mlsanityData to 14 Oct 2026

Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models

arXiv 2506.19037 ↗First posted 23 Jun 2025cs.CL cs.AI cs.ITcited by 34

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow, autoregressive behavior. We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-free method that partitions sequence positions into non-adjacent dilated groups and unmasks them in parallel so as to minimize an upper bound on joint entropy gain at each denoising step. By explicitly trading off the number of network calls against generation quality, DUS recovers most of the performance lost under traditional parallel unmasking strategies. Across math (GSM8K, MATH500), code (HumanEval, MBPP), general-knowledge (BBH, MMLU-Pro), and instruction following (IFEval) benchmarks, DUS outperforms confidence-based planners and turns the diffusion-specific quality-speed trade-off into a deterministic, predictable speedup set by the block size B, yielding up to 5.8× wall-clock speedup over token-by-token MDLM decoding without modifying the underlying denoiser. Applied as a drop-in post-filter, dilated spacing also improves adaptive samplers. Code is available at https://github.com/omerlux/DUS.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 28 of its 40 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

28 of 40 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking30 May
  2. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion27 May
  3. 2025dKV-Cache: The Cache for Diffusion Language Models21 May
  4. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models12 Mar
  5. 2025Large Language Diffusion Models14 Feb
  6. 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions10 Feb
  7. 2025Path Planning for Masked Diffusion Model Sampling5 Feb
  8. 2024Scaling up Masked Diffusion Models on Text24 Oct
  9. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning18 Oct
  10. 2024Think While You Generate: Discrete Diffusion with Planned Denoising8 Oct
  11. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  12. 2024Simplified and Generalized Masked Diffusion for Discrete Data6 Jun
1 more
  1. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct

Other references · 15

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  6. 2023Let's Verify Step by Stepcited by 3,789
  7. 2021Program Synthesis with Large Language Modelscited by 3,637
  8. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  9. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  10. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  11. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,653
  12. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 451
3 more
  1. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  2. 2022Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generationcited by 171
  3. 2024textitJump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Modelscited by 40

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 21.

34 papers.

Sort:

By area:

  1. 2025A Survey on Diffusion Language Modelscited by 78
  2. 2025ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMscited by 43
  3. 2025AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Sizecited by 31
  4. 2025Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphscited by 21
  5. 2025ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decodingcited by 18
  6. 2025Error Bounds and Optimal Schedules for Masked Diffusions with Factorized Approximationscited by 14
  7. 2025Thinking Inside the Mask: In-Place Prompting in Diffusion LLMscited by 13
  8. 2025Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Modelcited by 13
  9. 2025Parallel Sampling from Masked Diffusion Models via Conditional Independence Testingcited by 13
  10. 2025Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief Statescited by 9
  11. 2026DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmaskingcited by 9
  12. 2026Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generationcited by 6
22 more
  1. 2025Finish First, Perfect Later: Test-Time Token-Level Cross-Validation for Diffusion Large Language Modelscited by 5
  2. 2026Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Modelscited by 5
  3. 2026Fixed-Point Masked Generative Modelingcited by 5
  4. 2025Diffusion Language Model Inference with Monte Carlo Tree Searchcited by 4
  5. 2026Diffusion-State Policy Optimization for Masked Diffusion Language Modelscited by 4
  6. 2026Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learningcited by 4
  7. 2026Stopping Computation for Converged Tokens in Masked Diffusion-LM Decodingcited by 3
  8. 2026DODO: Discrete OCR Diffusion Modelscited by 2
  9. 2026On the Trainability of Masked Diffusion Language Models via Blockwise Localitycited by 2
  10. 2026Drifting Objectives for Refining Discrete Diffusion Language Modelscited by 2
  11. 2026Attention-Discounted Adaptive Sampler for Masked Diffusion Language Modelscited by 2
  12. 2026CRoCoDiL: Continuous and Robust Conditioned Diffusion for Languagecited by 1
  13. 2026Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Modelscited by 1
  14. 2026Looped Diffusion Language Modelscited by 1
  15. 2026Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphscited by 1
  16. 2026Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniquescited by 1
  17. 2025STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Modelscited by 0
  18. 2026Progressive Refinement Regulation for Accelerating Diffusion Language Model Decodingcited by 0
  19. 2026LaCache: Exact Caching and Precision-Adaptive Inference for Diffusion Large Language Modelscited by 0
  20. 2026Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Samplingcited by 0
  21. 2026Schedule optimization for tau-leaping in masked discrete diffusioncited by 0
  22. 2026Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reportedcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
  2. 2025Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
  3. 2025Optimal Inference Schedules for Masked Diffusion Models
  4. 2025Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
  5. 2026UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching
  6. 2026Machine Unlearning for Masked Diffusion Language Models
  7. 2026Adaptation to Intrinsic Dependence in Diffusion Language Models
  8. 2026Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes