L2D finetunes a small parallel diffusion path on a frozen pretrained LLM so that running more diffusion steps at inference monotonically improves task accuracy.
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
-
Large Language Models to Diffusion Finetuning
L2D finetunes a small parallel diffusion path on a frozen pretrained LLM so that running more diffusion steps at inference monotonically improves task accuracy.