mlsanityData to 7 Oct 2026

Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques

arXiv 2607.12829 ↗First posted 14 Jul 2026cs.LG cs.AI cs.CLcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guarantee practical speedups. Realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware caching and reuse. Consequently, as inference efficiency becomes a prerequisite for practical deployment, recent research has actively explored acceleration techniques across algorithms, architectures, and systems. However, rigorous comparisons remain difficult, as end-to-end latency stems from intricate trade-offs between algorithmic, architectural, and system-level factors that are often conflated in existing benchmarks. In this survey, we introduce a unified latency decomposition framework for dLLMs to disentangle these factors and analyze their impact on inference speed in real deployments. Guided by this framework, we categorize acceleration techniques along three axes covering algorithmic innovations, architectural and system optimizations, and inference-time scaling. Finally, we provide guidelines for reproducible benchmarking and highlight open challenges for realizing the full potential of parallel generation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 52 of its 60 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

52 of 60 references.

Closest ancestors · 26

Same direction, newest first

  1. 2025ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding15 Dec
  2. 2025Diffusion Language Model Inference with Monte Carlo Tree Search13 Dec
  3. 2025Learning Unmasking Policies for Diffusion Language Models9 Dec
  4. 2025Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules2 Dec
  5. 2025CDLM: Consistency Diffusion Language Models For Faster Sampling24 Nov
  6. 2025Encoder-Decoder Diffusion Language Models for Efficient Training and Inference26 Oct
  7. 2025SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models10 Oct
  8. 2025dInfer: An Efficient Inference Framework for Diffusion Language Models9 Oct
  9. 2025DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding28 Sep
  10. 2025SparseD: Sparse Attention for Diffusion Language Models28 Sep
  11. 2025Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning18 Sep
  12. 2025Dream 7B: Diffusion Large Language Models21 Aug
14 more
  1. 2025A Survey on Diffusion Language Models14 Aug
  2. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models12 Aug
  3. 2025Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models23 Jun
  4. 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking30 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. 2025Constrained Discrete Diffusion12 Mar
  8. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models12 Mar
  9. 2025Remasking Discrete Diffusion Models with Inference-Time Scaling1 Mar
  10. 2025Large Language Diffusion Models14 Feb
  11. 2024Beyond Autoregression: Fast LLMs via Self-Distillation Through Time28 Oct
  12. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  13. 2023Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time14 Dec
  14. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct

Other references · 26

  1. 2023Consistency Modelscited by 1,778
  2. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  3. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  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. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 195
  7. 2024Simple Guidance Mechanisms for Discrete Diffusion Modelscited by 148
  8. 2021Step-unrolled Denoising Autoencoders for Text Generationcited by 102
  9. 2025Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Evictioncited by 64
  10. 2024Speculative Diffusion Decoding: Accelerating Language Generation through Diffusioncited by 57
  11. 2025Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithmscited by 47
  12. 2024Distillation of Discrete Diffusion through Dimensional Correlationscited by 46
14 more
  1. 2025DiCache: Let Diffusion Model Determine Its Own Cachecited by 34
  2. 2025Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Modelscited by 32
  3. 2025Attention Is All You Need for KV Cache in Diffusion LLMscited by 32
  4. 2025Diffusion Tree Sampling: Scalable inference-time alignment of diffusion modelscited by 31
  5. 2025Self Speculative Decoding for Diffusion Large Language Modelscited by 29
  6. 2025Set Block Decoding is a Language Model Inference Acceleratorcited by 22
  7. 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Maskingcited by 21
  8. 2025Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inferencecited by 17
  9. 2025DINGO: Constrained Inference for Diffusion LLMscited by 15
  10. 2025Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusioncited by 14
  11. 2025Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Modelscited by 11
  12. 2025DLLMQuant: Quantizing Diffusion-based Large Language Modelscited by 10
  13. 2025What Exactly Does Guidance Do in Masked Discrete Diffusion Modelscited by 9
  14. 2025Learnable Sampler Distillation for Discrete Diffusion Modelscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026d-OPD: Future-Aware On-Policy Distillation for Block Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
  2. 2025How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices
  3. 2026Diffusion Language Models: An Experimental Analysis
  4. 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
  5. 2026Mosaic: Unlocking Long-Context Inference for Diffusion LLMs via Global Memory Planning and Dynamic Peak Taming
  6. 2025Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models
  7. 2026Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
  8. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models