ViRA study: better visual representations help end-to-end driving, but target choice matters
OpenDriveLab · hf · 2026-10-16
OpenDriveLab and Southeast University present ViRA, a planner-agnostic visual representation alignment framework that keeps planner architecture and inference cost unchanged. Findings: (1) VFM-guided representations consistently improve driving across diverse planners, extending to zero-shot closed-loop evaluation; (2) the choice of VFM target significantly affects planning gains, with different planners benefiting from different VFMs; (3) auxiliary perception supervision reduces sensitivity to target selection, narrowing the EPDMS spread across five targets.
More from Research
- Hironobu Fujiyoshi publishes deck: from AI agents to Agentic Robotics — HirokatuKataoka · 2026-10-16
- Is math just a language? A debate on why LLMs are good at mathematics — LucaAmb · 2026-10-16
- Alibaba open-sources OpenGCUA, a full-stack generalist computer-use agent; +19.6 points on OSWorld-v2 across 8 models — Tongyi-MAI · 2026-10-16
- CoDA co-evolves simulation and robot policies via shared failure memory, lifting OOD success from 5.3% to 27.6% — PLAN-Lab · 2026-10-16
- willcb: higher-level behavior shaping via RL envs is 'almost practical' — willcb · 2026-10-16
- Cambridge NLIP seminar: Danae Sanchez Villegas on multimodal reasoning beyond final answers — nikaletras · 2026-10-16