(Discrete-Conditioned":[95],"Continuous":[96],"Autoregressive":[97],"Model),":[98],"novel":[100],"framework":[101],"reinterprets":[103],"conditional":[107,116],"signals":[108],"rather":[109],"than":[110],"targets.":[112],"By":[113],"modeling":[114,133],"probability":[117],"conditioned":[121],"tokens,":[124],"circumvents":[126],"optimization":[128],"challenges":[129],"token":[132],"while":[134],"avoiding":[135],"caused":[139],"by":[140,157],"quantization.":[141],"achieves":[143],"gFID":[145],"score":[146],"1.38":[148],"ImageNet":[150],"256$\\times$256":[151],"generation,":[152],"outperforming":[153],"state-of-the-art":[154],"approaches":[156],"clear":[159],"margin.":[160],"Project":[161],"page:":[162],"https://pengzheng0707.github.io/DisCon.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}