{"id":"https://openalex.org/W7137951064","doi":"https://doi.org/10.1609/aaai.v40i16.38420","title":"Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices","display_name":"Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137951064","doi":"https://doi.org/10.1609/aaai.v40i16.38420"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38420","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38420","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i16.38420","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101383622","display_name":"Ya Zou","orcid":"https://orcid.org/0009-0003-4560-8810"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ya Zou","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650573","display_name":"Jingfeng Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfeng Yao","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129642491","display_name":"Siyuan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Yu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129682464","display_name":"Shuai Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129710196","display_name":"Wenyu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyu Liu","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129663592","display_name":"Xinggang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinggang Wang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101383622"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18454936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"16","first_page":"14086","last_page":"14094"},"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":0.6119999885559082,"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":0.6119999885559082,"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":0.07199999690055847,"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":0.03970000147819519,"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/mobile-device","display_name":"Mobile device","score":0.6995000243186951},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4514999985694885},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4433000087738037},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4392000138759613},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4187000095844269},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.412200003862381},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.40290001034736633},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.33469998836517334},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.33250001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501999974250793},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.6995000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4950999915599823},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4392000138759613},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.412200003862381},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3982999920845032},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C134535813","wikidata":"https://www.wikidata.org/wiki/Q1888734","display_name":"Transcoding","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2533999979496002},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38420","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38420","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38420","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38420","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":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.43742263317108154}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"There":[0],"is":[1,156,199],"a":[2,54,122,137,255],"growing":[3],"demand":[4],"for":[5,193],"deploying":[6],"large":[7,33],"generative":[8,18],"AI":[9],"models":[10],"on":[11,46,190,230,264],"mobile":[12,47,65,111,173,191],"devices.":[13,48,66],"For":[14],"recent":[15],"popular":[16],"video":[17,62,105,187,204],"models,":[19,211],"however,":[20],"the":[21,28,92,100,115,154,168,194,245,265],"Variational":[22],"AutoEncoder":[23],"(VAE)":[24],"represents":[25],"one":[26],"of":[27,94,166,237,244],"major":[29],"computational":[30],"bottlenecks.":[31],"Both":[32],"parameter":[34,239],"sizes":[35],"and":[36,75,113,241,260],"mismatched":[37],"kernels":[38],"cause":[39],"out-of-memory":[40],"errors":[41],"or":[42],"extremely":[43],"slow":[44],"inference":[45],"To":[49,179],"address":[50],"this,":[51],"we":[52,89,120,135,160],"propose":[53,121,145],"low-cost":[55],"solution":[56],"that":[57,99,128],"efficiently":[58],"transfers":[59],"widely":[60,200],"used":[61,157],"VAEs":[63,106,222],"to":[64,110,163,202,225,250],"(1)":[67],"We":[68,97,144],"analyze":[69],"redundancy":[70],"in":[71,103,258],"existing":[72],"VAE":[73,140,148,188],"architectures":[74],"get":[76],"empirical":[77],"design":[78],"insights.":[79],"By":[80],"integrating":[81],"3D":[82,124],"depthwise":[83],"separable":[84],"convolutions":[85],"into":[86,208],"our":[87,180,182],"model,":[88],"significantly":[90],"reduce":[91],"number":[93],"parameters.":[95],"(2)":[96],"observe":[98],"upsampling":[101],"techniques":[102],"mainstream":[104],"are":[107],"poorly":[108],"suited":[109],"hardware":[112],"form":[114],"main":[116],"bottleneck.":[117],"In":[118],"response,":[119],"decoupled":[123],"pixel":[125],"shuffle":[126],"scheme":[127],"slashes":[129],"end-to-end":[130],"delay.":[131],"Building":[132],"upon":[133],"these,":[134],"develop":[136],"universal":[138],"mobile-oriented":[139],"decoder,":[141],"Turbo-VAED.":[142],"(3)":[143],"an":[146],"efficient":[147],"decoder":[149,155],"training":[150,213],"method.":[151],"Since":[152],"only":[153],"during":[158],"deployment,":[159],"distill":[161],"it":[162,219],"Turbo-VAED":[164,253],"instead":[165],"retraining":[167],"full":[169],"VAE,":[170],"enabling":[171],"fast":[172],"adaptation":[174],"with":[175,212],"minimal":[176],"performance":[177],"loss.":[178],"knowledge,":[181],"method":[183],"enables":[184],"real-time":[185],"720p":[186,228],"decoding":[189],"devices":[192],"first":[195],"time.":[196],"This":[197],"approach":[198],"applicable":[201],"most":[203],"VAEs.":[205],"When":[206],"integrated":[207],"four":[209],"representative":[210],"cost":[214],"as":[215,217,233,235],"low":[216,234],"$95,":[218],"accelerates":[220],"original":[221,238,246],"by":[223],"up":[224],"84.5\u00d7":[226],"at":[227],"resolution":[229],"GPUs,":[231],"uses":[232],"17.5%":[236],"count,":[240],"retains":[242],"96.9%":[243],"reconstruction":[247,262],"quality.":[248],"Compared":[249],"mobile-optimized":[251],"VAEs,":[252],"achieves":[254],"2.9\u00d7":[256],"speedup":[257],"FPS":[259],"better":[261],"quality":[263],"iPhone":[266],"16":[267],"Pro.":[268]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}