Tag
This paper investigates when state adaptation during inference matters for masked diffusion language models (MDMs), organizing inference into five axes and showing that selective adaptation (using lightweight detectors to identify high-opportunity states) captures a large share of oracle gains, e.g., 56.9% of opportunity while adapting only the top 10% of states on LLaDA-8B constrained JSON filling.
This paper introduces a learnable control module trained via Group Relative Policy Optimization (GRPO) to optimize the generation order in multimodal masked diffusion models, achieving improvements in text-to-image alignment and multimodal understanding.