{"image_url":null,"published":"2025-02-01 15:30:35","blog_url":"https://ai-de-seikei.hatenablog.com/","blog_title":"AI\u3046\u3049\uff0d\uff0d\uff01(ai-wo-katsuyo-shitai !)","author_url":"https://blog.hatena.ne.jp/fanta_orange_grape/","description":"Titans: Learning to Memorize at Test Time https://arxiv.org/pdf/2501.00663 \u6982\u8981 Over more than a decade there has been an extensive research effort of how effectively utilize recurrent models and attentions. While recurrent models aim to compress the data into a fixed-size memory (called hidden state)\u2026","type":"rich","width":"100%","height":"190","version":"1.0","provider_name":"Hatena Blog","provider_url":"https://hatena.blog","author_name":"fanta_orange_grape","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fai-de-seikei.hatenablog.com%2Fentry%2F2025%2F02%2F01%2F153035\" title=\"\u8ad6\u6587\u300eTitans: Learning to Memorize at Test Time\u300f\u3092\u8aad\u3080\u3002(Transformer2)\u3002 - AI\u3046\u3049\uff0d\uff0d\uff01(ai-wo-katsuyo-shitai !)\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","title":"\u8ad6\u6587\u300eTitans: Learning to Memorize at Test Time\u300f\u3092\u8aad\u3080\u3002(Transformer2)\u3002","url":"https://ai-de-seikei.hatenablog.com/entry/2025/02/01/153035","categories":[]}