{"blog_title":"fltech - \u5bcc\u58eb\u901a\u7814\u7a76\u6240\u306e\u6280\u8853\u30d6\u30ed\u30b0","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fblog.fltech.dev%2Fentry%2F2023%2F04%2F19%2Ftoronto-iclr2023-paper-en\" title=\"\u201cMulti-Rate VAE: Train Once, Get the Full Rate-Distortion Curve\u201d accepted at ICLR2023 as notable-top-5%  - fltech - \u5bcc\u58eb\u901a\u7814\u7a76\u6240\u306e\u6280\u8853\u30d6\u30ed\u30b0\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_url":"https://blog.fltech.dev/","categories":["AI"],"author_name":"fltech","type":"rich","title":"\u201cMulti-Rate VAE: Train Once, Get the Full Rate-Distortion Curve\u201d accepted at ICLR2023 as notable-top-5% ","description":"Recently, in our joint research with the University of Toronto, we have developed an AI technology called Multi-Rate VAE (MR-VAE), enabling the acquisition of the full rate-distortion curve by only a single training run. We will present our work at ICLR 2023 (notable-top-5%). In this blog post, we i\u2026","width":"100%","url":"https://blog.fltech.dev/entry/2023/04/19/toronto-iclr2023-paper-en","provider_url":"https://hatena.blog","author_url":"https://blog.hatena.ne.jp/fltech/","published":"2023-04-19 09:00:00","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/f/fltech/20230417/20230417073429.png","provider_name":"Hatena Blog","version":"1.0","height":"190"}