Structured state-space regularization induces spectral structure in image tokenizer latent spaces via an SSM-derived objective, improving generative performance with minimal reconstruction loss.
Advances in Neural Information Processing Systems37, 56424–56445 (2024)
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
-
Structured State-Space Regularization for Generation-Friendly Image Tokenization
Structured state-space regularization induces spectral structure in image tokenizer latent spaces via an SSM-derived objective, improving generative performance with minimal reconstruction loss.