{"id":"https://openalex.org/W4416252344","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228445","title":"Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion","display_name":"Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252344","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228445"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5088584955","display_name":"Nguy\u1ec5n Ho\u00e0ng B\u1eafc","orcid":"https://orcid.org/0000-0002-2973-7909"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bac Nguyen","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044626752","display_name":"Chieh-Hsin Lai","orcid":"https://orcid.org/0009-0009-3059-929X"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chieh-Hsin Lai","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120354565","display_name":"Yuta Takida","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuta Takida","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031225419","display_name":"Naoki Murata","orcid":"https://orcid.org/0000-0001-7418-5173"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naoki Murata","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034556374","display_name":"Toshimitsu Uesaka","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toshimitsu Uesaka","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113804858","display_name":"Stefano Ermon","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefano Ermon","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5088584955"],"corresponding_institution_ids":["https://openalex.org/I2800278093"],"apc_list":null,"apc_paid":null,"fwci":1.428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87269058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.8587999939918518,"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":0.8587999939918518,"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":0.03929999843239784,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.01940000057220459,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7748000025749207},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.459199994802475},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.41370001435279846},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41130000352859497},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3840000033378601},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3463999927043915},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.33500000834465027},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.3206999897956848},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.30709999799728394}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7748000025749207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5343000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46470001339912415},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4268999993801117},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4194999933242798},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41130000352859497},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3840000033378601},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C205372313","wikidata":"https://www.wikidata.org/wiki/Q355645","display_name":"Latent image","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W100623710","https://openalex.org/W2108598243","https://openalex.org/W2962770929","https://openalex.org/W3180355996","https://openalex.org/W4229944339","https://openalex.org/W4312388283","https://openalex.org/W4312933868","https://openalex.org/W4313021454","https://openalex.org/W4313120002","https://openalex.org/W4313156423","https://openalex.org/W4401044003"],"related_works":[],"abstract_inverted_index":{"By":[0],"embedding":[1,51,70,89],"discrete":[2,21],"representations":[3],"into":[4],"a":[5,82,96,108,113],"continuous":[6],"latent":[7,13,29,57,84,144],"space,":[8],"we":[9,79],"can":[10],"leverage":[11],"continuous-space":[12,83],"diffusion":[14,30,45,58,85,145],"models":[15],"to":[16,142],"handle":[17],"generative":[18],"modeling":[19],"of":[20,40,153],"data.":[22],"However,":[23],"despite":[24],"their":[25],"initial":[26],"success,":[27],"most":[28],"methods":[31],"rely":[32],"on":[33,123,134,159],"fixed":[34],"pretrained":[35],"embeddings,":[36],"limiting":[37],"the":[38,44,50,56,88,101,128],"benefits":[39],"joint":[41,102],"training":[42,68,98],"with":[43,107,161],"model.":[46],"While":[47],"jointly":[48],"learning":[49],"(via":[52,60],"reconstruction":[53],"loss)":[54,63],"and":[55,118,138],"model":[59],"score":[61],"matching":[62],"could":[64],"enhance":[65],"performance,":[66],"end-to-end":[67],"risks":[69],"collapse,":[71],"degrading":[72],"generation":[73,158],"quality.":[74],"To":[75],"mitigate":[76],"this":[77],"issue,":[78],"introduce":[80],"VQ-LCMD,":[81],"framework":[86],"within":[87],"space":[90],"that":[91,127],"stabilizes":[92],"training.":[93],"VQ-LCMD":[94,130,149],"uses":[95],"novel":[97],"objective":[99],"combining":[100],"embedding-diffusion":[103],"variational":[104],"lower":[105],"bound":[106],"consistency-matching":[109],"(CM)":[110],"loss,":[111],"alongside":[112],"shifted":[114],"cosine":[115],"noise":[116],"schedule":[117],"random":[119],"dropping":[120],"strategy.":[121],"Experiments":[122],"several":[124],"benchmarks":[125],"show":[126],"proposed":[129],"yields":[131],"superior":[132],"results":[133],"FFHQ,":[135],"LSUN":[136,139],"Churches,":[137],"Bedrooms":[140],"compared":[141],"discrete-state":[143],"models.":[146],"In":[147],"particular,":[148],"achieves":[150],"an":[151],"FID":[152],"6.81":[154],"for":[155],"class-conditional":[156],"image":[157],"ImageNet":[160],"50":[162],"steps.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}