{"id":5977,"date":"2025-01-07T03:56:00","date_gmt":"2025-01-06T18:56:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5977"},"modified":"2025-01-07T03:56:00","modified_gmt":"2025-01-06T18:56:00","slug":"mulberry-empowering-mllm-with-o1-like-reasoning-and-reflection-via-collective-monte-carlo-tree-search","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5977","title":{"rendered":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search\u00a0<\/strong>[74.5]<br>\u52b9\u7387\u7684\u306a\u63a8\u8ad6\u30d1\u30b9\u63a2\u7d22\u3068\u5b66\u7fd2\u306e\u305f\u3081\u306e\u96c6\u5408\u30e2\u30f3\u30c6\u30ab\u30eb\u30ed\u6728\u63a2\u7d22(CoMCTS)\u3092\u63d0\u6848\u3059\u308b\u3002 \u6211\u3005\u306fMulberry-260k\u3092\u69cb\u7bc9\u3059\u308b\u3002Mulberry-260k\u306f\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u306a\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u3001\u5404\u8cea\u554f\u306b\u5bfe\u3057\u3066\u30ea\u30c3\u30c1\u3067\u660e\u793a\u7684\u3067\u660e\u78ba\u306b\u5b9a\u7fa9\u3055\u308c\u305f\u63a8\u8ad6\u30ce\u30fc\u30c9\u306e\u30c4\u30ea\u30fc\u3092\u6301\u3064\u3002 \u6211\u3005\u306f\u3001o1\u306e\u3088\u3046\u306a\u30b9\u30c6\u30c3\u30d7\u30d0\u30a4\u30b9\u30c6\u30c3\u30d7\u63a8\u8ad6\u3068\u30ea\u30d5\u30ec\u30af\u30b7\u30e7\u30f3\u6a5f\u80fd\u3092\u5099\u3048\u305fMLLM\u306e\u4e00\u9023\u306e\u30e2\u30c7\u30eb\u3067\u3042\u308bMulberry\u3092\u8a13\u7df4\u3059\u308b\u305f\u3081\u306b\u3001\u96c6\u5408SFT\u3092\u5b9f\u884c\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2412.18319v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2412.18319v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 24 Dec 2024 10:07:51 GMT)<\/li>\n\n\n\n<li>\uff08o1\u81ea\u4f53\u306f\u5229\u7528\u3057\u3066\u3044\u306a\u3044\u3068\u8a00\u308f\u308c\u3066\u3044\u308b\u304c\uff09o1 like\u306a\u30b7\u30b9\u30c6\u30e0\u3092\u4f5c\u308d\u3046\u3068\u3059\u308b\u3068\u8a71\u984c\u306b\u306a\u308b\u30e2\u30f3\u30c6\u30ab\u30eb\u30ed\u6728\u63a2\u7d22\u3092\u5bfe\u8c61\u3068\u3057\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/HJYao00\/Mulberry\">GitHub &#8211; HJYao00\/Mulberry<\/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":[232,283,491,517],"class_list":["post-5977","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-lrm","tag-o1","tag-491","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5977","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=5977"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5977\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5977"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5977"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5977"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}