DLM-One: Diffusion Language Models for One-Step Sequence Generation

• URL: http://arxiv.org/abs/2506.00290v1
• Date: Fri, 30 May 2025 22:42:23 GMT
• Title: DLM-One: Diffusion Language Models for One-Step Sequence Generation
• Authors: Tianqi Chen, Shujian Zhang, Mingyuan Zhou,
• Abstract summary: DLM-One is a score-distillation-based framework for one-step sequence generation with continuous diffusion language models.<n>We investigate whether DLM-One can achieve substantial gains in sampling efficiency for language modeling.
• Score: 63.43422118066493
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Discrete Diffusion in Large Language and Multimodal Models: A Survey [56.31088116526825]
  We provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs)<n>Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel decoding paradigm.<n>We trace the historical development of dLLMs and dMLLMs, formalize the underlying mathematical frameworks, and categorize representative models.
  arXiv  Detail & Related papers  (2025-06-16T17:59:08Z)
• Enhanced Continual Learning of Vision-Language Models with Model Fusion [16.764069327701186]
  Vision-Language Models (VLMs) represent a breakthrough in artificial intelligence.<n>VLMs are susceptible to catastrophic forgetting when sequentially fine-tuned on multiple downstream tasks.<n>We propose Continual Decoupling-Unifying (ConDU), a novel approach, by introducing model fusion into continual learning.
  arXiv  Detail & Related papers  (2025-03-12T15:48:13Z)
• Multimodal Latent Language Modeling with Next-Token Diffusion [111.93906046452125]
  Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video)<n>We propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers.
  arXiv  Detail & Related papers  (2024-12-11T18:57:32Z)
• Comparing Discrete and Continuous Space LLMs for Speech Recognition [46.70297458685438]
  This paper investigates discrete and continuous speech representations in Large Language Model (LLM)-based Automatic Speech Recognition (ASR) We classify LLMs based on their input and autoregressive feedback into continuous and discrete-space models. We present an open-sourced achievement of a state-of-the-art Word Error Rate (WER) of 1.69% on LibriSpeech using a HuBERT encoder.
  arXiv  Detail & Related papers  (2024-09-01T18:29:45Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors.<n>We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• SLMRec: Distilling Large Language Models into Small for Sequential Recommendation [38.51895517016953]
  Sequential Recommendation task involves predicting the next item a user is likely to interact with, given their past interactions.<n>Recent research demonstrates the great impact of LLMs on sequential recommendation systems.<n>Due to the huge size of LLMs, it is inefficient and impractical to apply a LLM-based model in real-world platforms.
  arXiv  Detail & Related papers  (2024-05-28T07:12:06Z)
• Diffusion Language Models Generation Can Be Halted Early [4.726777092009553]
  Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. One of the ways to reduce the performance gap between these two types of language models is to speed up the generation of DLMs. We propose a novel methodology to address this issue in this work. It enables the execution of more generation steps within a given time frame.
  arXiv  Detail & Related papers  (2023-05-18T08:56:05Z)
• Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study [76.52997424694767]
  We present an in-depth empirical study of keyphrase extraction and keyphrase generation using pre-trained language models. We show that PLMs have competitive high-resource performance and state-of-the-art low-resource performance. Further results show that in-domain BERT-like PLMs can be used to build strong and data-efficient keyphrase generation models.
  arXiv  Detail & Related papers  (2022-12-20T13:20:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.