{"id":5665,"date":"2024-10-28T05:30:00","date_gmt":"2024-10-27T20:30:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5665"},"modified":"2024-10-28T05:30:00","modified_gmt":"2024-10-27T20:30:00","slug":"scaling-diffusion-language-models-via-adaptation-from-autoregressive-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5665","title":{"rendered":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Scaling Diffusion Language Models via Adaptation from Autoregressive Models\u00a0<\/strong>[105.7]<br>\u62e1\u6563\u8a00\u8a9e\u30e2\u30c7\u30eb(DLM)\u306f\u3001\u30c6\u30ad\u30b9\u30c8\u751f\u6210\u30e2\u30c7\u30eb\u306e\u305f\u3081\u306e\u5c06\u6765\u6027\u306e\u3042\u308b\u65b0\u3057\u3044\u30d1\u30e9\u30c0\u30a4\u30e0\u3068\u3057\u3066\u767b\u5834\u3057\u305f\u3002 170M\u304b\u30897B\u307e\u3067\u306eAR\u30e2\u30c7\u30eb\u3092DiffuGPT\u3068DiffuLLaMA\u306e\u62e1\u6563\u30e2\u30c7\u30eb\u306b\u5909\u63db\u3057\u3001200B\u672a\u6e80\u306e\u30c8\u30fc\u30af\u30f3\u3067\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3067\u304d\u308b\u3053\u3068\u3092\u793a\u3059\u3002 \u5b9f\u9a13\u306e\u7d50\u679c,\u3053\u308c\u3089\u306e\u30e2\u30c7\u30eb\u306f\u521d\u671f\u306eDLM\u3088\u308a\u3082\u512a\u308c\u3066\u304a\u308a,AR\u3068\u7af6\u5408\u3057\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u3063\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.17891v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.17891v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 23 Oct 2024 14:04:22 GMT)<\/li>\n\n\n\n<li>\u300cBuilding on existing DLMs, we present a recipe for scaling DLMs by continuing training on off-the shelf autoregressive LLMs.\u300d\u3001Diffusion Language Model\u304c\u6709\u671b\u304b\u306f\u8b70\u8ad6\u304c\u5206\u304b\u308c\u308b\u3068\u3053\u308d\u3060\u3068\u306f\u601d\u3046\u304c\u9762\u767d\u3044\u624b\u6cd5\u3002DiffuLLaMA\u306fautoregressive model\u3068\u7af6\u5408\u3059\u308b\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/HKUNLP\/DiffuLLaMA\">GitHub &#8211; HKUNLP\/DiffuLLaMA: DiffuGPT and DiffuLLaMA: Scaling Diffusion Language Models via Adaptation from Autoregressive Models<\/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":[114,223],"class_list":["post-5665","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-diffusion-model","tag-llm"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5665","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=5665"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5665\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5665"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5665"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5665"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}