Monotonicity constraints represent a vital form of prior knowledge in machine learning, particularly within classification tasks where a natural ordering exists among class labels. In such contexts, ...

Self-supervised models generate implicit labels from unstructured data rather than relying on labeled datasets for supervisory signals. Self-supervised learning (SSL), a transformative subset of ...

Although large language models (LLMs) possess extensive world knowledge and strong reasoning capabilities, and are widely regarded as excellent few-shot learners, they still exhibit significant ...

Scene classification remains a central challenge in computer vision, requiring models to capture both the local structure and global context of visual environments. As scene understanding grows ...