Revision History
VQ-VAE (Vector Quantized Variational Autoencoder) · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected the claim that the original 2017 VQ-VAE used a self-attention (PixelSNAIL-style) prior; that prior arrived with VQ-VAE-2, and the original used a plain PixelCNN (plus 3 minor fixes)
Version 6 · Nov 5, 2026, 12:07 PM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:12 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 04:03 PM
- Render formulas with LaTeX math notation
Version 3 · Jul 12, 2026, 12:36 AM