{"id":"https://openalex.org/W4415398862","doi":"https://doi.org/10.1109/icdl63968.2025.11204413","title":"Analyzing Multimodal Integration in the Variational Autoencoder from an Information-Theoretic Perspective","display_name":"Analyzing Multimodal Integration in the Variational Autoencoder from an Information-Theoretic Perspective","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415398862","doi":"https://doi.org/10.1109/icdl63968.2025.11204413"},"language":null,"primary_location":{"id":"doi:10.1109/icdl63968.2025.11204413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010180461","display_name":"Carlotta Langer","orcid":"https://orcid.org/0000-0003-3536-9433"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carlotta Langer","raw_affiliation_strings":["Hamburg University of Technology (TUHH), Institute for Data Science Foundations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamburg University of Technology (TUHH), Institute for Data Science Foundations","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008546011","display_name":"Yasmin Kim Georgie","orcid":"https://orcid.org/0000-0002-5725-9596"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yasmin Kim Georgie","raw_affiliation_strings":["Humboldt-Universität zu Berlin,Department of Computer Science,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt-Universität zu Berlin,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114634923","display_name":"Ilja Porohovoj","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilja Porohovoj","raw_affiliation_strings":["Humboldt-Universität zu Berlin,Department of Computer Science,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt-Universität zu Berlin,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025141452","display_name":"Verena V. Hafner","orcid":"https://orcid.org/0000-0002-9125-8466"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Verena Vanessa Hafner","raw_affiliation_strings":["Humboldt-Universität zu Berlin,Department of Computer Science,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Humboldt-Universität zu Berlin,Department of Computer Science,Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065926474","display_name":"Nihat Ay","orcid":"https://orcid.org/0000-0002-8527-2579"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nihat Ay","raw_affiliation_strings":["Hamburg University of Technology (TUHH), Institute for Data Science Foundations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamburg University of Technology (TUHH), Institute for Data Science Foundations","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.3199000060558319,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.3199000060558319,"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/T13965","display_name":"Laser and Thermal Forming Techniques","score":0.31279999017715454,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.27300000190734863,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7491000294685364},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45100000500679016},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.44850000739097595},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.400299996137619},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.3970000147819519},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.3474000096321106},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32749998569488525},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.32589998841285706}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7491000294685364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6741999983787537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672999858856201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl63968.2025.11204413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl63968.2025.11204413","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1591713425","https://openalex.org/W1995875735","https://openalex.org/W2088335308","https://openalex.org/W2128957129","https://openalex.org/W2225156818","https://openalex.org/W2619383789","https://openalex.org/W2924334974","https://openalex.org/W2963223306","https://openalex.org/W2977483897","https://openalex.org/W2980999634","https://openalex.org/W3080780219","https://openalex.org/W3088212922","https://openalex.org/W3205239261","https://openalex.org/W3217108256","https://openalex.org/W4206297508","https://openalex.org/W4213299273","https://openalex.org/W4311415873","https://openalex.org/W4404931176"],"related_works":[],"abstract_inverted_index":{"Human":[0],"perception":[1],"is":[2,20,46,144,199],"inherently":[3],"multimodal.":[4],"We":[5],"integrate,":[6],"for":[7,23,43,109,135,233],"instance,":[8],"visual,":[9],"proprioceptive":[10],"and":[11,70,101,118,165,218,225],"tactile":[12],"information":[13],"into":[14],"one":[15,219],"experience.":[16],"Similarly,":[17],"multimodal":[18,44,48,85,234],"learning":[19],"of":[21,56,80,130,138,158,171,190],"importance":[22],"building":[24],"robotic":[25,111],"systems":[26],"that":[27,39,61,73],"aim":[28],"at":[29,92],"robustly":[30],"interacting":[31],"with":[32,213,221,228],"the":[33,47,63,98,128,131,136,139,147,163,166,172,188,206],"real":[34],"world.":[35],"One":[36],"potential":[37],"model":[38],"has":[40,183],"been":[41,184],"proposed":[42],"integration":[45,129],"variational":[49,52],"autoencoder.":[50],"A":[51],"autoencoder":[53],"(VAE)":[54],"consists":[55],"two":[57,93,159],"networks,":[58],"an":[59,78,179,202,222],"encoder":[60],"maps":[62],"data":[64,76],"to":[65,124,186,195,200,230],"a":[66,71,107,110,156,197],"stochastic":[67],"latent":[68,82,99,167,173,207],"space":[69,100],"decoder":[72],"reconstruct":[74],"this":[75,81,116],"from":[77,89],"element":[79],"space.":[83],"The":[84,142,169],"VAE":[86,143,198],"integrates":[87],"inputs":[88],"different":[90,132,160,215],"modalities":[91,133],"points":[94],"in":[95,97,122,205],"time":[96],"can":[102,152,175],"thereby":[103],"be":[104,153,176],"used":[105],"as":[106,155],"controller":[108],"agent.":[112],"Here":[113,209],"we":[114,210],"use":[115,201],"architecture":[117],"introduce":[119],"information-theoretic":[120],"measures":[121],"order":[123],"analyze":[125,226],"how":[126],"important":[127],"are":[134],"reconstruction":[137,164],"input":[140],"data.":[141],"trained":[145],"via":[146,178],"evidence":[148],"lower":[149],"bound,":[150],"which":[151,182],"written":[154],"sum":[157],"terms,":[161],"namely":[162],"loss.":[168,208],"impact":[170],"loss":[174],"weighted":[177],"additional":[180],"variable,":[181],"introduced":[185],"combat":[187],"problem":[189],"posterior":[191,204,224],"collapse.":[192],"Another":[193],"approach":[194],"improve":[196],"aggregated":[203,223],"train":[211],"networks":[212],"three":[214],"weighting":[216],"schedules":[217],"network":[220],"them":[227],"respect":[229],"their":[231],"capabilities":[232],"integration.":[235]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-22T00:00:00"}