Thinker-WM · 项目原始材料
核对原文摘录 · 3 段，支持 5 项资料
原阅读方向 / 一句话认识 / 输出什么
jointly models and generates RGB, metric depth, and robot action through a shared intermediate Unified Dynamics Transformer with modality-specific encoders and decoders.输入什么
RGB, depth, and action are modeled within the
same UDT, while a modality can either be generated from noise, provided as a
clean condition, or omitted from the computation.动作是否影响预测
clean action injected, prompt dropped