{"id":5031,"date":"2024-07-03T05:53:00","date_gmt":"2024-07-02T20:53:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5031"},"modified":"2024-07-03T05:53:00","modified_gmt":"2024-07-02T20:53:00","slug":"wildvision","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5031","title":{"rendered":"WildVision"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences\u00a0<\/strong>[122.9]<br>WildVision-Arena(WV-Arena)\u306f\u3001\u4eba\u9593\u306e\u597d\u307f\u3092\u53ce\u96c6\u3057\u3066\u8996\u899a\u8a00\u8a9e\u30e2\u30c7\u30eb(VLM)\u3092\u8a55\u4fa1\u3059\u308b\u30aa\u30f3\u30e9\u30a4\u30f3\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0\u3067\u3059\u3002 WV-\u30d9\u30f3\u30c1\u306f\u3001\u305d\u308c\u305e\u308c\u306eVLM\u3068Claude-3-Sonnet\u3092\u6bd4\u8f03\u3057\u3001WV-Arena Elo\u306e0.94\u306e\u30b9\u30d4\u30a2\u30de\u30f3\u76f8\u95a2\u3092\u9054\u6210\u3057\u3066\u3044\u308b\u3002 \u5b9f\u4e16\u754c\u306e20\u4e07\u4ef6\u306e\u30a4\u30f3\u30bf\u30e9\u30af\u30b7\u30e7\u30f3\u3092\u5305\u62ec\u7684\u306b\u5206\u6790\u3057\u305f\u7d50\u679c,\u30c8\u30c3\u30d7\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306eVLM\u306e\u969c\u5bb3\u4e8b\u4f8b\u306b\u5bfe\u3059\u308b\u91cd\u8981\u306a\u6d1e\u5bdf\u304c\u5f97\u3089\u308c\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2406.11069v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2406.11069v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sun, 16 Jun 2024 20:53:25 GMT)<\/li>\n\n\n\n<li>Vision Language\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1\u74b0\u5883\u3001\u4eba\u9593\u306e\u597d\u307f\u3092\u53ce\u96c6\u3059\u308b\u30aa\u30f3\u30e9\u30a4\u30f3\u30d7\u30e9\u30c3\u30c8\u30d5\u30a9\u30fc\u30e0WILDVISION-ARENA(WV-ARENA)\u3092\u4f5c\u6210\u3002GPT-4\u306e\u512a\u79c0\u3055\u3001\u4ed6\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068\u306e\u5dee\u7570\u304c\u8208\u5473\u6df1\u3044\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/huggingface.co\/spaces\/WildVision\/vision-arena\">Vision Arena (Testing VLMs side-by-side) &#8211; a Hugging Face Space by WildVision<\/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":[434,517],"class_list":["post-5031","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-vision-language","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5031","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=5031"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5031\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5031"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5031"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5031"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}