NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning

TL;DR

NORD is a data-efficient vision-language-action model for autonomous driving that achieves competitive performance with less data and no reasoning annotations by addressing difficulty bias in policy optimization.

Contribution

NORD introduces a novel approach combining reduced data requirements with a modified policy optimization algorithm to improve autonomous driving models without reasoning overhead.

Findings

NORD performs competitively on Waymo and NAVSIM datasets.

It requires less than 60% of the data used by previous models.

It eliminates the need for dense reasoning annotations.

Abstract

Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1) massive dataset collection, and (2) dense reasoning annotations. In this work, we address both challenges with NORD (No Reasoning for Driving). Compared to existing VLAs, NORD achieves competitive performance while being fine-tuned on <60% of the data and no reasoning annotations, resulting in 3x fewer tokens. We identify that standard Group Relative Policy Optimization (GRPO) fails to yield significant improvements when applied to policies trained on such small, reasoning-free datasets. We show that this limitation stems from difficulty bias, which disproportionately penalizes reward signals from scenarios that produce high-variance rollouts within GRPO. NORD overcomes this by incorporating Dr. GRPO, a recent algorithm designed to mitigate difficulty bias in LLMs. As a result, NORD achieves competitive performance on Waymo and NAVSIM with a fraction of the training data and no reasoning overhead, enabling more efficient autonomous systems. Website: https://nord-vla-ai.github.io/