PyTorch Implementation of Autoregressive Vision Generative Models with Discrete Latent Variables
-
Updated
Jul 18, 2025 - Python
PyTorch Implementation of Autoregressive Vision Generative Models with Discrete Latent Variables
Implementation of a straight-through gradient wrapper to allow for discrete latent representations. Provides binary discretizer which maps hidden representations to {0, 1} and a learnable multi-value discretizer, which maps hidden activations to their closest value in a set of given size.
Add a description, image, and links to the discrete-latent-representations topic page so that developers can more easily learn about it.
To associate your repository with the discrete-latent-representations topic, visit your repo's landing page and select "manage topics."