GitHub

SVG: Latent Diffusion Model without Variational Autoencoder

SVG Autoencoder - Uses a frozen representation encoder with a residual branch to compensate the information loss and a learned convolutional decoder to transfer the SVG latent space to pixel space.
eLife

Reconstructing Voice Identity from Noninvasive Auditory Cortex Recordings

Revised: This Reviewed Preprint has been revised by the authors in response to the previous round of peer review; the eLife assessment and the public reviews have been updated where necessary by the ...
IEEE

Emotional Regularization of the Latent Space of a Variational Autoencoder for Generating Musical Sequences

Abstract: This article presents a new regularization of the latent space of a variational autoencoder that facilitates the visual selection of specific emotions of generated monophonic musical ...
Morningstar

Variational AI Enters Collaboration with Merck to Apply Generative AI to Drug Discovery

Variational AI, Inc., a generative AI drug discovery company, today announced a collaboration with Merck, known as MSD outside of the United States and Canada, to apply Variational AI’s Enki™ platform ...
IEEE

Latent Space Bayesian Parameter Topology Optimization of Permanent Magnet Synchronous Motors via a Variational Autoencoder

Abstract: This study introduces a novel approach that combines a variational autoencoder and Bayesian optimization to accelerate the simultaneous parameter and topology optimization of interior ...
Scientific Research Publishing

Duan, J., Wang, C., Li, Y., & Zhang, X. (2022). Dynamic Latent Factor Modeling with Variational Autoencoders. Journal of Financial Data Science, 4, 10-28.

ABSTRACT: Accurate measurement of time-varying systematic risk exposures is essential for robust financial risk management. Conventional asset pricing models, such as the Fama-French three-factor ...
Scientific Research Publishing

Chen, Li, X., Grosse, R., & Duvenaud, D. (2018). Isolating Sources of Disentanglement in Variational Autoencoders. arXiv: 1802.04942.

ABSTRACT: Accurate measurement of time-varying systematic risk exposures is essential for robust financial risk management. Conventional asset pricing models, such as the Fama-French three-factor ...
GitHub

Dynamical Dual Latent Space Variational Autoencoder Model with Koopman Constraint for Semi-Supervised Soft Sensor Application

├── data_pre/ # Data preprocessing modules │ ├── data_pre.py # Data preprocessing script │ └── dataset.py # Dataset class definition ├── dataset/ # Data directory │ ├── SRU_data.npy # Process data in ...