IEEE

Fast Autoscheduling for Sparse ML Frameworks

Abstract: The rapid growth in the size of deep learning models strains the capabilities of dense computation paradigms. Leveraging sparse computation has become increasingly popular for training and ...
GitHub

CNN-AutoEncoder in pytorch

This is a pytorch implementation of the Muti-task Learning using CNN + AutoEncoder. Cifar10 is available for the datas et by default. You can also use your own dataset. epoch,train loss,train accuracy ...
IEEE

Prediction of Alzheimer's Disease using AlexNet and 3D Sparse Autoencoder CNNs

Abstract: He primary objective of this study is to develop robust Alzheimer's disease classifiers from limited structural MRI data using hybrid transfer learning approaches. We address data scarcity ...
GitHub

SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model

Important Note: This repository implements SVG-T2I, a text-to-image diffusion framework that performs visual generation directly in Visual Foundation Model (VFM) representation space, rather than ...