LaLa-World: Scaling Latent World Models with Natural Language Actions
机器人世界模型研究，未放权重，无法用于视频生成
This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the language-conditioned interface of video generation models. We establish this approach as an effective and efficient basis for planning with imagination an
判断口径 agnes-3.0-flash · 入库 #2237 · 回首页