{"id":5673,"date":"2024-10-30T05:53:00","date_gmt":"2024-10-29T20:53:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5673"},"modified":"2024-10-30T05:53:00","modified_gmt":"2024-10-29T20:53:00","slug":"taipan-efficient-and-expressive-state-space-language-models-with-selective-attention","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5673","title":{"rendered":"Taipan: Efficient and Expressive State Space Language Models with Selective Attention\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Taipan: Efficient and Expressive State Space Language Models with Selective Attention\u00a0<\/strong>[100.2]<br>\u81ea\u7136\u8a00\u8a9e\u51e6\u7406(NLP)\u306b\u304a\u3051\u308b\u9577\u6587\u8a00\u8a9e\u30e2\u30c7\u30ea\u30f3\u30b0\u306e\u8ab2\u984c Mamba\u306e\u3088\u3046\u306a\u6700\u8fd1\u306e\u30b9\u30c6\u30fc\u30c8\u30b9\u30da\u30fc\u30b9\u30e2\u30c7\u30eb(SSM)\u306f\u3001\u30e1\u30e2\u30ea\u4f7f\u7528\u91cf\u3092\u4e00\u5b9a\u306b\u6291\u3048\u308b\u4ee3\u66ff\u624b\u6bb5\u3092\u63d0\u4f9b\u3059\u308b\u304c\u3001\u5927\u898f\u6a21\u306a\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u5185\u691c\u7d22\u3092\u5fc5\u8981\u3068\u3059\u308b\u30bf\u30b9\u30af\u3067\u306f\u6027\u80fd\u304c\u52a3\u308b\u3002 \u6211\u3005\u306f,Mamba-2\u3068\u9078\u629e\u6ce8\u610f\u5c64(SAL)\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u65b0\u3057\u3044\u30cf\u30a4\u30d6\u30ea\u30c3\u30c9\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u3067\u3042\u308bTaipan\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u6211\u3005\u306e\u5b9f\u9a13\u306f\u3001\u69d8\u3005\u306a\u30b9\u30b1\u30fc\u30eb\u3084\u30bf\u30b9\u30af\u306b\u307e\u305f\u304c\u308b\u512a\u308c\u305f\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u793a\u3057\u3001\u3088\u308a\u52b9\u7387\u7684\u306a\u9577\u6587\u8a00\u8a9e\u30e2\u30c7\u30ea\u30f3\u30b0\u306e\u305f\u3081\u306e\u6709\u671b\u306a\u30bd\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u3092\u63d0\u4f9b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.18572v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.18572v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 24 Oct 2024 09:25:37 GMT)<\/li>\n\n\n\n<li>Mamba-2 + Selective Attention Layers\u306a\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u306e\u63d0\u6848\u3002Mamba\u3084Jamba\u3092\u8d85\u3048\u308b\u6027\u80fd\u3092\u4e3b\u5f35\u3002\u30cf\u30a4\u30d6\u30ea\u30c3\u30c9\u30a2\u30d7\u30ed\u30fc\u30c1\u304c\u6709\u671b\uff1f<\/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":[235],"class_list":["post-5673","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mamba"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5673","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=5673"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5673\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5673"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5673"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5673"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}