Meta’s New Open-Source SAM Audio AI Model Can Isolate Sounds From Audio Mixtures

Meta’s new SAM Audio AI model lets users isolate and edit sounds from mixed audio using text, visual or time prompts.
AZoSensors

AI Maps Heat Inside Steelmaking’s Critical Sintering Process Beds

The Temporal Fusion Transformer model provides near-real-time insights into sintering temperatures, addressing critical ...
IEEE

Double Discrete Variational Autoencoder for Epileptic EEG Signals Classification

Abstract: Electroencephalography (EEG) plays a key role in the clinical evaluation of epilepsy and provides strong support for treatment decisions. However, analyzing and decoding EEG recordings is a ...
GitHub

REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

We address a fundamental question: Can latent diffusion models and their VAE tokenizer be trained end-to-end? While training both components jointly with standard diffusion loss is observed to be ...
IEEE

Fundamental Investigation of Performance Degradation of Multimode Optical Fiber Imaging with Variational Autoencoder against Fiber Bending

Abstract: In multimode optical fiber imaging with variational autoencoder (VAE), deformation of the fiber after VAE training can significantly degrade image recovery performance. As a first step to ...