Farshad Sangari Abiz

Enhancing Interpretability of Sparse Latent Representations with Class Information

2025 · arXiv (Cornell University)

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially in high-dimensional spaces. To address this challenge, …