mlsanityData to 7 Oct 2026

How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices

arXiv 2510.18480 ↗First posted 21 Oct 2025cs.CLcited by 10

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yield greater efficiency. Yet, in practice, current open-source DLMs often underperform their AR counterparts in speed, limiting their real-world utility. This work presents a systematic study of DLM efficiency, identifying key issues in prior evaluation methods. Through empirical benchmarking and a theoretical analysis, we demonstrate that AR models generally achieve higher throughput, while DLMs consistently lag. We also investigate acceleration strategies, finding that techniques like dual cache and parallel decoding mainly offer gains at small batch sizes, with their benefits diminishing upon scaling. Our findings underscore the necessity of robust evaluation methods and improved acceleration strategies to advance research on DLMs.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 19 of its 22 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

19 of 22 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025dInfer: An Efficient Inference Framework for Diffusion Language Models9 Oct
  2. 2025DPad: Efficient Diffusion Language Models with Suffix Dropout19 Aug
  3. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing8 Aug
  4. 2025DLM-One: Diffusion Language Models for One-Step Sequence Generation30 May
  5. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion27 May
  6. 2025dKV-Cache: The Cache for Diffusion Language Models21 May
  7. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models12 Mar
  8. 2025Large Language Diffusion Models14 Feb

Other references · 11

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2023A Survey of Large Language Modelscited by 2,537
  4. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  5. 2025Mercury: Ultra-Fast Language Models Based on Diffusioncited by 225
  6. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  7. 2025Fast-dLLM v2: Efficient Block-Diffusion LLMcited by 128
  8. 2025Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Evictioncited by 64
  9. 2024Distillation of Discrete Diffusion through Dimensional Correlationscited by 46
  10. 2025Exploring the Potential of Diffusion Large Language Models in Code Generationcited by 16
  11. 2025Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Modelscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 9.

10 papers.

  1. 2025SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understandingcited by 12
  2. 2026FOCUS: DLLMs Know How to Tame Their Compute Boundcited by 3
  3. 2026Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoningcited by 3
  4. 2026Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretrainingcited by 3
  5. 2026Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Cachingcited by 2
  6. 2026GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Modelscited by 1
  7. 2026CaRE Compute-aware Remasking Evaluation Protocol for Masked Diffusion Language Modelscited by 1
  8. 2026PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decodingcited by 0
  9. 2026Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challengescited by 0
  10. 2026Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Samplingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Diffusion Language Models
  2. 2026Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
  3. 2025Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
  4. 2026Introspective Diffusion Language Models
  5. 2025From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
  6. 2026Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
  7. 2026Locally Coherent Parallel Decoding in Diffusion Language Models
  8. 2026d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation