<ul><li>Handling complex environments in autonomous driving is a challenge due to the scarcity and diversity of extreme scenario datasets.</li><li>Current autonomous driving models struggle to manage corner cases, posing a significant safety risk.</li><li>VLM-C4L is a continual learning framework that enhances corner case datasets using Vision-Language Models (VLMs).</li><li>VLM-C4L enables incremental learning from diverse corner cases while preserving performance on routine scenarios.</li></ul>

VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous Driving

Discover more