Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models
Selective state adaptation captures most masked-diffusion gains, including 56.9% of LLaDA-8B oracle opportunity.
1 stories, newest first · one card per story
Selective state adaptation captures most masked-diffusion gains, including 56.9% of LLaDA-8B oracle opportunity.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views