Preprint
Sep 2026
PRIME: Perception Feedback with Situational Memory Embeddings in VLA Models
Current Vision-Language-Action (VLA) models for autonomous driving operate primarily through feedforward inference across the perception--reasoning--planning hierarchy. While modern architectures maintain temporal recurrence within the perceptual module, early perception remains blind to downstream reasoning and naviga...
Erik Deinzer, Naya Baslan, L. Paparusso et al.
· 0 citations