{"id":4423,"date":"2024-02-19T05:19:00","date_gmt":"2024-02-18T20:19:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4423"},"modified":"2024-02-19T05:19:00","modified_gmt":"2024-02-18T20:19:00","slug":"sora%e3%81%a8gemini-1-5","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4423","title":{"rendered":"SORA\u3068Gemini-1.5"},"content":{"rendered":"\n<p>\u5148\u9031\u8a71\u984c\u3068\u306a\u3063\u305f\u30cb\u30e5\u30fc\u30b9\u306b\u30c6\u30ad\u30b9\u30c8\u304b\u3089\u306e\u30d3\u30c7\u30aa\u751f\u6210\u30e2\u30c7\u30eb\u3067\u3042\u308bOpenAI\u306eSORA\u3001\u6975\u3081\u3066\u9577\u3044\u30c6\u30ad\u30b9\u30c8\u3092\u6271\u3048\u308bGoogle\u306eGemini 1.5\u304c\u3042\u308b\u3002\u4e21\u767a\u8868\u3068\u3082\u6280\u8853\u304c\u4e00\u6bb5\u9032\u5316\u3057\u305f\u611f\u304c\u3042\u308b\u3002<\/p>\n\n\n\n<p>Reka\uff08<a href=\"https:\/\/reka.ai\/reka-flash-an-efficient-and-capable-multimodal-language-model\/\">Reka Flash: An Efficient and Capable Multimodal Language Model &#8211; Reka AI<\/a>\uff09\u306e\u3088\u3046\u306a\u30c1\u30e3\u30ec\u30f3\u30b8\u30e3\u30fc\u3082\u51fa\u3066\u304d\u3066\u3044\u3066\u30cb\u30e5\u30fc\u30b9\u304c\u591a\u3044\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Video generation models as world simulators<\/strong><br>\u79c1\u305f\u3061\u306fAI\u306b\u3001\u52d5\u4f5c\u4e2d\u306e\u7269\u7406\u4e16\u754c\u3092\u7406\u89e3\u3057\u3001\u30b7\u30df\u30e5\u30ec\u30fc\u30c8\u3059\u308b\u3088\u3046\u306b\u6559\u3048\u3066\u3044\u307e\u3059\u3002\u30d3\u30c7\u30aa\u3068\u753b\u50cf\u306e\u6f5c\u5728\u30b3\u30fc\u30c9\u4e0a\u306e\u6642\u7a7a\u9593\u30d1\u30c3\u30c1\u3092\u6271\u3046\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u3092\u6d3b\u7528\u3057\u3066\u3044\u307e\u3059\u3002Sora\u306f\u3001\u8996\u899a\u7684\u54c1\u8cea\u3068\u30e6\u30fc\u30b6\u306e\u30d7\u30ed\u30f3\u30d7\u30c8\u3078\u306e\u56fa\u57f7\u3092\u7dad\u6301\u3057\u306a\u304c\u3089\u3001\u6700\u59271\u5206\u9593\u306e\u30d3\u30c7\u30aa\u3092\u751f\u6210\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u308b\u3002<\/li>\n\n\n\n<li><a href=\"https:\/\/openai.com\/sora\">Sora (openai.com)<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/openai.com\/research\/video-generation-models-as-world-simulators\">Video generation models as world simulators (openai.com)<\/a><\/li>\n\n\n\n<li>\u65e2\u5b58\u7814\u7a76\uff08\u4f8b\u3048\u3070<a href=\"https:\/\/devneko.jp\/wordpress\/?p=4341\">Lumiere \u2013 arXiv\u6700\u65b0\u8ad6\u6587\u306e\u7d39\u4ecb (devneko.jp)<\/a>\u3001<a href=\"https:\/\/lumiere-video.github.io\/\">Lumiere (lumiere-video.github.io)<\/a>\u3084<a href=\"https:\/\/magicvideov2.github.io\/\">MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation (magicvideov2.github.io)<\/a>\uff09\u3082\u3059\u3054\u304b\u3063\u305f\u304c\u3001\u672c\u4ef6\u306f\u751f\u6210\u53ef\u80fd\u306a\u52d5\u753b\u306e\u9577\u3055\u3068\u81ea\u7136\u3055\u3067\u304b\u306a\u308a\u9032\u3093\u3067\u3044\u308b\u5370\u8c61\u3002<\/li>\n<\/ul>\n\n\n\n<p><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Gemini 1.5: Unlocking multimodalunderstanding across millions of tokens ofcontext<\/strong><br>Gemini 1.5 