Contents

CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving

WACV 2025, Oral Turing Inc. arXiv 2408.10845 Hugging Faceturing-motors/CoVLA-Dataset covla-ad

TL;DR

Motivations & Innovations

CoVLA-Dataset

Raw Data Collection

Data Sampling

Auto Labeling

Auto Captioning

Approach

Model

./images/index-20260330114204.webp

Training Recipe

Data Recipe

Experiments