{"id":"https://openalex.org/W4413147863","doi":"https://doi.org/10.1109/cvpr52734.2025.01816","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","display_name":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413147863","doi":"https://doi.org/10.1109/cvpr52734.2025.01816"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5083481253","display_name":"Kevin Qinghong Lin","orcid":"https://orcid.org/0000-0003-2568-2346"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kevin Qinghong Lin","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110673725","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0002-9817-1793"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001133932","display_name":"Difei Gao","orcid":"https://orcid.org/0000-0001-8494-3492"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Difei Gao","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050209478","display_name":"Zhengyuan Yang","orcid":"https://orcid.org/0000-0002-5808-0889"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934104","display_name":"Shiwei Wu","orcid":"https://orcid.org/0000-0002-3206-6827"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shiwei Wu","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037364812","display_name":"Zechen Bai","orcid":"https://orcid.org/0000-0001-5953-0442"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zechen Bai","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070601116","display_name":"Stan Weixian Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Stan Weixian Lei","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore,Show Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Show Lab","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19498","last_page":"19508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9814000129699707,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9814000129699707,"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/T13382","display_name":"Robotics and Automated Systems","score":0.911300003528595,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/computer-science","display_name":"Computer science","score":0.7910489439964294},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6119292378425598},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.450914204120636},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4504580497741699},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4088943600654602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910489439964294},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6119292378425598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450914204120636},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4504580497741699},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4088943600654602},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Building":[0],"Graphical":[1],"User":[2],"Interface":[3],"(GUI)":[4],"assistants":[5],"holds":[6],"significant":[7,147],"promise":[8],"for":[9,44,93],"enhancing":[10],"human":[11],"workflow":[12],"productivity.":[13],"While":[14],"most":[15],"agents":[16],"are":[17,218],"language-based,":[18],"relying":[19],"on":[20],"closed-source":[21],"API":[22],"with":[23],"text-rich":[24],"meta-information":[25],"(e.g.,":[26],"HTML":[27],"or":[28,119],"accessibility":[29],"tree),":[30],"they":[31],"show":[32],"limitations":[33],"in":[34,56,117,167,211],"perceiving":[35],"UI":[36,80],"visuals":[37],"as":[38,78,90],"humans":[39],"do,":[40],"highlighting":[41],"the":[42,63,91,187,204],"need":[43],"GUI":[45,109,133,213],"visual":[46,180,214],"agents.":[47,215],"In":[48],"this":[49],"work,":[50],"we":[51],"develop":[52],"a":[53,142,155,163],"vision-language-action":[54],"model":[55,158,210],"digital":[57],"world,":[58],"namely":[59],"ShowUI,":[60,154],"which":[61],"features":[62],"following":[64],"innovations:":[65],"(i)":[66],"UI-Guided":[67],"Visual":[68],"Token":[69],"Selection":[70],"to":[71,126,145],"reduce":[72],"computational":[73],"costs":[74],"by":[75,136,189],"formulating":[76],"screenshots":[77],"an":[79],"connected":[81],"graph,":[82],"adaptively":[83],"identifying":[84],"their":[85],"redundant":[86,179],"relationship":[87],"and":[88,140,184,198,206],"serve":[89],"criteria":[92],"token":[94,173],"selection":[95,174],"during":[96,182],"self-attention":[97],"blocks;":[98],"(ii)":[99],"Interleaved":[100],"Vision-Language-Action":[101],"Streaming":[102],"that":[103],"flexibly":[104],"unifies":[105],"diverse":[106],"needs":[107],"within":[108],"tasks,":[110],"enabling":[111],"effective":[112],"management":[113],"of":[114,178,208],"visual-action":[115],"history":[116],"navigation":[118],"pairing":[120],"multi-turn":[121],"query-action":[122],"sequences":[123],"per":[124],"screenshot":[125,169],"enhance":[127],"training":[128,183],"efficiency;":[129],"(iii)":[130],"Small-scale":[131],"High-quality":[132],"Instruction-following":[134],"Datasets":[135],"careful":[137],"data":[138,148],"curation":[139],"employing":[141],"resampling":[143],"strategy":[144],"address":[146],"type":[149],"imbalances.":[150],"With":[151],"above":[152],"components,":[153],"lightweight":[156],"2B":[157],"using":[159],"256K":[160],"data,":[161],"achieves":[162],"strong":[164],"75.1%":[165],"accuracy":[166],"zero-shot":[168],"grounding.":[170],"Its":[171],"UI-guided":[172],"further":[175,202],"reduces":[176],"33%":[177],"tokens":[181],"speeds":[185],"up":[186],"performance":[188],"1.4\u00d7.":[190],"Navigation":[191],"experiments":[192],"across":[193],"web":[194],"[12],":[195],"mobile":[196],"[35],":[197],"online":[199],"[39]":[200],"environments":[201],"underscore":[203],"effectiveness":[205],"potential":[207],"our":[209],"advancing":[212],"The":[216],"models":[217],"available":[219],"at":[220],"https://github.com/showlab/ShowUI.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
