Personal data from more than 64 million McDonald’s job applicants was exposed after a basic coding flaw in an AI-powered ...
Abstract: Recently, new paradigms of camouflaged object detection (COD), such as referring COD (Ref-COD) and collaborative COD (Co-COD), have been proposed to enhance task performance. However, there ...
Abstract: Large Vision-Language Models (LVLMs) suffer from severe object hallucinations, leading them to frequently generate outputs that do not correspond to the image content, significantly reducing ...