arxivcs.CV2026-06-30
Reasoning-aware Speculative Decoding for Efficient Vision-Language-Action Models in Autonomous Driving
Anh Dung Dinh, Simon Khan, Flora Salim
Modern Vision-Language-Action (VLA) planners for autonomous driving emit a chain-of-causation (CoC) reasoning step \emph{before} producing a trajectory. The reasoning is autoregressive and dominates inference latency, while the trajectory head is parallel and cheap. Latency is an…