{"id":5719,"date":"2024-11-12T05:35:00","date_gmt":"2024-11-11T20:35:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5719"},"modified":"2024-11-12T05:35:00","modified_gmt":"2024-11-11T20:35:00","slug":"mmau-a-massive-multi-task-audio-understanding-and-reasoning-benchmark","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5719","title":{"rendered":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark\u00a0<\/strong>[44.7]<br>MMAU\u306f\u3001\u4eba\u9593\u306e\u6ce8\u91c8\u4ed8\u304d\u81ea\u7136\u8a00\u8a9e\u306e\u8cea\u554f\u3068\u56de\u7b54\u3068\u3092\u5408\u308f\u305b\u305f\u3001\u6ce8\u610f\u6df1\u304f\u7de8\u96c6\u3055\u308c\u305f10k\u306e\u30aa\u30fc\u30c7\u30a3\u30aa\u30af\u30ea\u30c3\u30d7\u3067\u69cb\u6210\u3055\u308c\u3066\u3044\u308b\u3002 \u3053\u308c\u306b\u306f\u3001\u60c5\u5831\u62bd\u51fa\u3068\u63a8\u8ad6\u306e\u8cea\u554f\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001\u30e2\u30c7\u30eb\u306f\u3001\u30e6\u30cb\u30fc\u30af\u3067\u56f0\u96e3\u306a\u30bf\u30b9\u30af\u306b\u307e\u305f\u304c\u308b27\u306e\u7570\u306a\u308b\u30b9\u30ad\u30eb\u3092\u5b9f\u8a3c\u3059\u308b\u5fc5\u8981\u304c\u3042\u308b\u3002 \u6211\u3005\u306f18\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u304a\u3088\u3073\u30d7\u30ed\u30d7\u30e9\u30a4\u30a8\u30bf\u30ea\u306aAudio-Language Model\u3092\u8a55\u4fa1\u3057\u3001MMAU\u304c\u3082\u305f\u3089\u3059\u91cd\u5927\u306a\u8ab2\u984c\u3092\u5b9f\u8a3c\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.19168v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.19168v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 24 Oct 2024 21:20:10 GMT)<\/li>\n\n\n\n<li>\u97f3\u58f0\uff08speech, sounds, music\uff09\u3092\u8ef8\u3068\u3057\u305f\u7406\u89e3\u30fb\u63a8\u8ad6\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002GPT-4o\u3001Gemini Pro  1.5\u306e\u6027\u80fd\u304c\u9ad8\u3081\u3060\u304c\u3001\u300cOur evaluations of 18 open-source and proprietary LALMs reveal that even the overall best model achieves only 59% accuracy on MMAU, highlighting the significant challenges it poses.\u300d\u3068\u306e\u3053\u3068\u3002\u4eba\u9593\u306e\u30b9\u30b3\u30a2\uff08\u7d0480%\uff09\u3068\u306e\u5dee\u3082\u5927\u304d\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/sakshi113.github.io\/mmau_homepage\/\">MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark<\/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":[491,517],"class_list":["post-5719","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-491","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5719","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=5719"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5719\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5719"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5719"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5719"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}