{"id":"https://openalex.org/W4412887717","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1152","title":"Aria-UI: Visual Grounding for GUI Instructions","display_name":"Aria-UI: Visual Grounding for GUI Instructions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887717","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1152"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1152","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1152","pdf_url":"https://aclanthology.org/2025.findings-acl.1152.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1152.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024168844","display_name":"Yuhao Yang","orcid":"https://orcid.org/0000-0002-2543-8450"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371961","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0001-6936-5081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054389280","display_name":"Dongxu Li","orcid":"https://orcid.org/0009-0007-0016-4469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056165952","display_name":"Ziyang Luo","orcid":"https://orcid.org/0000-0001-7415-8124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760114","display_name":"Bei Chen","orcid":"https://orcid.org/0000-0002-8033-8102"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040402082","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0001-9872-3511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100608756","display_name":"Junnan Li","orcid":"https://orcid.org/0000-0002-1405-2034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junnan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22418","last_page":"22433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9708999991416931,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.9628999829292297,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.9603000283241272,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/computer-science","display_name":"Computer science","score":0.7924016714096069},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5019805431365967},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.45366838574409485},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4267650544643402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7924016714096069},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5019805431365967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.45366838574409485},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4267650544643402}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1152","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1152","pdf_url":"https://aclanthology.org/2025.findings-acl.1152.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1152","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1152","pdf_url":"https://aclanthology.org/2025.findings-acl.1152.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887717.pdf","grobid_xml":"https://content.openalex.org/works/W4412887717.grobid-xml"},"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":{"Digital":[0],"agents":[1],"for":[2,48,78,98],"automating":[3],"tasks":[4],"across":[5,104],"different":[6],"platforms":[7],"by":[8],"directly":[9],"manipulating":[10],"the":[11],"GUIs":[12],"are":[13],"increasingly":[14],"important.For":[15],"these":[16],"agents,":[17],"grounding":[18],"from":[19],"language":[20],"instructions":[21],"to":[22,30,61,125],"target":[23],"elements":[24],"remains":[25],"a":[26,42,52,67],"significant":[27],"challenge":[28],"due":[29],"reliance":[31,56],"on":[32,57],"HTML":[33],"or":[34],"AXTree":[35],"inputs.In":[36],"this":[37],"paper,":[38],"we":[39,65],"introduce":[40],"Aria-UI,":[41],"large":[43],"multimodal":[44],"model":[45,121],"specifically":[46],"designed":[47],"GUI":[49],"grounding.Aria-UI":[50,99],"adopts":[51],"pure-vision":[53],"approach,":[54],"eschewing":[55],"auxiliary":[58],"inputs.To":[59],"adapt":[60],"heterogeneous":[62],"planning":[63],"instructions,":[64],"propose":[66],"scalable":[68],"data":[69,119],"pipeline":[70],"that":[71],"synthesizes":[72],"diverse":[73],"and":[74,89,106,113,120],"highquality":[75],"instruction":[76],"samples":[77],"grounding.To":[79],"handle":[80],"dynamic":[81],"contexts":[82],"in":[83],"task":[84],"performing,":[85],"Aria-UI":[86],"incorporates":[87],"textual":[88],"text-image":[90],"interleaved":[91],"action":[92],"histories,":[93],"enabling":[94],"robust":[95],"context-aware":[96],"reasoning":[97],"sets":[100],"new":[101],"state-of-the-art":[102],"results":[103],"offline":[105],"online":[107],"agent":[108],"benchmarks,":[109],"outperforming":[110],"both":[111],"vision-only":[112],"AXTree-reliant":[114],"baselines.We":[115],"release":[116],"all":[117],"training":[118],"checkpoints":[122],"at":[123],"https://ariaui.github.io":[124],"foster":[126],"further":[127],"research.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
