In this work we show that the size versus accuracy trade-off of neural network quantization
can be significantly improved by increasing the quantization dimensionality. We propose the …

Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised learning
(SSL) method that has shown promising results on a variety of tasks. However, the …

Abstract Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised
learning (SSL) method that has shown promising results on a variety of tasks. However, the …

Data-driven artificial intelligence (AI) models have made significant advancements in
weather forecasting, particularly in medium-range and nowcasting. However, most data …

The Diffusion Transformers Models (DiTs) have transitioned the network architecture from
traditional UNets to transformers, demonstrating exceptional capabilities in image …

This work focuses on the efficient quantization of convolutional neural networks (CNNs).
Specifically, we introduce a method called non-uniform uniform quantization (NUUQ), a …

Deep convolutional neural networks have a large number of parameters and require a
significant number of floating-point operations during computation, which limits their …

While post-training quantization receives popularity mostly due to its evasion in accessing
the original complete training dataset, its poor performance also stems from scarce images …

Internet of Things (IoT) systems provide large amounts of data on all aspects of human
behavior. Machine learning techniques, especially deep neural networks (DNN), have …

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is
ubiquitous to achieve the trade-off between model predictive performance and efficiency …