{"id":6621,"date":"2025-04-30T05:10:00","date_gmt":"2025-04-29T20:10:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6621"},"modified":"2025-04-30T05:10:00","modified_gmt":"2025-04-29T20:10:00","slug":"tongui-building-generalized-gui-agents-by-learning-from-multimodal-web-tutorials","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6621","title":{"rendered":"TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials\u00a0<\/strong>[70.1]<br>\u30ea\u30c3\u30c1\u306a\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30ebWeb\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u304b\u3089\u5b66\u7fd2\u3057,\u6c4e\u7528GUI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u69cb\u7bc9\u3059\u308bTongUI\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u63d0\u6848\u3059\u308b\u3002 \u6211\u3005\u306f\u30015\u3064\u306e\u30aa\u30da\u30ec\u30fc\u30c6\u30a3\u30f3\u30b0\u30b7\u30b9\u30c6\u30e0\u3068200\u4ee5\u4e0a\u306e\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u307e\u305f\u304c\u308b143K\u30c8\u30e9\u30b8\u30a7\u30af\u30c8\u30ea\u30c7\u30fc\u30bf\u3092\u542b\u3080GUI-Net\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u4f5c\u6210\u3059\u308b\u3002 \u6211\u3005\u306fGUI-Net\u4e0a\u3067Qwen2.5-VL-3B\/7B\u30e2\u30c7\u30eb\u3092\u5fae\u8abf\u6574\u3057\u3066TongUI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u958b\u767a\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.12679v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.12679v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 17 Apr 2025 06:15:56 GMT)<\/li>\n\n\n\n<li>WEB\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3092\u6d3b\u7528\u3057\u305f\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u69cb\u7bc9\u3068fine tuning\u306b\u3088\u308b\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u958b\u767a<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/tongui-agent.github.io\/\">TongUI: Building Generalized GUI Agents by Learning from Multimodal Web Tutorials<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[181,491],"class_list":["post-6621","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gui-agent","tag-491"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6621","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6621"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6621\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6621"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6621"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6621"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}