Preprint
Aug 2026
STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision
STAR-VLM is introduced, an automotive radar-supervised framework that enhances spatiotemporal VLMs with motion reasoning and metric velocity estimation for autonomous driving, and achieves state-of-the-art performance on both motion classification and metric velocity estimation.
Pou-Chun Kung, Aryaman Rao, U. Sahai et al.
· 0 citations