{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/bc0a8701-3bb6-4137-bd0b-8abb710172a1\" width=\"1280\" height=\"720\" title=\"AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause Tokens — 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/bc0a8701-3bb6-4137-bd0b-8abb710172a1/episode.poster.webp","title":"AbridgeKV: Compressing Long Reasoning into the KV Cache of Learned Pause Tokens","type":"video","version":"1.0","width":1280}