{"id":"https://openalex.org/W4415796735","doi":"https://doi.org/10.52202/079017-2668","title":"Phased Consistency Models","display_name":"Phased Consistency Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415796735","doi":"https://doi.org/10.52202/079017-2668"},"language":"en","primary_location":{"id":"doi:10.52202/079017-2668","doi":"https://doi.org/10.52202/079017-2668","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-2668","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.18407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fu-Yun Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu-Yun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024134159","display_name":"Zhaoyang Huang","orcid":"https://orcid.org/0000-0002-0123-7486","observed_orcids":["https://orcid.org/0000-0002-0123-7486"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoyang Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091610843","display_name":"Alexander W. Bergman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Bergman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101253764","display_name":"Dazhong Shen","orcid":"https://orcid.org/0000-0002-3947-4153","observed_orcids":["https://orcid.org/0000-0002-3947-4153"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dazhong Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001634428","display_name":"Michael Lingelbach","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Lingelbach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112010204","display_name":"Keqiang Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keqiang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023250570","display_name":"Weikang Bian","orcid":"https://orcid.org/0000-0001-9986-3348","observed_orcids":["https://orcid.org/0000-0001-9986-3348"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weikang Bian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033877290","display_name":"Guanglu Song","orcid":"https://orcid.org/0000-0001-5391-5712","observed_orcids":["https://orcid.org/0000-0001-5391-5712"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglu Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057316846","display_name":"Fuyun Wang","orcid":"https://orcid.org/0009-0003-7843-5215","observed_orcids":["https://orcid.org/0009-0003-7843-5215"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaogang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100732450","display_name":"Hongsheng Li","orcid":"https://orcid.org/0000-0002-2664-7975","observed_orcids":["https://orcid.org/0000-0002-2664-7975"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongsheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.394,"has_fulltext":true,"cited_by_count":65,"citation_normalized_percentile":{"value":0.98532782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"83951","last_page":"84009"},"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":1.0,"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":1.0,"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":0.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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/consistency-models","display_name":"consistency models","score":0.7039999961853027},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/text-to-video-generation","display_name":"text-to-video generation","score":0.8479999899864197},{"id":"https://openalex.org/keywords/high-resolution-image-synthesis","display_name":"high-resolution image generation","score":0.8119999766349792},{"id":"https://openalex.org/keywords/latent-space","display_name":"latent space","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.8589000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6279000043869019},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.5023999810218811},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45660001039505005},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C31388003","wikidata":"https://www.wikidata.org/wiki/Q7624548","display_name":"Strong consistency","level":3,"score":0.3853999972343445},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-2668","doi":"https://doi.org/10.52202/079017-2668","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-2668","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.18407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.18407","pdf_url":"https://arxiv.org/pdf/2405.18407","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.2405.18407","doi":"https://doi.org/10.48550/arxiv.2405.18407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.18407","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:2405.18407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.18407","pdf_url":"https://arxiv.org/pdf/2405.18407","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":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415796735.pdf","grobid_xml":"https://content.openalex.org/works/W4415796735.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W3092442149","https://openalex.org/W3110257065","https://openalex.org/W4221159371","https://openalex.org/W4288099666","https://openalex.org/W4297676498","https://openalex.org/W4298185919","https://openalex.org/W4303647933","https://openalex.org/W4319653963","https://openalex.org/W4320351336","https://openalex.org/W4323076585","https://openalex.org/W4323706282","https://openalex.org/W4378771707","https://openalex.org/W4380994608","https://openalex.org/W4383472654","https://openalex.org/W4387389604","https://openalex.org/W4387928896","https://openalex.org/W4392090197","https://openalex.org/W4392538976","https://openalex.org/W4392737350","https://openalex.org/W4394656839","https://openalex.org/W4394867031","https://openalex.org/W4396822569","https://openalex.org/W4399401533","https://openalex.org/W4399912930","https://openalex.org/W4403322434","https://openalex.org/W4403363894","https://openalex.org/W4403573316","https://openalex.org/W4403757510","https://openalex.org/W4403923215","https://openalex.org/W4403964572","https://openalex.org/W4404088177","https://openalex.org/W4404307599","https://openalex.org/W4404520210","https://openalex.org/W4404971693","https://openalex.org/W4409366442","https://openalex.org/W4413145195","https://openalex.org/W4415795614","https://openalex.org/W4415795783","https://openalex.org/W4415796806","https://openalex.org/W4415800534"],"related_works":["https://openalex.org/W4394656839","https://openalex.org/W7166827917","https://openalex.org/W4407384793","https://openalex.org/W4323076585","https://openalex.org/W4407170453","https://openalex.org/W4392737350","https://openalex.org/W4389821189","https://openalex.org/W7213733512","https://openalex.org/W4389714018","https://openalex.org/W4413811430"],"abstract_inverted_index":{"Consistency":[0,42,55],"Models":[1,43,56],"(CMs)":[2],"have":[3],"made":[4],"significant":[5],"progress":[6],"in":[7,22,36],"accelerating":[8],"the":[9,23,37,47,60,65,104,119],"generation":[10,21,78,92],"of":[11,40,106],"diffusion":[12],"models.":[13],"However,":[14],"their":[15],"application":[16],"to":[17,94,112,117],"high-resolution,":[18],"text-conditioned":[19],"image":[20],"latent":[24],"space":[25,62],"remains":[26],"unsatisfactory.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,102],"identify":[32],"three":[33],"key":[34],"flaws":[35],"current":[38],"design":[39,61],"Latent":[41],"(LCMs).":[44],"We":[45],"investigate":[46],"reasons":[48],"behind":[49],"these":[50],"limitations":[51],"and":[52,63,110],"propose":[53],"Phased":[54],"(PCMs),":[57],"which":[58],"generalize":[59],"address":[64],"identified":[66],"limitations.":[67],"Our":[68,124],"evaluations":[69],"demonstrate":[70],"that":[71],"PCMs":[72,81,107],"outperform":[73],"LCMs":[74],"across":[75],"1--16":[76],"step":[77],"settings.":[79],"While":[80],"are":[82],"specifically":[83,97],"designed":[84,98],"for":[85],"multi-step":[86],"refinement,":[87],"they":[88],"achieve":[89],"comparable":[90],"1-step":[91,99],"results":[93],"previously":[95],"state-of-the-art":[96,120],"methods.":[100],"Furthermore,":[101],"show":[103],"methodology":[105],"is":[108,126],"versatile":[109],"applicable":[111],"video":[113],"generation,":[114],"enabling":[115],"us":[116],"train":[118],"few-step":[121],"text-to-video":[122],"generator.":[123],"code":[125],"available":[127],"at":[128],"https://github.com/G-U-N/Phased-Consistency-Model.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":32},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":10}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-03T00:00:00"}