The importance of addressing fairness and bias in artificial intelligence (AI) systems cannot
be over-emphasized. Mainstream media has been awashed with news of incidents around …

Nowadays an ever-growing concerning phenomenon, the emergence of algorithmic biases
that can lead to unfair models, emerges. Several debiasing approaches have been …

Recently, one-stream trackers have achieved parallel feature extraction and relation
modeling through the exploitation of Transformer-based architectures. This design greatly …

Accurate 3D environmental perception is crucial for ensuring the safety of autonomous
vehicles. However, many existing point-based 3D object detection methods rely only on …

In various academic and applied domains including software engineering, lightweight
software applications can be facilitated by knowledge distillation, which involves the transfer …

Our everyday lives now heavily rely on artificial intelligence (AI) powered large language
models (LLMs). Like regular users, programmers are also benefiting from the newest large …

To achieve a fused image that contains rich texture details and prominent targets, we
present a progressive dual-branch infrared and visible image fusion network called …

The widespread use of large language models has brought up essential questions about the
potential biases these models might learn. This led to the development of several metrics …

In the last decade, the scientific community has witnessed the blooming and the massive
exploitation of deep neural networks (DNNs). This is fueled by multiple factors: the inherent …

Efficient compression of large language models is important for enhancing computational
efficiency and reducing the necessary virtual memory requirements for deployment in …