The field of autonomous driving and vehicle design is rapidly evolving with the integration of advanced technologies such as vision-language models and point cloud data. Researchers are exploring innovative approaches to enhance the safety and efficiency of cooperative autonomous driving, including the development of frameworks that leverage real-world LiDAR datasets and few-shot learning capabilities. Additionally, there is a growing interest in using deep learning-based methods to evaluate aerodynamic performance, with a focus on improving prediction accuracy and reducing the time and cost required for traditional computational fluid dynamics simulations. Noteworthy papers include:

• A study that introduces a novel framework for point cloud-based vehicle classification using vision-language models, which demonstrates encouraging performance and potential to reduce annotation efforts.
• A proposal of a point cloud learning framework called DrivAer Transformer, which enables fast and accurate drag prediction and is expected to accelerate the vehicle design process.