{"id":"https://openalex.org/W4415799019","doi":"https://doi.org/10.52202/079017-0128","title":"LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models","display_name":"LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415799019","doi":"https://doi.org/10.52202/079017-0128"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0128","doi":"https://doi.org/10.52202/079017-0128","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0128","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.14477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103057315","display_name":"Seyedmorteza Sadat","orcid":"https://orcid.org/0009-0003-4668-5703","observed_orcids":["https://orcid.org/0009-0003-4668-5703"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seyedmorteza Sadat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006852143","display_name":"Jakob Buhmann","orcid":"https://orcid.org/0009-0008-3038-4881","observed_orcids":["https://orcid.org/0009-0008-3038-4881"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakob Buhmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018563642","display_name":"Derek Bradley","orcid":"https://orcid.org/0000-0002-2055-9325","observed_orcids":["https://orcid.org/0000-0002-2055-9325"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derek Bradley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025000908","display_name":"Otmar Hilliges","orcid":"https://orcid.org/0000-0002-5068-3474","observed_orcids":["https://orcid.org/0000-0002-5068-3474"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Otmar Hilliges","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013194672","display_name":"Romann M. Weber","orcid":"https://orcid.org/0000-0003-1196-5425","observed_orcids":["https://orcid.org/0000-0003-1196-5425"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romann Weber","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":3.2234,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.94383717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3907","last_page":"3936"},"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":0.9994999766349792,"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":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00019999999494757503,"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/T11105","display_name":"Advanced Image Processing Techniques","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":0.8809999823570251},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.9359999895095825},{"id":"https://openalex.org/keywords/2d-discrete-wavelet-transform","display_name":"two-dimensional wavelet transform","score":0.9459999799728394},{"id":"https://openalex.org/keywords/lightweight-models","display_name":"lightweight models","score":0.4959999918937683},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.5540000200271606},{"id":"https://openalex.org/keywords/decoder-architecture","display_name":"decoder architecture","score":0.6449999809265137},{"id":"https://openalex.org/keywords/training-dynamics","display_name":"training dynamics","score":0.46399998664855957},{"id":"https://openalex.org/keywords/reconstruction-quality","display_name":"reconstruction quality","score":0.5899999737739563},{"id":"https://openalex.org/keywords/gpu-memory-efficiency","display_name":"GPU memory efficiency","score":0.753000020980835}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426999926567078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5350000262260437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3231000006198883},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0128","doi":"https://doi.org/10.52202/079017-0128","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0128","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.14477","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.14477","pdf_url":"https://arxiv.org/pdf/2405.14477","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.14477","doi":"https://doi.org/10.48550/arxiv.2405.14477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.14477","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.14477","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.14477","pdf_url":"https://arxiv.org/pdf/2405.14477","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415799019.pdf","grobid_xml":"https://content.openalex.org/works/W4415799019.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2073075511","https://openalex.org/W2117539524","https://openalex.org/W2132984323","https://openalex.org/W2741196023","https://openalex.org/W2776107444","https://openalex.org/W2904367110","https://openalex.org/W2962785568","https://openalex.org/W2963494934","https://openalex.org/W2964121744","https://openalex.org/W2995327724","https://openalex.org/W3111551570","https://openalex.org/W3181955432","https://openalex.org/W3212516020","https://openalex.org/W4224035735","https://openalex.org/W4226229873","https://openalex.org/W4288099666","https://openalex.org/W4302366751","https://openalex.org/W4308163867","https://openalex.org/W4312694728","https://openalex.org/W4312933868","https://openalex.org/W4318350327","https://openalex.org/W4319989813","https://openalex.org/W4320853729","https://openalex.org/W4380032909","https://openalex.org/W4383472654","https://openalex.org/W4386066464","https://openalex.org/W4387164994","https://openalex.org/W4387195417","https://openalex.org/W4389115686","https://openalex.org/W4390872297","https://openalex.org/W4390873030","https://openalex.org/W4390873084","https://openalex.org/W4392538976","https://openalex.org/W4403990754","https://openalex.org/W7214218271"],"related_works":["https://openalex.org/W4414711592","https://openalex.org/W6979371417","https://openalex.org/W4413145445","https://openalex.org/W4416548863","https://openalex.org/W4417308502","https://openalex.org/W7135082457","https://openalex.org/W7140186459","https://openalex.org/W4415161210","https://openalex.org/W7128475177","https://openalex.org/W7214936584"],"abstract_inverted_index":{"Advances":[0],"in":[1,59,96,103],"latent":[2],"diffusion":[3],"models":[4],"(LDMs)":[5],"have":[6],"revolutionized":[7],"high-resolution":[8],"image":[9],"generation,":[10],"but":[11],"the":[12,16,40,64,68,79,90,93],"design":[13,35],"space":[14],"of":[15,71,92,121],"autoencoder":[17,34],"that":[18,77],"is":[19],"central":[20],"to":[21,45,107],"these":[22],"systems":[23],"remains":[24],"underexplored.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"introduce":[30],"LiteVAE,":[31],"a":[32,100],"new":[33],"for":[36],"LDMs,":[37],"which":[38],"leverages":[39],"2D":[41],"discrete":[42],"wavelet":[43],"transform":[44],"enhance":[46],"scalability":[47],"and":[48,67,73,82,110,131],"computational":[49],"efficiency":[50],"over":[51],"standard":[52],"variational":[53],"autoencoders":[54],"(VAEs)":[55],"with":[56,99],"no":[57],"sacrifice":[58],"output":[60],"quality.":[61,84],"We":[62],"investigate":[63],"training":[65,80,109],"methodologies":[66],"decoder":[69],"architecture":[70],"LiteVAE":[72,87],"propose":[74],"several":[75],"enhancements":[76],"improve":[78],"dynamics":[81],"reconstruction":[83],"Our":[85],"base":[86],"model":[88,118],"matches":[89],"quality":[91],"established":[94],"VAEs":[95,120],"current":[97],"LDMs":[98],"six-fold":[101],"reduction":[102],"encoder":[104],"parameters,":[105],"leading":[106],"faster":[108],"lower":[111],"GPU":[112],"memory":[113],"requirements,":[114],"while":[115],"our":[116],"larger":[117],"outperforms":[119],"comparable":[122],"complexity":[123],"across":[124],"all":[125],"evaluated":[126],"metrics":[127],"(rFID,":[128],"LPIPS,":[129],"PSNR,":[130],"SSIM).":[132]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-11-03T00:00:00"}