{"id":5609,"date":"2024-10-15T04:56:00","date_gmt":"2024-10-14T19:56:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5609"},"modified":"2024-10-15T04:56:00","modified_gmt":"2024-10-14T19:56:00","slug":"selu-self-learning-embodied-mllms-in-unknown-environments","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5609","title":{"rendered":"SELU: Self-Learning Embodied MLLMs in Unknown Environments"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>SELU: Self-Learning Embodied MLLMs in Unknown Environments\u00a0<\/strong>[35.6]<br>\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u306a\u5927\u8a00\u8a9e\u30e2\u30c7\u30eb(MLLM)\u306f\u3001\u5f37\u529b\u306a\u8996\u899a\u7684\u7406\u89e3\u3068\u610f\u601d\u6c7a\u5b9a\u80fd\u529b\u3092\u793a\u3057\u3066\u3044\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u5f37\u5316\u5b66\u7fd2\u306b\u304a\u3051\u308b\u30a2\u30af\u30bf\u30fc\u6279\u5224\u7684\u81ea\u5df1\u5b66\u7fd2\u30d1\u30e9\u30c0\u30a4\u30e0\u306b\u89e6\u767a\u3055\u308c\u305f,SELU\u3068\u547c\u3070\u308c\u308b\u65b0\u3057\u3044\u30a2\u30af\u30bf\u30fc\u6279\u5224\u7684\u81ea\u5df1\u5b66\u7fd2\u30d1\u30e9\u30c0\u30a4\u30e0\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.03303v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.03303v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 04 Oct 2024 10:40:11 GMT)<\/li>\n\n\n\n<li>\u300cWe propose a self-learning paradigm for embodied MLLMs, SELU, inspired by the actorcritic paradigm in reinforcement learning, which enables MLLMs to self-adapt to unknown environments.\u300d\u3068\u3044\u3046Self-X\u3067Embodied\u3068\u3044\u3046\u3068\u3066\u3082\u672a\u6765\u3092\u611f\u3058\u308b\u7814\u7a76\u3002<\/li>\n\n\n\n<li>\u74b0\u5883\u306b\u5bfe\u3059\u308bActor\u306b\u5bfe\u3057\u3066MLLM Critic\u304c\u8a55\u4fa1\u3059\u308b\u3068\u3044\u3046\u3001\u6700\u8fd1\u6d41\u884c\u308a\u306e\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3060\u304c\u3001Actor MLLM\u3068Clitic MLLM\u3092\u305d\u308c\u305e\u308cfine tuning\u3057\u3066\u3044\u304f\u3053\u3068\u306b\u7279\u5fb4\u304c\u3042\u308b\uff08\u540c\u3058MLLM\u3092\u4f7f\u3046SELU One\u3088\u308a\u512a\u308c\u3066\u3044\u308b\u3068\u306e\u3053\u3068\uff09<\/li>\n<\/ul>\n\n\n\n<p><\/p>\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":[84,125,343,356],"class_list":["post-5609","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-critic","tag-embodied","tag-robotic","tag-self-x"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5609","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=5609"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5609\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5609"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5609"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5609"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}