{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/bcc98066-c23f-4b76-88db-2021882e32d9\" width=\"1280\" height=\"720\" title=\"Not Another Text Benchmark: Putting the &quot;Visual&quot; Back in Visual Question Answering for Large Video Models — 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/bcc98066-c23f-4b76-88db-2021882e32d9/episode.poster.webp","title":"Not Another Text Benchmark: Putting the \"Visual\" Back in Visual Question Answering for Large Video Models","type":"video","version":"1.0","width":1280}