UnMaskFork: Test-Time Scaling for Masked Diffusion Models

SakanaAILabs · x · 2026-07-04

Sakana AI introduced UnMaskFork, a test-time scaling framework for Masked Diffusion Language Models (MMDLM), which will be presented at ICML 2026.

Leveraging Monte Carlo Tree Search (MCTS), the method dynamically switches between multiple pretrained MDLMs for collaborative text generation, exploring diverse generation paths. It consistently outperforms standard Best-of-N and other tree search baselines on coding and mathematical reasoning tasks.

Original post →

More from Research

Research channel →