Deep neural networks (DNNs) typically have a single exit point that makes predictions by
running the entire stack of neural layers. Since not all inputs require the same amount of …

Recent research demonstrates that the nascent fine-tuning-as-a-service business model
exposes serious safety concerns--fine-tuning over a few harmful data uploaded by the users …

Deep neural network (DNN) is a promising technology for Internet of Visual Things (IoVT)
devices to extrct their visual information from unstructured data. However, it is hard to deploy …

Early Exit Neural Networks (EENNs) endow neural network architectures with auxiliary
classifiers to progressively process the input and make decisions at intermediate points of …

The emerging field of artificial intelligence of things (AIoT) is propelled by the remarkable
success of deep learning and hardware evolution, which has a significant impact on our …

This work addresses the need for a balanced approach between performance and efficiency
in scalable production environments for visually-rich document understanding (VDU) tasks …

Les réseaux neuronaux artificiels dynamiques à sortie anticipée (RNDSA) ont pour but de
réduire le coût des prédictions en sautant les couches les plus profondes du réseau pour …

Large Language Models (LLMs) have achieved remarkable success in serving end-users
with human-like intelligence. However, LLMs demand high computational resources …

Deep neural networks (DNNs) have been successfully applied in various fields. In DNNs, a
large number of multiply-accumulate (MAC) operations is required to be performed, posing …

In this paper, we focus on Dynamic Execution techniques that optimize the computation flow
based on input. This aims to identify simpler problems that can be solved using fewer …