Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies
Vision-language-action (VLA) models are trained by imitation and capture what action to take but not why; adding causal reasoning improves manipulation, but current methods pay for it at inference time-generating reasoning tokens or rolling out predicted future states at every step, a cost that compounds over long hori...
A. Li, Zhuo Li, Zhe-Lin Yang et al.
· Cyber .. · 3 citations