SOURCE-LINKED INTELLIGENCE

Reasoning Without Inference Cost: Latent Semantic Scaffolding for Robot VLA Policies

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

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 horizons. We ask whether this benefit can instead be captured during training and discarded before deployment. We introduce Latent Semantic Scaffolding (LSS), an auxiliary loss applied during human-demonstration pretraining that aligns a VLA's action-token representations to text e

Read original source ↗ Open in workspace

recordType

paper

region

Global