{"id":5717,"date":"2024-11-06T05:25:00","date_gmt":"2024-11-05T20:25:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5717"},"modified":"2024-11-06T05:25:00","modified_gmt":"2024-11-05T20:25:00","slug":"os-atlas-a-foundation-action-model-for-generalist-gui-agents","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5717","title":{"rendered":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>OS-ATLAS: A Foundation Action Model for Generalist GUI Agents\u00a0<\/strong>[55.4]<br>OS-Atlas\u306fGUI\u30b0\u30e9\u30a6\u30f3\u30c7\u30a3\u30f3\u30b0\u3068OOD\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30bf\u30b9\u30af\u306b\u512a\u308c\u305f\u57fa\u790e\u7684\u306aGUI\u30a2\u30af\u30b7\u30e7\u30f3\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 \u73fe\u5728\u307e\u3067\u306b1300\u4e07\u4ee5\u4e0a\u306eGUI\u8981\u7d20\u3092\u542b\u3080\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e\u30af\u30ed\u30b9\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0GUI\u57fa\u76e4\u30b3\u30fc\u30d1\u30b9\u3092\u30ea\u30ea\u30fc\u30b9\u3057\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.23218v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.23218v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 30 Oct 2024 17:10:19 GMT)<\/li>\n\n\n\n<li>GUI\u3092\u5bfe\u8c61\u3068\u3057\u305fFoundation Action Model\u306e\u63d0\u6848\u3001Anthropic\u306e\u767a\u8868\u3082\u3042\u3063\u3066\u76db\u308a\u4e0a\u304c\u3063\u3066\u3044\u308b\u9818\u57df\u3002\u6027\u80fd\u306f\u300calthough GPT-4o with OS-Atlas-Base as the grounding module still lags behind human performance, it significantly outperforms other grounding methods such as SeeClick and Set-of-Mark (SoM)\u300d\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/osatlas.github.io\/\">OS-Atlas Homepage<\/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":[8,153,180,181,423],"class_list":["post-5717","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-action","tag-foundation-models","tag-gui","tag-gui-agent","tag-ui"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5717","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=5717"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5717\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5717"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5717"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5717"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}