نسخة أولية وصول مفتوح
D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VLA) policies often rely on the latest observation, and refreshing their visual context typically requires another costly vision-language model (VLM) pass. We present D$^ …