{"id":"https://openalex.org/W4416036167","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.920","title":"UI-Hawk: Unleashing the Screen Stream Understanding for Mobile GUI Agents","display_name":"UI-Hawk: Unleashing the Screen Stream Understanding for Mobile GUI Agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036167","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.920"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.920","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.920","pdf_url":"https://aclanthology.org/2025.emnlp-main.920.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.920.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024632865","display_name":"Jiwen Zhang","orcid":"https://orcid.org/0000-0002-8060-6824"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiwen Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100544606","display_name":"Yaqi Yu","orcid":"https://orcid.org/0009-0006-2700-8389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya-Qi Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082417575","display_name":"Minghui Liao","orcid":"https://orcid.org/0000-0003-0184-5702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghui Liao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451390","display_name":"Wentao Li","orcid":"https://orcid.org/0000-0001-8980-0909"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"WenTao Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110966409","display_name":"Jihao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihao Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011504177","display_name":"Zhongyu Wei","orcid":"https://orcid.org/0000-0003-3789-8507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyu Wei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5024632865"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35936449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18228","last_page":"18247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.09009999781847,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.09009999781847,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.07989999651908875,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.07150000333786011,"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/mobile-device","display_name":"Mobile device","score":0.3650999963283539},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.31040000915527344},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.28700000047683716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2736000120639801},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.2721000015735626},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.2623000144958496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6050999760627747},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.920","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.920","pdf_url":"https://aclanthology.org/2025.emnlp-main.920.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.920","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.920","pdf_url":"https://aclanthology.org/2025.emnlp-main.920.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036167.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}