{"id":"https://openalex.org/W7224837158","doi":"https://doi.org/10.48550/arxiv.2610.39277","title":"Efficient Covariance-Aware Vicinal Latent Diffusion for Continuous Conditional Image Generation","display_name":"Efficient Covariance-Aware Vicinal Latent Diffusion for Continuous Conditional Image Generation","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224837158","doi":"https://doi.org/10.48550/arxiv.2610.39277"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39277","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39277","pdf_url":"https://arxiv.org/pdf/2610.39277","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160187586","display_name":"Xin Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding, Xin","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160234340","display_name":"Shuo Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Shuo","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160230397","display_name":"Zhenglong Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Zhenglong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160198677","display_name":"Sen Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Sen","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160168244","display_name":"Nenglun Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Nenglun","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102424607","display_name":"Peibei Cao","orcid":"https://orcid.org/0000-0001-7463-0409","observed_orcids":["https://orcid.org/0000-0001-7463-0409"]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Peibei","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160191689","display_name":"Yongwei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yongwei","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160232800","display_name":"Fei Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Fei","raw_affiliation_strings":["School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence/School of Future Technology , Nanjing University of Information Science & Technology (NUIST) , Nanjing , China","institution_ids":["https://openalex.org/I200845125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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"}}],"keywords":[{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.9700000286102295},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.5360000133514404},{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.6510000228881836},{"id":"https://openalex.org/keywords/niqe","display_name":"NIQE","score":0.7269999980926514},{"id":"https://openalex.org/keywords/probability-flow-ode","display_name":"probability flow ODE","score":0.5400000214576721},{"id":"https://openalex.org/keywords/efficient-sampling","display_name":"efficient sampling","score":0.47999998927116394},{"id":"https://openalex.org/keywords/semantic-regularization","display_name":"semantic regularization","score":0.4090000092983246}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5685999989509583},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.5188000202178955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5113000273704529},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4034000039100647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4032999873161316},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3801000118255615},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C121349320","wikidata":"https://www.wikidata.org/wiki/Q285851","display_name":"Vicinal","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C103982235","wikidata":"https://www.wikidata.org/wiki/Q7309594","display_name":"Regular conditional probability","level":4,"score":0.2815000116825104},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39277","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39277","pdf_url":"https://arxiv.org/pdf/2610.39277","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39277","doi":"https://doi.org/10.48550/arxiv.2610.39277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39277","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39277","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39277","pdf_url":"https://arxiv.org/pdf/2610.39277","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1596368423","display_name":null,"funder_award_id":"62502442","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2239281307","display_name":null,"funder_award_id":"2024r056","funder_id":"https://openalex.org/F4320335990","funder_display_name":"Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology"},{"id":"https://openalex.org/G2487224310","display_name":null,"funder_award_id":"62306144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4205386251","display_name":null,"funder_award_id":"62303231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4927132670","display_name":null,"funder_award_id":"62306147","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/F4320335990","display_name":"Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224837158.pdf","grobid_xml":"https://content.openalex.org/works/W7224837158.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417137512","https://openalex.org/W7127431194","https://openalex.org/W4210924551","https://openalex.org/W3113433972","https://openalex.org/W3100754158","https://openalex.org/W7223300414","https://openalex.org/W7127359398","https://openalex.org/W4387995353","https://openalex.org/W4407403561","https://openalex.org/W4287597924"],"abstract_inverted_index":{"Continuous":[0],"Conditional":[1],"Generative":[2],"Modeling":[3],"(CCGM)":[4],"aims":[5],"to":[6,34,118],"synthesize":[7],"high-dimensional":[8],"data":[9,23,89],"conditioned":[10],"on":[11,122],"continuously":[12],"valued":[13],"scalar":[14],"labels.":[15],"However,":[16],"existing":[17],"continuous":[18,68,135],"diffusion":[19,65],"models":[20],"face":[21],"severe":[22],"sparsity":[24],"under":[25],"imbalanced":[26],"and":[27,37,44,86,106,125,138],"long-tailed":[28],"label":[29],"distributions,":[30],"which":[31],"can":[32],"lead":[33],"visual":[35],"artifacts":[36],"condition":[38,136],"inconsistency.":[39],"Moreover,":[40],"inference-time":[41],"classifier-free":[42],"guidance":[43,96],"dense":[45],"pixel-space":[46],"integration":[47],"introduce":[48],"substantial":[49],"sampling":[50,116,139],"overhead,":[51],"limiting":[52],"practical":[53],"deployment.":[54],"To":[55],"address":[56],"these":[57],"challenges,":[58],"we":[59],"propose":[60],"CAViLD,":[61],"an":[62,99],"efficient":[63],"latent":[64,77],"framework":[66],"for":[67,111],"conditional":[69,95,104],"generation.":[70],"CAViLD":[71],"first":[72],"constructs":[73],"a":[74,129],"purified":[75],"condition-aware":[76],"space":[78],"through":[79,98],"density-adaptive":[80],"vicinal":[81],"learning,":[82],"auxiliary":[83],"semantic":[84],"regularization,":[85],"NIQE-guided":[87],"negative":[88],"augmentation.":[90],"It":[91],"then":[92],"internalizes":[93],"the":[94],"direction":[97],"EMA":[100],"teacher,":[101],"enabling":[102],"single-branch":[103],"inference,":[105],"introduces":[107],"covariance-aware":[108],"progressive":[109],"distillation":[110],"label-dependent":[112],"probability-flow":[113],"ODEs,":[114],"supporting":[115],"down":[117],"four":[119],"NFEs.":[120],"Experiments":[121],"RC-49,":[123],"UTKFace,":[124],"Steering":[126],"Angle":[127],"demonstrate":[128],"favorable":[130],"trade-off":[131],"among":[132],"generation":[133],"fidelity,":[134],"consistency,":[137],"efficiency.":[140]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-10-31T00:00:00"}