AI RESEARCH
LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
arXiv CS.CV
•
ArXi:2603.01928v2 Announce Type: replace While Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning, their reliance on explicit textual Chain-of-Thought (CoT) leads to semantic-perceptual decoupling and perceptual-symbolic conflicts. Recent shifts toward latent reasoning attempt to bypass these bottlenecks by thinking in continuous hidden space. However, without explicit intermediate constraints, standard latent CoT often operates as a physics-agnostic representation.