Learned Unmasking Policies Improve Diffusion Language Model Efficiency
A 856K-parameter policy trained on trajectory-contraction targets achieves best accuracy-NFE frontier on LLaDA-8B-Instruct.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #unmasking
Study isolates what improves learned unmasking in diffusion language models
An 856K-parameter policy on LLaDA-8B-Instruct leads the accuracy–NFE frontier on GSM8K and largely transfers to Dream-7B-Instruct.