{"id":"https://openalex.org/W7160081868","doi":"https://doi.org/10.48550/arxiv.2605.00644","title":"Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision","display_name":"Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160081868","doi":"https://doi.org/10.48550/arxiv.2605.00644"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00644","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.00644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135147694","display_name":"Jiali Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Jiali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111675302","display_name":"Z. Lao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lao, Zhiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135279909","display_name":"Heather Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Heather","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":null,"has_fulltext":false,"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":0.9580000042915344,"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":0.9580000042915344,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.006000000052154064,"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/T11448","display_name":"Face recognition and analysis","score":0.0052999998442828655,"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/inference","display_name":"Inference","score":0.6543999910354614},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.582099974155426},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.42010000348091125},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4172999858856201},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41040000319480896},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3806000053882599},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.37950000166893005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347999811172485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6682000160217285},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6543999910354614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6168000102043152},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.582099974155426},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4172999858856201},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41040000319480896},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32350000739097595},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00644","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":"doi:10.48550/arxiv.2605.00644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00644","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6800584197044373,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Energy-based":[0],"models":[1,10,184,188],"(EBMs)":[2],"are":[3,12,85],"a":[4,66,71,127],"flexible":[5],"class":[6],"of":[7,114,231],"deep":[8],"generative":[9],"and":[11,47,70,81,121,144,194,198,212,222,229],"well-suited":[13],"to":[14,49,97,152,172,215,225],"capture":[15],"complex":[16,100],"dependencies":[17,63],"in":[18,35,59,140],"multimodal":[19,23,104,116,155,200,209,234],"data.":[20,105],"However,":[21,75],"learning":[22,112,128],"EBM":[24,164,192,201],"by":[25,64,103],"maximum":[26],"likelihood":[27],"requires":[28],"Markov":[29],"Chain":[30],"Monte":[31],"Carlo":[32],"(MCMC)":[33],"sampling":[34,193],"the":[36,77,99,111,115,142,148,167,227,232],"joint":[37,72,82,122],"data":[38,143],"space,":[39],"where":[40],"noise-initialized":[41],"Langevin":[42],"dynamics":[43],"often":[44],"mixes":[45],"poorly":[46],"fails":[48],"discover":[50],"coherent":[51,154,199],"inter-modal":[52,62],"relationships.":[53],"Multimodal":[54],"VAEs":[55],"have":[56],"made":[57],"progress":[58],"capturing":[60],"such":[61],"introducing":[65],"shared":[67,78,118],"latent":[68,79,119,145,175],"generator":[69,80,149,178],"inference":[73,83,123,168],"model.":[74,124],"both":[76,141],"model":[84,169],"parameterized":[86],"as":[87,159,186],"unimodal":[88],"Gaussian":[89],"(or":[90],"Laplace),":[91],"which":[92],"severely":[93],"limits":[94],"their":[95,133],"ability":[96],"approximate":[98],"structure":[101],"induced":[102],"In":[106],"this":[107],"work,":[108],"we":[109],"study":[110],"problem":[113],"EBM,":[117],"generator,":[120],"We":[125,218],"present":[126],"framework":[129],"that":[130,157,189],"effectively":[131],"interweaves":[132],"MLE":[134],"updates":[135],"with":[136],"corresponding":[137],"MCMC":[138],"refinements":[139],"spaces.":[146],"Specifically,":[147],"is":[150,170],"learned":[151,171],"produce":[153],"samples":[156],"serve":[158,185],"strong":[160],"initial":[161],"states":[162],"for":[163,177,208],"sampling,":[165],"while":[166],"provide":[173],"informative":[174],"initializations":[176],"posterior":[179],"sampling.":[180],"Together,":[181],"these":[182],"two":[183],"complementary":[187],"enable":[190],"effective":[191],"learning,":[195],"yielding":[196],"realistic":[197],"samples.":[202],"Extensive":[203],"experiments":[204],"demonstrate":[205],"superior":[206],"performance":[207],"synthesis":[210],"quality":[211],"coherence":[213],"compared":[214],"various":[216,220],"baselines.":[217],"conduct":[219],"analyses":[221],"ablation":[223],"studies":[224],"validate":[226],"effectiveness":[228],"scalability":[230],"proposed":[233],"framework.":[235]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-05T00:00:00"}