Papers2

#semi-autoregressive decoding

dVoting: Fast Voting for dLLMs

Sicheng Feng, Zigeng Chen et al.Feb 12arXiv

Diffusion Large Language Models (dLLMs) can write many parts of an answer at once, not just left to right like usual chatbots.

#diffusion large language models#remasking#test-time scaling

Learning Unmasking Policies for Diffusion Language Models

Intermediate

Metod Jazbec, Theo X. Olausson et al.Dec 9arXiv

Diffusion language models write by gradually unmasking hidden words, so deciding which blanks to reveal next is a big deal for both speed and accuracy.

#diffusion language models#masked diffusion#unmasking policy