News

Google's Veo 3 can now create an 8-second video from a single image - how to try it
The latest iteration of Google's video-generating AI model, Veo 3, continues to evolve at a rapid clip.
Vidu updates Q1 AI video generation model to handle up to seven image inputs
Vidu AI, a generative artificial intelligence video platform developed by Chinese firm ShengShu Technology, today announced ...
IEEE4mon
Tree Variational Autoencoder for Code - IEEE Xplore
Autoencoder models of source code are an emerging alternative to autoregressive large language models with important benefits for genetic improvement of software. We hypothesize that encoder-decoder ...
IEEE1y
Hyperspectral Pixel Unmixing With Latent Dirichlet Variational Autoencoder - IEEE Xplore
We present a method for hyperspectral pixel unmixing. The proposed method assumes that 1) abundances can be encoded as Dirichlet distributions and 2) spectra of endmembers can be represented as ...
GitHub1y
GitHub - pourialaghayee/scVAG: scVAG: Unified Single-Cell Clustering via Variational-Autoencoder Integration with Graph Attention Autoencoder
scVAG is an innovative framework that integrates Variational Autoencoder (VAE) and Graph Attention Autoencoder (GATE) models for enhanced analysis of single-cell gene expression data. Built upon the ...
Semiconductor Engineering1y
Improving ML-Based Device Modeling Using Variational Autoencoder Techniques - Semiconductor Engineering
They can be particularly difficult to obtain in the semiconductor industry due to the complexity and expense of the device fabrication. In this article, we propose a self-augmentation strategy for ...
GitHub2y
GitHub - psipred/protein-vae: Variational autoencoder for protein sequences - add metal binding sites and generate sequences for novel topologies
This repository provides code to accompany the paper: Greener JG, Moffat L and Jones DT, Design of metalloproteins and novel protein folds using variational autoencoders, Scientific Reports 8:16189, ...