DLM-One: Diffusion Language Models for One-Step Sequence Generation
This addresses the efficiency bottleneck for researchers and practitioners using diffusion models in natural language processing, though it is incremental as it builds on existing diffusion methods.
The paper tackles the problem of slow inference in diffusion language models by proposing DLM-One, a one-step generation framework that achieves up to ~500x speedup while maintaining competitive performance on benchmark text generation tasks.
This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates the need for iterative refinement by aligning the scores of a student model's outputs in the continuous token embedding space with the score function of a pretrained teacher DLM. We investigate whether DLM-One can achieve substantial gains in sampling efficiency for language modeling. Through comprehensive experiments on DiffuSeq -- a representative continuous DLM -- we show that DLM-One achieves up to ~500x speedup in inference time while maintaining competitive performance on benchmark text generation tasks used to evaluate the teacher models. We further analyze the method's empirical behavior across multiple datasets, providing initial insights into its generality and practical applicability. Our findings position one-step diffusion as a promising direction for efficient, high-quality language generation and broader adoption of continuous diffusion models operating in embedding space for natural language processing.