Masked diffusion language models trained on 100M words match a hybrid GPT-BERT baseline on BabyLM tests, with a rare-word-focused masking variant.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Masked Diffusion Language Models with Frequency-Informed Training
Masked diffusion language models trained on 100M words match a hybrid GPT-BERT baseline on BabyLM tests, with a rare-word-focused masking variant.