Efficient World Action Model Inference with Adaptive Intermediate States
World Action Models (WAMs) enable future-aware control by jointly modeling actions and environment dynamics. However, iterative diffusion or flow inference incurs substantial denoising latency. Prior inference state offers a natural opportunity for acceleration, yet changing planning contexts, observations, and interme...
Zhi-Nan Liu, Hao-Zhi Han, Ru-Ge Zhang et al.
· 0 citations