RynnWorld-Latent · 项目原始材料
核对原文摘录 · 2 段,支持 3 项资料
原阅读方向 / 一句话认识
We present RynnWorld-Latent, a cross-embodiment video world model that uses the 3D-grounded latent actions introduced by RynnLAM as a shared conditioning interface.材料说明的限制
Latent actions are inferred from observed visual transitions and may encode camera motion or appearance information as well as manipulation.