News

VoxelMatters2d
Sparc3D introduces next-gen high-resolution 3D model generation
Explore how Sparc3D transforms 2D images into detailed 3D models with AI-powered efficiency and precision. Discover more.
Frontiers1mon
Integrating multi-source monitoring data and deep convolutional autoencoder technology for slope failure pattern recognition - Frontiers
Integrating multi-source monitoring data and deep convolutional autoencoder ... the validation set, and 142 samples as the test set. The model was trained for 500 epochs with a batch size of 8. The ...
GitHub1mon
Tro-fish/Decoding-Dense-Embeddings: Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval - GitHub
Overview of our method. We first train a SAE to decompose dense embeddings into latent concepts. Given a query or a passage, the SAE encoder sparsely activates latent concepts, which are mapped to ...
IEEE1mon
AlphaGrad: Normalized Gradient Descent for Adaptive Multi-loss Functions in EEG-based Motor Imagery Classification - IEEE Xplore
In this study, we propose AlphaGrad, a novel adaptive loss blending strategy for optimizing multi-task learning (MTL) models in motor imagery (MI)-based electroencephalography (EEG) classification.
IEEE1mon
Numerical Analysis of Sparse-Array Metasurface Antennas using Gaussian Basis Functions - IEEE Xplore
A sparse-array metasurface (MTS) antenna corresponds to a continuously modulated sheet impedance on top of a grounded slab, periodically repeated over many unit cells (with a few wavelengths cell size ...