Striking an optimal balance between predictive performance and fairness continues to be a fundamental challenge in machine learning. In this work, we propose a post-processing framework that facilitates fairness-aware prediction by leveraging model ensembling. Designed to operate independently of any specific model internals, our approach is widely applicable across various learning tasks, model architectures, and fairness definitions. Through extensive experiments spanning classification, regression, and survival analysis, we demonstrate that the framework effectively enhances fairness while maintaining, or only minimally affecting, predictive accuracy.

However, much less effort has been devoted to exploring the adversarial robustness of pre-trained models.

Continual learning (CL) empowers pre-trained vision-language (VL) models to efficiently adapt to a sequence of downstream tasks.

However, current AI models often fail to retain this ability.

Extensive evaluations demonstrate that AMT yields significant improvements, up to 12.92% in

Diffusion models have significantly advanced the field of generative modeling.