MergeTok unifies VAE and VQ tokenizers via token merging to impose semantic alignment on continuous latents and stabilize discrete codebook training, achieving lower rFID on ImageNet-256.
Vaevq: Enhancing discrete visual tokenization through variational modeling.ArXiv, abs/2511.06863, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
MergeTok unifies VAE and VQ tokenizers via token merging to impose semantic alignment on continuous latents and stabilize discrete codebook training, achieving lower rFID on ImageNet-256.