{"id":"https://openalex.org/W4416978029","doi":"https://doi.org/10.1109/wacv61042.2026.00118","title":"AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent","display_name":"AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416978029","doi":"https://doi.org/10.1109/wacv61042.2026.00118"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00118","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.00846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Neeraj Anand","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neeraj Anand","raw_affiliation_strings":["Media and Data Science Research, Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Data Science Research, Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030428486","display_name":"Rishabh Jain","orcid":"https://orcid.org/0009-0005-3100-4201"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishabh Jain","raw_affiliation_strings":["Media and Data Science Research, Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Data Science Research, Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061843533","display_name":"Sohan Patnaik","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sohan Patnaik","raw_affiliation_strings":["Media and Data Science Research, Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Data Science Research, Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081562101","display_name":"Balaji Krishnamurthy","orcid":"https://orcid.org/0000-0003-0464-536X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balaji Krishnamurthy","raw_affiliation_strings":["Media and Data Science Research, Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Data Science Research, Adobe","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112660758","display_name":"Mausoom Sarkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mausoom Sarkar","raw_affiliation_strings":["Media and Data Science Research, Adobe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Media and Data Science Research, Adobe","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01779166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1147","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8032000064849854,"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":0.8032000064849854,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.02070000022649765,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.01600000075995922,"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/automation","display_name":"Automation","score":0.6151000261306763},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.578499972820282},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4799000024795532},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4542999863624573},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43860000371932983},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43230000138282776},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.4034999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8331000208854675},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.6151000261306763},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.578499972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5127999782562256},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4401000142097473},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3885999917984009},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.336899995803833},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.32679998874664307},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2694999873638153}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00118","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"},{"id":"pmh:oai:arXiv.org:2512.00846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00846","pdf_url":"https://arxiv.org/pdf/2512.00846","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.00846","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.00846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.00846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00846","pdf_url":"https://arxiv.org/pdf/2512.00846","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"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":[1,199],"a":[2,188],"growing":[3],"demand":[4],"for":[5,34,48,80,192],"mobile":[6],"user":[7],"interface":[8],"(UI)":[9],"automation,":[10],"driven":[11],"by":[12,67],"its":[13,144],"broad":[14],"applications":[15],"across":[16],"industries.":[17],"With":[18],"the":[19,141,152],"advent":[20],"of":[21,64,143],"visual":[22],"language":[23,154],"models":[24,85,106],"(VLMs),":[25],"GUI":[26,134],"automation":[27,42,135],"has":[28],"progressed":[29],"from":[30],"generating":[31],"text-based":[32],"instructions":[33],"humans":[35],"to":[36,52,55,96],"autonomously":[37],"executing":[38],"tasks,":[39],"thus":[40],"optimizing":[41],"workflows.":[43],"Recent":[44],"approaches":[45],"leverage":[46],"VLMs":[47],"this":[49,119],"problem":[50],"due":[51,95],"their":[53],"ability":[54],"1)":[56],"process":[57],"on-screen":[58],"content":[59],"directly,":[60],"2)":[61],"remain":[62],"independent":[63],"device-specific":[65],"APIs":[66],"utilizing":[68],"human":[69],"actions":[70,94],"(e.g.,":[71],"clicks,":[72],"typing),":[73],"and":[74,92,113,175,184],"3)":[75],"apply":[76],"real-world":[77],"contextual":[78],"knowledge":[79],"task":[81],"understanding.":[82],"However,":[83],"these":[84],"often":[86,108],"have":[87],"trouble":[88],"accurately":[89],"identifying":[90],"widgets":[91],"determining":[93],"limited":[97],"spatial":[98],"information":[99],"in":[100,115,133,151],"vision":[101],"encoder":[102],"features.":[103],"Additionally,":[104],"top-performing":[105],"are":[107],"large,":[109],"requiring":[110],"extensive":[111],"training":[112],"resulting":[114],"inference":[116],"delays.":[117],"In":[118],"work,":[120],"we":[121,158],"introduce":[122],"AFRAgent":[123,181],",":[124],"an":[125,160],"instruct-BLIP-based":[126],"multimodal":[127],"architecture":[128],"that":[129,169],"achieves":[130],"superior":[131],"performance":[132],"while":[136],"being":[137],"less":[138],"than":[139],"one-fourth":[140],"size":[142],"nearest":[145],"competitor.":[146],"To":[147],"enhance":[148],"image":[149,173],"embeddings":[150,174],"large":[153],"model":[155],"(LLM)":[156],"pipeline,":[157],"propose":[159],"adaptive":[161],"feature":[162],"renormalization-based":[163],"(a":[164],"token-level":[165],"affine":[166],"transformation)":[167],"technique":[168],"effectively":[170],"enriches":[171],"low-resolution":[172],"fuses":[176],"high-resolution":[177],"details.":[178],"We":[179],"evaluate":[180],"on":[182],"Meta-GUI":[183],"AITW":[185],"benchmarks,":[186],"establishing":[187],"new":[189],"state-of-the-art":[190],"baseline":[191],"smartphone":[193],"automation.<sup":[194],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[196],"The":[197],"code":[198],"available":[200],"at":[201],"https://github.com/neerajanand321/AFRAgent":[202]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-12-03T00:00:00"}