{"id":7213,"date":"2025-07-28T05:43:00","date_gmt":"2025-07-27T20:43:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7213"},"modified":"2025-07-27T12:04:20","modified_gmt":"2025-07-27T03:04:20","slug":"alphago-moment-for-model-architecture-discovery","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7213","title":{"rendered":"AlphaGo Moment for Model Architecture Discovery\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>AlphaGo Moment for Model Architecture Discovery&nbsp;<\/strong>[26.3]<br>AI\u7814\u7a76\u306e\u305f\u3081\u306e\u4eba\u5de5\u8d85\u77e5\u80fd\u306e\u6700\u521d\u306e\u5b9f\u8a3c\u3067\u3042\u308bAII-Arch\u3092\u7d39\u4ecb\u3059\u308b\u3002 ASI-Arch\u306f\u5b8c\u5168\u306b\u81ea\u5f8b\u7684\u306a\u30b7\u30b9\u30c6\u30e0\u3067\u3001AI\u304c\u72ec\u81ea\u306e\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u9769\u65b0\u3092\u5b9f\u884c\u3067\u304d\u308b\u3088\u3046\u306b\u3059\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u5236\u7d04\u3092\u63fa\u3055\u3076\u308b\u3002 \u6211\u3005\u306f2\u4e07\u6642\u9593\u306b\u308f\u305f\u3063\u30661,773\u500b\u306e\u81ea\u5f8b\u7684\u306a\u5b9f\u9a13\u3092\u884c\u3044\u3001106\u500b\u306e\u9769\u65b0\u7684\u306aSOTA(State-of-the-art)\u7dda\u5f62\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u3092\u767a\u898b\u3057\u307e\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2507.18074v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2507.18074v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 24 Jul 2025 03:57:27 GMT)<\/li>\n\n\n\n<li>ASI\u3092\u30bf\u30a4\u30c8\u30eb\u306b\u5165\u308c\u305f\u8208\u5473\u6df1\u3044\u8ad6\u6587\u3001\u300cASI-ARCH conducted 1,773 autonomous experiments over 20,000 GPU hours, culminating in the discovery of 106 innovative, state-of-the-art (SOTA) linear attention architectures.\u300d\u3068\u4e3b\u5f35\u3002\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/devneko.jp\/wordpress\/?p=6998\">Language Modeling by Language Models \u2013 arXiv\u6700\u65b0\u8ad6\u6587\u306e\u7d39\u4ecb<\/a>\u3068\u306e\u5dee\u7570\u3084\u3088\u308a\u5b9f\u7528\u30fb\u5927\u898f\u6a21\u306a\u30d1\u30e9\u30e1\u30fc\u30bf\u30fb\u30c7\u30fc\u30bf\u30fb\u8a08\u7b97\u30b3\u30b9\u30c8\u3067\u306e\u7d50\u679c\u304c\u6c17\u306b\u306a\u308b\u3002<\/li>\n\n\n\n<li>\u305d\u306e\u3046\u3061\u6700\u8fd1\u51fa\u3066\u3044\u305f\u4e0b\u8a18\u6210\u679c\u306e\u3088\u3046\u306a\u8907\u5408\u7684\u306a\u52b9\u7387\u5316\u307e\u3067\u6271\u3048\u308b\u3088\u3046\u306b\u306a\u308b\u306e\u3060\u308d\u3046\u304b\u3002<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/GAIR-NLP\/ASI-Arch\">GAIR-NLP\/ASI-Arch: AlphaGo Moment for Model Architecture Discovery.<\/a>\u3001<a href=\"https:\/\/gair-nlp.github.io\/ASI-Arch\/\">Neural Network Research Data Gallery<\/a><\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Scaling Linear Attention with Sparse State Expansion\u00a0<\/strong>[58.2]<br>\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u306f\u30012\u6b21\u8a08\u7b97\u3068\u7dda\u5f62\u30e1\u30e2\u30ea\u6210\u9577\u306b\u3088\u308b\u9577\u671f\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u30b7\u30ca\u30ea\u30aa\u306b\u82e6\u616e\u3057\u3066\u3044\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u60c5\u5831\u5206\u985e\u3068\u3057\u3066\u72b6\u614b\u66f4\u65b0\u3092\u6982\u5ff5\u5316\u3057,\u7dda\u5f62\u6ce8\u610f\u306e\u305f\u3081\u306e\u884c\u30b9\u30d1\u30fc\u30b9\u66f4\u65b0\u5b9a\u5f0f\u5316\u3092\u63d0\u6848\u3059\u308b\u3002 \u6b21\u306b\u3001\u30b9\u30d1\u30fc\u30b9\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u5185\u306b\u30b9\u30d1\u30fc\u30b9\u72b6\u614b\u62e1\u5f35(SSE)\u3092\u793a\u3057\u3001\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u72b6\u614b\u3092\u8907\u6570\u306e\u30d1\u30fc\u30c6\u30a3\u30b7\u30e7\u30f3\u306b\u62e1\u5f35\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2507.16577v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2507.16577v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 22 Jul 2025 13:27:31 GMT)<\/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":[16,356],"class_list":["post-7213","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-agi","tag-self-x"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7213","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=7213"}],"version-history":[{"count":2,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7213\/revisions"}],"predecessor-version":[{"id":7216,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7213\/revisions\/7216"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7213"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7213"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7213"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}