Discrete Stochastic Localization lets a single trained network support an entire family of per-token SNR paths for discrete sequence generation, with masked diffusion as a special case, and improves MAUVE scores when fine-tuning pretrained checkpoints.
Information-theoretic diffusion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Semantic similarity between texts is measured by the Jeffreys divergence between the image distributions induced by conditioning a diffusion model on each text, computed via Monte-Carlo sampling of the reverse-time SDEs.
citing papers explorer
-
Discrete Stochastic Localization for Non-autoregressive Generation
Discrete Stochastic Localization lets a single trained network support an entire family of per-token SNR paths for discrete sequence generation, with masked diffusion as a special case, and improves MAUVE scores when fine-tuning pretrained checkpoints.
-
Conjuring Semantic Similarity
Semantic similarity between texts is measured by the Jeffreys divergence between the image distributions induced by conditioning a diffusion model on each text, computed via Monte-Carlo sampling of the reverse-time SDEs.