A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models

arXiv:2604.09921v1 Announce Type: new Abstract: Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on the tradeoff between speed and quality of individual samples; how to additionally ensure diversity across samples remains less well understood. In this work, we show that diversity can be increased by using softened, tempered versions of familiar confidence-based remasking heuristics, retaining their computational benefits and offering simple implementations. We motivate this approach by introducing an idealized formal model of fork tokens and studying the impact of remasking on the expected entropy at the forks. Empirically, the proposed tempered heuristics close the exploration gap (pass@k) between existing confidence-based and autoregressive sampling, hence outperforming both when controlling for cost (pass@NFE). We further study how the increase in diversity translates to downstream post-training and test-time compute scaling. Overall, our findings demonstrate that simple, efficient, and diverse sampling from dLLMs is possible.

Related

• Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
• Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards
• Diffusion Processes on Implicit Manifolds
• BADiff: Bandwidth Adaptive Diffusion Model
• Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs

Source: arXiv cs.LG | 2026-04-14