Abstract: Deep generative models such as the generative adversarial network (GAN) and the variational autoencoder (VAE) have obtained increasing attention in a wide variety of applications.

A computational method combining generative AI with atomistic simulations can identify promising platinum alloy catalyst structures for hydrogen fuel cells, report researchers from Science Tokyo.

DeSCOPE is a single-cell perturbation prediction framework designed for scRNA-seq, scATAC-seq, and general single-cell–level perturbation modeling. It is built on a conditional Variational Autoencoder ...

Additional visualizations highlighting the comparison between the proposed two-stage AG-VQ-VAE network (without skip connections) and the single-stage AG-UNet (with skip connections) are presented.

CatDRX is a generative AI framework developed at Institute of Science Tokyo, which enables the design of new chemical catalysts based on the specific chemical reactions in which they are used. The ...

Abstract: We present a variational autoencoder (VAE) learning framework with introspective training for conditional image synthesis, and explore conditional capsule encoder by class-wise mask label ...

Developing models for identifying mild traumatic brain injury (mTBI) has often been challenging due to large variations in data from subjects, resulting in difficulties for the mTBI-identification ...