arXiv AI
Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 30
CAR-VLA: Complexity-Aware and Risk-Adaptive Reasoning for Autonomous Driving
CAR‑VLA is a Vision‑Language‑Action model for autonomous driving that jointly considers scene complexity and dynamic risk to determine reasoning depth, urgency, and focus. It maps four complexity‑risk categories to three reasoning modes—Fast Intuition, Slow Thinking, and Reflex Response—each tailored to different driving scenarios. The model is trained via progressive supervised learning and reinforcement learning, achieving competitive performance on NAVSIM and Navhard benchmarks and demonstrating risk‑aware reasoning in high‑risk scenarios.
arXiv AI
Jul 3
DriveVLM-RL: Neuroscience-Inspired Reinforcement Learning with Vision-Language Models for Safe and Deployable Autonomous Driving
arXiv:2603. 18315v2 Announce Type: replace-cross Abstract: Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse collision signals, which fail to capture the rich contextual understanding required for safe driving and make unsafe exploration unavoidable in real-world settings.
arXiv Computer Vision
Sep 30
Speed in the Blind Spot: An Interpretability Analysis of Dynamic Perception in VLMs for Autonomous Driving
Vision‑Language Models (VLMs) used in autonomous driving are evaluated on their ability to understand velocity through three tasks: surrounding‑agent speed, current ego speed, and short‑horizon future ego‑speed. Experiments on nuScenes show that while current ego speed can be accessed internally, verbal outputs are poor and surrounding‑agent speed is weakly encoded; temporal cues and frame order are largely ignored. Specialized driving models (Alpamayo‑1.5) improve latent speed representations but still leave gaps between internal knowledge and verbal readout, indicating that good planning outputs do not guarantee reliable dynamic state recovery.
arXiv Computer Vision
Oct 26
SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
arXiv:2610.31835v1 Announce Type: new Abstract: Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a...
arXiv AI
Jul 21
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
arXiv:2607. 16938v1 Announce Type: cross Abstract: End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation.
Hugging Face Trending Papers
Jul 18
What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning
End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation. Yet the internal logic of these safety-critical systems remains largely opaque, due to the complexity of traffic scenes.