{"id":7829,"date":"2025-11-26T18:48:00","date_gmt":"2025-11-26T09:48:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7829"},"modified":"2025-11-23T20:53:55","modified_gmt":"2025-11-23T11:53:55","slug":"can-world-simulators-reason-gen-vire-a-generative-visual-reasoning-benchmark","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7829","title":{"rendered":"Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark\u00a0<\/strong>[48.0]<br>\u30d3\u30c7\u30aa\u751f\u6210\u30e2\u30c7\u30eb\u306f\u3001Chain-of-Frames (CoF)\u63a8\u8ad6\u3092\u901a\u3058\u3066\u3001\u6f5c\u5728\u7684\u306a\u4e16\u754c\u30b7\u30df\u30e5\u30ec\u30fc\u30bf\u3068\u3057\u3066\u767b\u5834\u3057\u305f\u3002 \u65e2\u5b58\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306f\u3001\u5fe0\u5b9f\u3055\u3084\u30a2\u30e9\u30a4\u30e1\u30f3\u30c8\u306b\u91cd\u70b9\u3092\u7f6e\u3044\u3066\u304a\u308a\u3001CoF\u306e\u63a8\u8ad6\u3092\u8a55\u4fa1\u3057\u3066\u3044\u306a\u3044\u3002 \u6211\u3005\u306f,\u8a8d\u77e5\u79d1\u5b66\u3068\u5b9f\u4e16\u754c\u306eAI\u5fdc\u7528\u3092\u57fa\u76e4\u3068\u3057\u305f\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bGen-ViRe\u3092\u7d39\u4ecb\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2511.13853v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2511.13853v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 17 Nov 2025 19:11:39 GMT)<\/li>\n\n\n\n<li>\u30d3\u30c7\u30aa\u751f\u6210\u30e2\u30c7\u30eb\u3092\u901a\u3058\u305f\u56e0\u679c\u95a2\u4fc2\u306e\u628a\u63e1\uff08world model\u3078\u306e\u53ef\u80fd\u6027\uff09\u3092\u8a55\u4fa1\u3059\u308b\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u63d0\u6848\u3002\u300cGen-ViRe evaluates six core cognitive dimensions: (1) Perceptual, (2) Analogical, (3) Abstract, (4) Planning, (5) Spatial &amp; Temporal, and (6) Algorithmic &amp; Logical, with each dimension comprising four different sub-categories.\u300d<\/li>\n\n\n\n<li>\u300cSora-2 achieves the highest overall score (0.560), establishing the top tier with particularly strong performance in the most cognitively demanding domains: \u201cAbstract Reasoning\u201d (0.604), \u201cAlgorithmic &amp; Logical\u201d (0.472), and \u201cPerceptual\u201d (0.496). The second tier comprises three highly competitive models\u2014Hailuo-2.3 (0.493), Wan-2.5 (0.490), and Veo-3.1 (0.486)\u2014each exhibiting distinct specialized strengths. Hailuo-2.3 achieves the highest score in \u201cPlanning\u201d (0.778), showcasing exceptional sequential decision-making capabilities, while Wan-2.5 leads in \u201cAnalogy\u201d (0.500), excelling at analogical reasoning.\u300d\u3068\u30e2\u30c7\u30eb\u3054\u3068\u306b\u7279\u6027\u304c\u304b\u306a\u308a\u7570\u306a\u308b\u306e\u304c\u8208\u5473\u6df1\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/L-CodingSpace\/GVR\">https:\/\/github.com\/L-CodingSpace\/GVR<\/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":[449,517],"class_list":["post-7829","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-world-model","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7829","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=7829"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7829\/revisions"}],"predecessor-version":[{"id":7830,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7829\/revisions\/7830"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7829"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7829"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7829"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}