Abstract The integration of Deep Learning (DL) algorithms in Autonomous Vehicles (AVs)
has revolutionized their precision in navigating various driving scenarios, ranging from anti …

JPEG remains one of the most widespread lossy image coding methods. However, the non-
differentiable nature of JPEG restricts the application in deep learning pipelines. Several …

On-device ML is increasingly used in different applications. It brings convenience to offline
tasks and avoids sending user-private data through the network. On-device ML models are …

We propose a demonstration-efficient strategy to compress a computationally expensive
Model Predictive Controller (MPC) into a more computationally efficient representation …

In recent years, various domains have been influenced by the rapid growth of machine
learning. Autonomous driving is an area that has tremendously developed in parallel with …

In the past five years, research has shifted from traditional Machine Learning (ML) and Deep
Learning (DL) approaches to leveraging Large Language Models (LLMs), including …

With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks,
recent literature have proposed various variants of vanilla ViTs to achieve better efficiency …

In recent years, there has been a significant increase in the development of autonomous
vehicles. One critical task for ensuring their safety and dependability, is obstacle avoidance …

We present a Body Measurement network (BMnet) for estimating 3D anthropomorphic
measurements of the human body shape from silhouette images. Training of BMnet is …

Vision Transformer (ViT) variants have made rapid advances in a variety of computer vision
tasks. However, their performance on corrupted inputs, which are inevitable in realistic use …