Abstract
Diffusion large language models (DLLMs) have the potential to enable fast text generation by decoding multiple tokens in parallel. However, in practice, their inference efficiency is constrained by the need for many refinement steps, while aggressively reducing the number of steps leads to a substantial degradation in generation quality. To alleviate this, we propose a trajectory self-distillation framework that improves few-step decoding by distilling the model's own generative trajectories. We incorporate Direct Discriminative Optimization (DDO), a reverse-KL objective that promotes mode-seeking distillation and encourages the student to concentrate on high-probability teacher modes. Across benchmarks, our approach consistently outperforms strong few-step baselines and standard training under tight step budgets. Although full-step decoding remains superior, we substantially narrow the gap, establishing a strong foundation towards practical few-step DLLMs. The source code is available at this https URL.
Abstract (translated)
扩散型大型语言模型（DLLM）具有通过并行解码多个标记来实现快速文本生成的潜力。然而，在实践中，其推理效率受到需要多次细化步骤的限制，而过于激进地减少这些步骤会导致生成质量大幅下降。为了缓解这一问题，我们提出了一种轨迹自我蒸馏框架，该框架通过提炼模型自身的生成轨迹来改进少步解码。我们引入了直接判别性优化（DDO），这是一种反向KL目标函数，它促进了模式寻求的蒸馏，并鼓励学生集中在高概率教师模式上。在各个基准测试中，我们的方法始终优于强大的少步基线和标准训练下的紧缩步骤预算。尽管全步解码仍然更优，但我们显著缩小了差距，为实用的少步DLLM建立了坚实的基础。源代码可在该链接获取。
URL
https://arxiv.org/abs/2602.12262
