TDLM reuses past denoiser states to speed diffusion language models
On LLaDA the added modules are about 0.84% of parameters and generation is up to 7.15 times faster.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
On LLaDA the added modules are about 0.84% of parameters and generation is up to 7.15 times faster.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views