Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?
Visual foundation models (VFMs) are increasingly integrated into end-to-end autonomous driving for their powerful representations, yet it remains unclear when these representations improve driving performance. To investigate this question, we introduce ViRA, a planner-agnostic visual representation alignment framework that keeps the planner architecture and inference cost unchanged. Our study reveals three findings: (1) VFM-guided visual representations consistently improve driving performance across diverse end-to-end planners, with gains extending to zero-shot closed-loop evaluation. (2) The choice of VFM target matters for planning performance, and alignment to a different VFM can furt...
| Authors | Zihao Zhang, Haochen Tian, Tianyu Li et al. |
|---|---|
| Primary category | cs.RO |
| Published | 7 October 2026 |
| Last updated at source | 7 October 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Description: Visual foundation models (VFMs) are increasingly integrated into end-to-end autonomous driving for their powerful representations, yet it remains unclear when these representations improve driving performance. To investigate this question, → Visual foundation models (VFMs) are increasingly integrated into end-to-end autonomous driving for their powerful representations, yet it remains unclear when these representations improve driving performance. To investigate this question,
- 16 Oct 2026 Topics added cs.RO, cs.CV removed hf-daily-papers, visual foundation models, end-to-end autonomous driving, planner-agnostic visual representation alignment, zero-shot closed-loop evaluation, diffusion-based planner, auxiliary perception supervision, epdms
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.