{"id":4985,"date":"2024-06-18T03:30:00","date_gmt":"2024-06-17T18:30:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4985"},"modified":"2024-06-18T03:30:00","modified_gmt":"2024-06-17T18:30:00","slug":"mmworld-towards-multi-discipline-multi-faceted-world-model-evaluation-in-videos","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4985","title":{"rendered":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos\u00a0<\/strong>[155.5]<br>MMWorld\u306f,\u8907\u6570\u5206\u91ce\u306e\u30de\u30eb\u30c1\u30e2\u30fc\u30c9\u30d3\u30c7\u30aa\u7406\u89e3\u306e\u305f\u3081\u306e\u65b0\u3057\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002 MMWorld\u306f\u3001\u30d3\u30c7\u30aa\u5168\u4f53\u306b\u95a2\u3059\u308b\u8cea\u554f\u3092\u4f34\u3046MLLM\u3092\u8a55\u4fa1\u3059\u308b\u4eba\u9593\u30a2\u30ce\u30c6\u30fc\u30b7\u30e7\u30f3\u4ed8\u304d\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3068\u3001\u77e5\u899a\u306e\u5358\u4e00\u30e2\u30fc\u30c9\u5185\u3067MLLM\u3092\u5206\u6790\u3059\u308b\u5408\u6210\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u3002 \u3053\u306e\u8a55\u4fa1\u306b\u306f2\u3064\u306e\u30d7\u30ed\u30d7\u30e9\u30a4\u30a8\u30bf\u30ea\u306aMLLM\u306810\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9MLLM\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001MMWorld\u3068\u7af6\u5408\u3057\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2406.08407v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2406.08407v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 12 Jun 2024 16:54:54 GMT)<\/li>\n\n\n\n<li>\u4e16\u754c\u30e2\u30c7\u30eb\u3068\u3057\u3066\u306eMLLM\uff08\u4f8b\u3048\u3070\u7269\u7406\u73fe\u8c61\u3092\u30b7\u30df\u30e5\u30ec\u30fc\u30c8\u3067\u304d\u308b\u304b\uff1f\u306a\u3069\uff09\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002Leader board\u304b\u3089\u306fGPT-4V\u304c\u9996\u4f4d\u3067GeminiPro\u304c2\u4f4d\u306b\u306a\u3063\u3066\u3044\u308b\u3002\u4e00\u65b9\u3067\u300cEven the best performer, GPT-4V, can only achieve a 52.30% overall accuracy, and four MLLMs particularly trained on videos perform worse than random chance.\u300d\u3068\u3044\u3046\u6307\u6458\u3082\u3002MLLM\u306a\u3044\u3057\u30d3\u30c7\u30aa\u5408\u6210\u7cfb\u306e\u30e2\u30c7\u30eb\u304cWorld model\u306b\u306a\u308a\u3048\u308b\u304b\u306f\u8cdb\u5426\u4e21\u8ad6\u3042\u308b\u304c\u3001\u6ce8\u76ee\u3092\u96c6\u3081\u3066\u3044\u308b\u5206\u91ce\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/mmworld-bench.github.io\/\">MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos (mmworld-bench.github.io)<\/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":[251,449,517],"class_list":["post-4985","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mllm","tag-world-model","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4985","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=4985"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4985\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4985"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4985"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4985"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}