#masked-diffusion-models2 articles

2 articles

AIBullisharXiv – CS AI · 5d ago7/103

🧠

On the Reasoning Abilities of Masked Diffusion Language Models

New research demonstrates that Masked Diffusion Models (MDMs) for text generation are computationally equivalent to chain-of-thought augmented transformers in finite-precision settings. The study proves MDMs can solve all reasoning problems that CoT transformers can, while being more efficient for certain problem classes due to parallel generation capabilities.

AIBullisharXiv – CS AI · Feb 275/106

🧠

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies

Researchers developed a learned scheduler for masked diffusion models (MDMs) in language modeling that outperforms traditional rule-based approaches. The new method uses a KL-regularized Markov decision process framework and demonstrated significant improvements, including 20.1% gains over random scheduling and 11.2% over max-confidence approaches on benchmark tests.