Abstract: Deep neural networks (DNNs) reveal significant robustness deficiencies due to their susceptibility to being misled by small and imperceptible adversarial ...

If you’re like me and countless others, you are spending January in a time of reflection. Whether it’s starting a New Year’s ...

Abstract: Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significant ...

Introduction Visual Hallucinations (VHs) (seeing things that others do not, or visions) are a common feature of psychosis, causing significant distress and disability. Services rarely ask about these ...