Pro\u306f\u3001\u304d\u3081\u7d30\u304b\u3044\u60c5\u5831\u3092\u30ea\u30b3\u30fc\u30eb\u3057\u3066\u63a8\u8ad6\u3067\u304d\u308b\u8a08\u7b97\u52b9\u7387\u306e\u9ad8\u3044\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u6df7\u5408\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002\u30e2\u30c0\u30ea\u30c6\u30a3\u9593\u306e\u9577\u3044\u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u691c\u7d22\u30bf\u30b9\u30af\u306e\u307b\u307c\u5b8c\u74a7\u306a\u30ea\u30b3\u30fc\u30eb\u3092\u5b9f\u73fe\u3059\u308b\u3002Gemini 1.0 Ultra\u306e\u6700\u5148\u7aef\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u3001\u5e45\u5e83\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u6bd4\u8f03\u307e\u305f\u306f\u4e0a\u56de\u308b\u3002<\/li>\n\n\n\n<li>\u9577\u6587\u3092\u6271\u3048\u308b\u80fd\u529b\u304c\u9ad8\u304fTF-IDF\u00a0\u3067\u306e\u691c\u7d22\uff0bre rank\u3092\u884c\u3046\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u69cb\u6210\u3092\u3068\u3063\u305f\u5834\u5408\u3092\u5927\u304d\u304f\u8d85\u3048\u308b\u6027\u80fd\u3002\u305d\u3057\u3066\u3001\u65e7Twitter\u3067\u3082\u7d39\u4ecb\u3055\u308c\u3066\u3044\u305f\u300cWith only instructional materials (500 pages of linguistic documentation, a dictionary, and \u2248 400 parallel sentences) all provided in context, Gemini 1.5 Pro is capable of learning to translate from English to Kalamang, a language spoken by fewer than 200 speakers in western New Guinea in the east of Indonesian Papua2, and therefore almost no online presence.\u300d\u304c\u885d\u6483\u7684\u3002<\/li>\n\n\n\n<li><a href=\"https:\/\/storage.googleapis.com\/deepmind-media\/gemini\/gemini_v1_5_report.pdf\">gemini_v1_5_report.pdf (storage.googleapis.com)<\/a>\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/japan.googleblog.com\/2024\/02\/gemini-15.html\">Google Japan Blog: \u6b21\u4e16\u4ee3\u30e2\u30c7\u30eb\u3001 Gemini 1.5 \u3092\u767a\u8868 (googleblog.com)<\/a><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u5148\u9031\u8a71\u984c\u3068\u306a\u3063\u305f\u30cb\u30e5\u30fc\u30b9\u306b\u30c6\u30ad\u30b9\u30c8\u304b\u3089\u306e\u30d3\u30c7\u30aa\u751f\u6210\u30e2\u30c7\u30eb\u3067\u3042\u308bOpenAI\u306eSORA\u3001\u6975\u3081\u3066\u9577\u3044\u30c6\u30ad\u30b9\u30c8\u3092\u6271\u3048\u308bGoogle\u306eGemini 1.5\u304c\u3042\u308b\u3002\u4e21\u767a\u8868\u3068\u3082\u6280\u8853\u304c\u4e00\u6bb5\u9032\u5316\u3057\u305f\u611f\u304c\u3042\u308b\u3002 Reka\uff08Reka Fla &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=4423\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;SORA\u3068Gemini-1.5&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[223,510,667],"class_list":["post-4423","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm","tag-510","tag-667"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4423","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=4423"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4423\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4423"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4423"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4423"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}