{"id":"https://openalex.org/W7160324738","doi":"https://doi.org/10.1109/wacv61042.2026.00100","title":"ZonUI-3B: Competitive GUI Grounding with a 3B VLM Trained on a Single Consumer GPU","display_name":"ZonUI-3B: Competitive GUI Grounding with a 3B VLM Trained on a Single Consumer GPU","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160324738","doi":"https://doi.org/10.1109/wacv61042.2026.00100"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5120486458","display_name":"ZongHan Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"ZongHan Hsieh","raw_affiliation_strings":["National Yang Ming Chiao Tung University,DeepCAT Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,DeepCAT Lab","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103407606","display_name":"S F Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"ShengJing Yang","raw_affiliation_strings":["National Yang Ming Chiao Tung University,DeepCAT Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,DeepCAT Lab","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135321021","display_name":"Tzer-Jen Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzer-Jen Wei","raw_affiliation_strings":["National Yang Ming Chiao Tung University,DeepCAT Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,DeepCAT Lab","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39942003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"959","last_page":"966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11429","display_name":"Semiconductor Lasers and Optical Devices","score":0.17759999632835388,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11429","display_name":"Semiconductor Lasers and Optical Devices","score":0.17759999632835388,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10851","display_name":"Optical Wireless Communication Technologies","score":0.12540000677108765,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10232","display_name":"Optical Network Technologies","score":0.06350000202655792,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/software","display_name":"Software","score":0.41839998960494995},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.36649999022483826},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.2542000114917755},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.24079999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6577000021934509},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.24079999327659607},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.23029999434947968}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4618559181690216,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W4402671607","https://openalex.org/W4402753874","https://openalex.org/W4412888531","https://openalex.org/W4412888849","https://openalex.org/W4413147863","https://openalex.org/W4415539539","https://openalex.org/W7160083757"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"ZonUI-3B,":[5],"a":[6,17,48,70,106],"lightweight":[7],"Vision-Language":[8],"Model":[9],"(VLM)":[10],"that":[11,103,120],"can":[12,111],"be":[13],"fully":[14],"trained":[15],"on":[16,31,86,105,132,149,152,156],"single":[18],"consumer-grade":[19],"GPU":[20],"(RTX":[21],"4090)":[22],"while":[23,114],"delivering":[24],"performance":[25],"comparable":[26],"to":[27,89],"significantly":[28,115],"larger":[29],"models":[30,161],"GUI":[32,80,134,179],"grounding":[33,135],"tasks.":[34],"The":[35],"model":[36],"incorporates":[37],"several":[38],"key":[39],"innovations:":[40],"(i)":[41],"integration":[42],"of":[43,52,171],"multiple":[44],"open-source":[45],"datasets":[46],"into":[47],"cross-platform,":[49],"multi-resolution":[50],"corpus":[51],"24K":[53],"examples":[54],"covering":[55],"mobile,":[56],"desktop,":[57],"and":[58,92,140,154],"web":[59],"GUIs,":[60],"effectively":[61],"addressing":[62],"data":[63,88,94,121],"scarcity":[64],"in":[65,174,182],"high-resolution":[66,87,183],"desktop":[67,184],"environments;":[68],"(ii)":[69],"two-stage":[71,172],"fine-tuning":[72,85,173],"strategy,":[73],"where":[74,99],"initial":[75],"cross-platform":[76],"training":[77,104,117],"builds":[78],"robust":[79],"understanding,":[81],"followed":[82],"by":[83],"specialized":[84],"enhance":[90],"adaptability;":[91],"(iii)":[93],"curation":[95],"with":[96],"redundancy":[97],"reduction,":[98],"our":[100],"results":[101],"reveal":[102],"smaller":[107],"randomly":[108],"sampled":[109],"subset":[110],"maintain":[112],"accuracy":[113],"reducing":[116],"time,":[118],"highlighting":[119],"diversity":[122],"is":[123],"more":[124],"critical":[125],"than":[126],"sheer":[127],"dataset":[128],"scale.":[129],"Empirical":[130],"evaluation":[131],"standard":[133],"benchmarks\u2014including":[136],"ScreenSpot,":[137,150],"ScreenSpot-v2,":[138,153],"GroundUI-1K,":[139,157],"the":[141,169],"challenging":[142],"ScreenSpot-Pro\u2014demonstrates":[143],"ZonUI-3B\u2019s":[144],"strong":[145],"performance,":[146],"achieving":[147],"84.9%":[148],"86.4%":[151],"82.4%":[155],"surpassing":[158],"all":[159],"prior":[160],"under":[162],"4B":[163],"parameters.":[164],"Ablation":[165],"studies":[166],"further":[167],"confirm":[168],"effectiveness":[170],"improving":[175],"robustness":[176],"across":[177],"diverse":[178],"environments,":[180],"particularly":[181],"scenarios.":[185]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}
