The field of vision-language models and face image quality assessment is moving towards developing more robust and efficient methods. Researchers are focusing on improving the performance of vision-language models under noisy conditions and evaluating their robustness against various corruption types. There is also a growing interest in developing lightweight and efficient face image quality assessment methods that can be deployed in real-world applications. Noteworthy papers in this area include: Evaluating Robustness of Vision-Language Models Under Noisy Conditions, which presents a comprehensive evaluation framework to assess the performance of state-of-the-art vision-language models under controlled perturbations. VisMoDAl, a visual analytics framework designed to evaluate vision-language model robustness against various corruption types and identify underperformed samples to guide the development of effective data augmentation strategies.