Preprint
Oct 2026
Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?
ViRA is introduced, a planner-agnostic visual representation alignment framework that keeps the planner architecture and inference cost unchanged and develops ViRA-Diffusion, a diffusion-based planner trained without auxiliary perception supervision, which achieves 92.3 EPDMS on NAVSIM v2 navtest.
Zi-Hao Zhang, Hao-Chen Tian, Tianyu Li et al.
· 1 citation