Abstract: This paper tackles the problem of class-conditional generation for spatial data represented as unordered sets of graph-structured nodes. Each node encodes spatial coordinates and activation ...
This repository provides the code for training and evaluating a Conditional Variational Autoencoder (CVAE) with multi-head attention on an image dataset. The project demonstrates the process of ...
Abstract: We introduce a Conditional Variational Autoencoder (CVAE) surrogate for exoplanet spectral modeling, trained on a wide grid of synthetic spectra spanning key planetary regimes. By tuning ...
"""**3 A dataset of zeolite structures were assembled from crystallographic information files (CIFs). Each CIF describes a periodic framework with a fixed lattice and atomic positions. The structures ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results