{"id":4740,"date":"2024-04-18T05:11:00","date_gmt":"2024-04-17T20:11:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4740"},"modified":"2024-04-18T05:11:00","modified_gmt":"2024-04-17T20:11:00","slug":"visualwebbench","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4740","title":{"rendered":"VisualWebBench"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?\u00a0<\/strong>[115.6]<br>MLLM(Multimodal Large Language Model)\u306f\u3001Web\u95a2\u9023\u306e\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u6709\u671b\u3067\u3042\u308b\u3053\u3068\u3092\u793a\u3059\u3002 Web\u30c9\u30e1\u30a4\u30f3\u306b\u304a\u3051\u308b\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u8a55\u4fa1\u306f\u3001\u5305\u62ec\u7684\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u304c\u6b20\u5982\u3057\u3066\u3044\u308b\u305f\u3081\u3001\u4f9d\u7136\u3068\u3057\u3066\u8ab2\u984c\u3067\u3042\u308b\u3002 bench\u306f\u3001\u3055\u307e\u3056\u307e\u306aWeb\u30bf\u30b9\u30af\u306b\u308f\u305f\u308bMLLM\u306e\u6a5f\u80fd\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2404.05955v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2404.05955v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 09 Apr 2024 02:29:39 GMT)<\/li>\n\n\n\n<li>\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u306aLLM\u3092\u5bfe\u51e6\u3068\u3057\u305fWeb undestanding\u30bf\u30b9\u30af\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u300cVisualWebBench consists of seven tasks, and comprises 1.5K human-curated instances from 139 real websites, covering 87 sub-domains.\u300d\u3068\u305d\u3053\u305d\u3053\u306e\u898f\u6a21\u3002\u7d50\u679c\u306f\u30bf\u30b9\u30af\u306b\u3088\u3063\u3066\u7570\u306a\u308b\u304c\u3001\u5e73\u5747\u7684\u306b\u306fClaude Sonnet > GPT-4V > Claude Opus > LLaVA-1.6-34B > Gemini Pro \u3068\u3084\u3084\u610f\u5916\u3002\u65e5\u672c\u8a9e\u7248\u4f5c\u308a\u305f\u3044\u306a\u30fc\u3068\u601d\u308f\u306a\u304f\u3082\u306a\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/visualwebbench.github.io\/\">VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?<\/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":[251,517],"class_list":["post-4740","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mllm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4740","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=4740"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4740\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4740"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4740"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4740"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}