{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/2b2b196c-df61-41e4-ab27-826a16508173\" width=\"1280\" height=\"720\" title=\"Long-term User Engagement Optimization through Model-agnostic Downstream Rewards 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://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/2b2b196c-df61-41e4-ab27-826a16508173/episode.poster.webp","title":"Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning","type":"video","version":"1.0","width":1280}