This thesis reports an empirical D3PM versus autoregressive comparison on WikiText-103, but the claimed speed advantage is unsupported because the speed numbers duplicate NLL values.
Towards tokenization evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Discrete Diffusion Models for Language Generation
This thesis reports an empirical D3PM versus autoregressive comparison on WikiText-103, but the claimed speed advantage is unsupported because the speed numbers duplicate NLL values.