vla-4d-spatiotemporal

【效率与协作】Enhance VLA models with spatiotemporal awareness by embedding both 3D spatial coordinates and temporal sequences: predict actions that include temporal parameters (duration) alongside spatial movements, achieving 97.4% robotic manipulation success by grounding reasoning in coherent 4D representations.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准