Score entropy loss enables discrete diffusion models (SEDD) that cut perplexity 25-75% versus prior diffusion methods and outperform GPT-2 on language modeling while supporting infilling and compute-quality tradeoffs.
org/CorpusID:2352990
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
Score entropy loss enables discrete diffusion models (SEDD) that cut perplexity 25-75% versus prior diffusion methods and outperform GPT-2 on language modeling while supporting infilling and compute-quality tradeoffs.