Abstract: Transformer-based diffusion models, dubbed Diffusion Transformers (DiTs), have achieved state-of-the-art performance in image and video generation tasks. However, their large model size and ...

Existing prompt learning methods, which are built upon CLIP models, leverage textual tokens as anchors to guide the learnable soft tokens. This guidance improves CLIP generalizations. However, these ...

Abstract: Vulnerability detection in source code has been a focal point of research in recent years. Traditional rule-based methods fail to identify complex and unknown vulnerabilities, leading to ...