Hierarchical Masked Diffusion Language Models
Predicts which masked positions should be filled first, then predicts their tokens with a hierarchy-aware diffusion model. Tests this ordering on text generation and Sudoku, where earlier solved cells can help determine later ones.
First public: · Added to this list: October 22, 2026
Explore this approach
Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.