نسخة أولية وصول مفتوح
WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models
World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT). In closed-loop control, the video DiT runs at every chunk to encode the current observation into layerwise key-value (KV) pairs that the action expert …