{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/1fdbf079-1aa8-42b0-b8d3-402803ed03d1\" width=\"1280\" height=\"720\" title=\"COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation — 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/1fdbf079-1aa8-42b0-b8d3-402803ed03d1/episode.poster.webp","title":"COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation","type":"video","version":"1.0","width":1280}