Problem
Research questions and friction points this paper is trying to address.
Diffusion language models
sequence length
unnecessary denoising steps
length predictor
Survival-Guided Length Control for Efficient Diffusion Language Models
🤖 AI Summary
研究通过将长度选择视为离散时间生存问题，并提出无需训练的长度预测器，解决了扩散语言模型中不必要的去噪步骤问题，提高了推理速度。
📝 Abstract
Diffusion language models (DLMs) generate text by iteratively denoising masked sequences, but standard decoding either fixes the sequence length or relies on ad hoc stopping rules, often leading to unnecessary denoising steps. We recast length selection as a discrete-time survival problem over the end-of-sequence token and propose a plug-in, training-free length predictor that can be added to any existing DLM. Across reasoning and code-generation benchmarks, survival-guided length decoding speeds up inference by up to 7 times while preserving task accuracy. We further find that predicted lengths vary widely even within the same dataset, making model performance sensitive to the chosen length.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Survival-Guided
Length Control
Diffusion Language Models
Inference Speedup
🔎 Similar Papers
No similar papers found.
