{"id":"https://openalex.org/W4405434149","doi":"https://doi.org/10.1109/iccv51701.2025.02277","title":"Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining","display_name":"Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405434149","doi":"https://doi.org/10.1109/iccv51701.2025.02277"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.10342","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066775492","display_name":"Zhiqi Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Ge","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060135268","display_name":"Xiaoli Pang","orcid":"https://orcid.org/0000-0002-5520-1083"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglei Pang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061203331","display_name":"Minghe Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghe Gao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033407215","display_name":"Kaihang Pan","orcid":"https://orcid.org/0009-0001-2967-4573"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaihang Pan","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Lin","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Fei","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":"Hao Fei","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082131901","display_name":"Wenqiao Zhang","orcid":"https://orcid.org/0000-0002-5988-7609"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqiao Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063062444","display_name":"Siliang Tang","orcid":"https://orcid.org/0000-0002-7356-9711"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siliang Tang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00081579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10470","display_name":"Usability and User Interface Design","score":0.9126999974250793,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10470","display_name":"Usability and User Interface Design","score":0.9126999974250793,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10789","display_name":"Interactive and Immersive Displays","score":0.9061999917030334,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/refining","display_name":"Refining (metallurgy)","score":0.6970688700675964},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.668705940246582},{"id":"https://openalex.org/keywords/iris","display_name":"IRIS (biosensor)","score":0.6011672019958496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5128353238105774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3013291358947754},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.14886808395385742},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1317635178565979},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.10005876421928406}],"concepts":[{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.6970688700675964},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.668705940246582},{"id":"https://openalex.org/C2779503344","wikidata":"https://www.wikidata.org/wiki/Q5973514","display_name":"IRIS (biosensor)","level":3,"score":0.6011672019958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5128353238105774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3013291358947754},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.14886808395385742},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1317635178565979},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.10005876421928406},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.10342","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10342","pdf_url":"https://arxiv.org/pdf/2412.10342","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.2412.10342","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.10342","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.10342","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.10342","pdf_url":"https://arxiv.org/pdf/2412.10342","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":[{"id":"https://openalex.org/G4881796371","display_name":null,"funder_award_id":"62436007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405434149.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1595345252","https://openalex.org/W2392526918","https://openalex.org/W2362540361","https://openalex.org/W2019560916","https://openalex.org/W2361983698","https://openalex.org/W2347697528","https://openalex.org/W2354123794"],"abstract_inverted_index":{"Digital":[0],"agents":[1,23,39,59],"are":[2],"increasingly":[3],"employed":[4],"to":[5,35,119,130,186],"automate":[6],"tasks":[7,133],"in":[8,63,141,189],"interactive":[9],"digital":[10,72],"environments":[11],"such":[12],"as":[13],"web":[14,191],"pages,":[15],"software":[16],"applications,":[17],"and":[18,93,101,150,192],"operating":[19],"systems.":[20],"While":[21],"text-based":[22],"built":[24],"on":[25],"Large":[26,42],"Language":[27,43],"Models":[28,44],"(LLMs)":[29],"often":[30],"require":[31],"frequent":[32],"updates":[33],"due":[34],"platform-specific":[36],"APIs,":[37],"visual":[38,64,80],"leveraging":[40,135],"Multimodal":[41],"(MLLMs)":[45],"offer":[46],"enhanced":[47],"adaptability":[48],"by":[49,114,134],"interacting":[50],"directly":[51],"with":[52,121,170],"Graphical":[53],"User":[54],"Interfaces":[55],"(GUIs).":[56],"However,":[57],"these":[58,84],"face":[60],"significant":[61,187],"challenges":[62,85],"perception,":[65],"particularly":[66],"when":[67],"handling":[68],"high-resolution,":[69],"visually":[70,103],"complex":[71,132],"environments.":[73],"This":[74],"paper":[75],"introduces":[76],"Iris,":[77],"a":[78,107,136],"foundational":[79],"agent":[81,194],"that":[82,162],"addresses":[83],"through":[86],"two":[87],"key":[88],"innovations:":[89],"Information-Sensitive":[90],"Cropping":[91],"(ISC)":[92],"Self-Refining":[94],"Dual":[95],"Learning":[96],"(SRDL).":[97],"ISC":[98],"dynamically":[99],"identifies":[100],"prioritizes":[102],"dense":[104],"regions":[105],"using":[106,177],"edge":[108],"detection":[109],"algorithm,":[110],"enabling":[111],"efficient":[112],"processing":[113],"allocating":[115],"more":[116,179],"computational":[117],"resources":[118],"areas":[120],"higher":[122],"information":[123],"density.":[124],"SRDL":[125],"enhances":[126],"the":[127],"agent's":[128],"ability":[129],"handle":[131],"dual-learning":[137],"loop,":[138],"where":[139],"improvements":[140,183],"referring":[142],"(describing":[143],"UI":[144],"elements)":[145,149],"reinforce":[146],"grounding":[147],"(locating":[148],"vice":[151],"versa,":[152],"all":[153],"without":[154],"requiring":[155],"additional":[156],"annotated":[157],"data.":[158,181],"Empirical":[159],"evaluations":[160],"demonstrate":[161],"Iris":[163],"achieves":[164],"state-of-the-art":[165],"performance":[166],"across":[167],"multiple":[168],"benchmarks":[169],"only":[171],"850K":[172],"GUI":[173],"annotations,":[174],"outperforming":[175],"methods":[176],"10x":[178],"training":[180],"These":[182],"further":[184],"translate":[185],"gains":[188],"both":[190],"OS":[193],"downstream":[195],"tasks.":[196]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}