{"id":8206,"date":"2026-02-17T06:17:00","date_gmt":"2026-02-16T21:17:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=8206"},"modified":"2026-02-14T21:19:20","modified_gmt":"2026-02-14T12:19:20","slug":"points-gui-g-gui-grounding-journey","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=8206","title":{"rendered":"POINTS-GUI-G: GUI-Grounding Journey\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>POINTS-GUI-G: GUI-Grounding Journey\u00a0<\/strong>[22.4]<br>POINTS-GUIG-8B\u306f\u3001ScreenSpotPro\u306759.9\u3001OSWorld-G\u306766.0\u3001ScreenSpot-v2\u306795.7\u3001UIVision\u306749.9\u306e\u30b9\u30b3\u30a2\u3067\u6700\u5148\u7aef\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u5b9f\u73fe\u3059\u308b\u3002 \u30e2\u30c7\u30eb\u306e\u6210\u529f\u306f,(1)\u30c7\u30fc\u30bf\u5de5\u5b66\u306e\u7cbe\u932c,(2)\u8a13\u7df4\u6226\u7565\u306e\u6539\u5584,(3)\u691c\u8a3c\u3055\u308c\u305f\u30ea\u30ef\u30fc\u30c9\u306b\u3088\u308b\u5f37\u5316\u5b66\u7fd2\u306e3\u3064\u306e\u8981\u56e0\u306b\u3088\u3063\u3066\u5f15\u304d\u8d77\u3053\u3055\u308c\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2602.06391v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2602.06391v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 06 Feb 2026 05:14:11 GMT)<\/li>\n\n\n\n<li>GUI grounding\u3067\u826f\u3044\u6027\u80fd\u3092\u51fa\u3059\u5c0f\u578b\u30e2\u30c7\u30eb\u306e\u63d0\u6848\u3002\u300c(1) Refined Data Engineering, involving the unification of diverse open-source datasets format alongside sophisticated strategies for augmentation, filtering, and difficulty grading; (2) Improved Training Strategies, including continuous fine-tuning of the vision encoder to enhance perceptual accuracy and maintaining resolution consistency between training and inference; and (3) Reinforcement Learning (RL) with Verifiable Rewards.\u300d\u3068\u69cb\u7bc9\u904e\u7a0b\u3082\u53c2\u8003\u306b\u306a\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/Tencent\/POINTS-GUI\">GitHub &#8211; Tencent\/POINTS-GUI<\/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],"class_list":["post-8206","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gui-agent"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8206","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=8206"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8206\/revisions"}],"predecessor-version":[{"id":8207,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8206\/revisions\/8207"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8206"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8206"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8206"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}