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 ...

CAESAR is a unified framework for spatio-temporal scientific data reduction. The baseline model, CAESAR-V, is built on a variational autoencoder (VAE) with scale hyperpriors and super-resolution ...

Variational Autoencoders (VAEs) have proven to be powerful generative models in quantitative finance, capable of learning latent representations of market data and generating synthetic scenarios for ...