{"height":"190","width":"100%","provider_url":"https://hatena.blog","author_url":"https://blog.hatena.ne.jp/BioErrorLog/","provider_name":"Hatena Blog","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fen.bioerrorlog.work%2Fentry%2Fnvidia-cosmos-policy-paper\" title=\"Understanding How NVIDIA Cosmos Policy Works | Paper: Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning - BioErrorLog Tech Blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_url":"https://en.bioerrorlog.work/","blog_title":"BioErrorLog Tech Blog","version":"1.0","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/B/BioErrorLog/20260308/20260308155126.png","title":"Understanding How NVIDIA Cosmos Policy Works | Paper: Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","published":"2026-03-11 22:04:43","type":"rich","categories":["Physical AI","AI","LLM","Papers"],"description":"These are my reading notes on the NVIDIA Cosmos Policy paper, \"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning.\" Introduction Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning Background Method Latent Frame Injection Joint Training of Policy, Wor\u2026","url":"https://en.bioerrorlog.work/entry/nvidia-cosmos-policy-paper","author_name":"BioErrorLog"}