改进扩散模型采样，小步生成也能高质量。
Guided Star-Shaped Masked Diffusion
- 用星型结构重设计生成流程，支持错误修正。
- 轻量微调单层后，小步生成质量显著提升。
- 适合需要快速生成的场景，如文本与代码生成。
预训练掩码扩散模型的性能常受限于不可逆的采样过程，在低步数生成中表现不佳。本文提出一种新型采样算法，可与预训练模型协同工作，仅需轻量级微调单层参数，即可显著提升样本质量和生成效率。该方法采用星型架构重构生成过程，天然支持误差修正；并通过可学习的重掩码调度器，智能识别并修复潜在错误。实验表明，该方法在少步数生成下表现突出。我们在文本和代码生成任务上进行了全面验证，结果优于或匹配现有方法。
原文摘要 · Abstract (English)
The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works with pre-trained models and, after a lightweight fine-tuning of a single layer, significantly improves sample quality and efficiency. Our method reformulates the generation process using a star-shaped paradigm, which inherently allows for error correction. To make this process effective, we augment it with a learnable re-masking scheduler that intelligently identifies and revises likely errors. This approach yields a substantial quality boost, particularly when using a small number of sampling steps. We extensively ablate key components of our approach and show its usability in different scenarios. In comprehensive experiments on text, and code generation, our sampling algorithm outperforms or matches existing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。