AI 导读
2/ 变化之处：旧的 Cosmos 将工作拆分到多个独立模型——一个理解场景，一个生成视频，一个做可控仿真。 Cosmos 3 将所有能力融合进单一的 Mixture-of-Transformers，包含两个塔： → 一个推理器（VLM“大脑”） → 一个扩散生成器（“想象力”）
正文
2/ What changed: old Cosmos split the work across separate models — one to understand a scene, one to generate video, one for controlled simulation.
Cosmos 3 fuses everything into a single Mixture-of-Transformers with two towers:
→ a reasoner (the VLM "brain")
→ a diffusion generator (the "imagination")
来源：@kimmonismus · x.com