{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/cef79687-1ce0-4d81-a90c-eaa3e3d63d3b\" width=\"1280\" height=\"720\" title=\"Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs — 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/cef79687-1ce0-4d81-a90c-eaa3e3d63d3b/episode.poster.webp","title":"Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs","type":"video","version":"1.0","width":1280}