Diffusion LLMs lose accuracy fast at high parallelism; RePara trains two-token blocks and lifts GSM8K from 28.20 to 68.54
Diffusion language models lose much of their accuracy when committing many tokens per step, and RePara reinforces short consecutive token blocks with group-relative policy optimization, raising LLaDA's GSM8K accuracy at Diff#16 from JustGRPO's 28.20 to 68.54.