Towards training VQ-VAE models robustly!
-
Updated
Jul 14, 2025 - Python
Towards training VQ-VAE models robustly!
This project compares global and localized replacement strategies for mitigating explicit content, highlighting the diffused nature of discrete latent representations and the limitations of semantic code substitution.
Add a description, image, and links to the vector-quantized topic page so that developers can more easily learn about it.
To associate your repository with the vector-quantized topic, visit your repo's landing page and select "manage topics."