{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/f6784443-7603-4a64-9a70-b3673e91b4b8\" width=\"1280\" height=\"720\" title=\"Routing Policy Optimization for Online Diffusion Reinforcement Learning — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://montaan.com/","thumbnail_url":"https://montaan.com/media/episodes/f6784443-7603-4a64-9a70-b3673e91b4b8/episode.poster.webp","title":"Routing Policy Optimization for Online Diffusion Reinforcement Learning","type":"video","version":"1.0","width":1280}