On the Reasoning Abilities of Masked Diffusion Language Models
ICLROral2026
TL;DR
We prove that masked text diffusion models are equivalent to padded looped transformers, can solve all problems that chain-of-thought transformers can, and are more efficient on certain problem classes due to their parallel generation mechanism.
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
chain-of-thought language model transformer diffusion efficient reasoning