{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":480,"html":"<iframe src=\"https://montaan.com/embed/episode/cf952683-af5f-42ac-8fdd-5ebaa91a43c7\" width=\"1280\" height=\"480\" title=\"Visual Token Coding for Video Multimodal Large Language 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/cf952683-af5f-42ac-8fdd-5ebaa91a43c7/episode.poster.webp","title":"Visual Token Coding for Video Multimodal Large Language Models","type":"rich","version":"1.0","width":1280}