{"id":"https://openalex.org/W7138285241","doi":"https://doi.org/10.1609/aaai.v40i31.39795","title":"Efficient Modality Translation via Arbitrary Conditioning and Wasserstein Regularization","display_name":"Efficient Modality Translation via Arbitrary Conditioning and Wasserstein Regularization","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138285241","doi":"https://doi.org/10.1609/aaai.v40i31.39795"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i31.39795","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39795","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i31.39795","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068185631","display_name":"Tom\u00e1\u0161 Tok\u00e1r","orcid":"https://orcid.org/0000-0002-4873-0032"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tomas Tokar","raw_affiliation_strings":["Department of Mechanical and Industrial Engineering, University of Toronto\nWondeur AI, Toronto, ON"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Industrial Engineering, University of Toronto\nWondeur AI, Toronto, ON","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129640861","display_name":"Scott Sanner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Scott Sanner","raw_affiliation_strings":["Department of Mechanical and Industrial Engineering, University of Toronto\nVector Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Industrial Engineering, University of Toronto\nVector Institute for AI","institution_ids":["https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"40","issue":"31","first_page":"25949","last_page":"25957"},"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":0.8734999895095825,"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":0.8734999895095825,"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":0.01679999940097332,"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/T10028","display_name":"Topic Modeling","score":0.01269999984651804,"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/inference","display_name":"Inference","score":0.6417999863624573},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6261000037193298},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6248999834060669},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5706999897956848},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4629000127315521},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41839998960494995},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4077000021934509},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3873000144958496}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6417999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291999816894531},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.539900004863739},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41839998960494995},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.320499986410141},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2994999885559082},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2732999920845032},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i31.39795","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39795","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/39795","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i31.39795","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39795","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"central":[1],"challenge":[2,57],"in":[3,8,116,152],"multimodal":[4,22,118,178,222],"generative":[5],"modeling":[6],"lies":[7],"accurately":[9],"approximating":[10],"the":[11,53,117,124,167,187,199,210],"joint":[12],"data":[13,141],"distribution,":[14],"even":[15],"when":[16],"some":[17],"modalities":[18,50,77,84,100],"are":[19,85],"missing.":[20,88],"Existing":[21],"VAEs":[23],"solve":[24],"this":[25,58],"by":[26,51,60],"designing":[27],"increasingly":[28],"complex":[29],"encoding":[30,54],"architectures,":[31],"relying":[32],"on":[33,157],"modality-specific":[34],"encoders,":[35],"factorized":[36],"posteriors,":[37],"and":[38,78,142,216],"custom":[39],"inference":[40,207],"procedures.":[41],"This":[42,89,145],"restricts":[43],"their":[44],"ability":[45],"to":[46,95,113,136,162],"capture":[47],"relations":[48],"among":[49],"amortizing":[52],"parameters.":[55],"We":[56,110,180],"paradigm":[59],"introducing":[61],"a":[62,73,79,91,106,149],"model":[63,212],"trained":[64],"for":[65],"arbitrary":[66,120],"conditioning,":[67],"i.e.,":[68],"generating":[69],"any":[70,97],"modality":[71,143],"given":[72],"subset":[74,98],"of":[75,99,177],"observed":[76],"logical":[80],"index":[81],"indicating":[82],"which":[83,130,155],"present":[86],"or":[87,205],"enables":[90],"single":[92],"unified":[93],"encoder":[94],"handle":[96],"while":[101],"capturing":[102],"inter-modal":[103],"relationships":[104],"via":[105],"compact,":[107],"shared":[108],"posterior.":[109],"find":[111],"that":[112,160,182,186],"work":[114],"efficiently":[115],"setup,":[119],"conditioning":[121,194],"requires":[122],"replacing":[123],"KL":[125,158],"divergence":[126],"with":[127,198],"Wasserstein":[128,183],"regularization,":[129],"allows":[131],"more":[132],"dispersed":[133],"latent":[134,189],"embeddings":[135,165],"support":[137],"learning":[138],"over":[139],"diverse":[140,175],"subsets.":[144],"key":[146],"insight":[147],"exposes":[148],"critical":[150],"deficiency":[151],"existing":[153],"methods,":[154],"rely":[156],"regularization":[159,184],"tends":[161],"concentrate":[163],"individual":[164],"near":[166],"standard":[168],"Gaussian":[169],"prior,":[170],"despite":[171],"coming":[172],"from":[173],"very":[174],"subsets":[176,195],"inputs.":[179],"prove":[181],"ensures":[185],"aggregate":[188],"distribution":[190],"--":[191,196],"spanning":[192],"all":[193],"aligns":[197],"prior":[200],"without":[201],"requiring":[202],"mixture":[203],"models":[204],"auxiliary":[206],"tricks.":[208],"Empirically,":[209],"proposed":[211],"improves":[213],"cross-modal":[214],"generation":[215],"yields":[217],"better":[218],"reconstructions":[219],"than":[220],"state-of-the-art":[221],"VAEs.":[223]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}