Achieving high reliability in AI systems—such as autonomous vehicles that stay on course even in snowstorms or medical AI that can diagnose cancer from low-resolution images—depends heavily on model ...

Abstract Model robustness indicates a model's capability to generalize well on unforeseen distributional shifts, including data corruptions and ...

Artificial intelligence (AI) is increasingly prevalent, integrated into phone apps, search engines and social media platforms as well as supporting myriad research applications. Of particular interest ...