mlsanityData to 14 Oct 2026

KLASS: KL-Guided Fast Inference in Masked Diffusion Models

arXiv 2511.05664 ↗First posted 7 Nov 2025cs.LGcited by 47

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To overcome this problem, we introduce `KL-Adaptive Stability Sampling' (KLASS), a fast yet effective sampling method that exploits token-level KL divergence to identify stable, high-confidence predictions. By unmasking multiple tokens in each iteration without any additional model training, our approach speeds up generation significantly while maintaining sample quality. On reasoning benchmarks, KLASS achieves up to 2.78× wall-clock speedups while improving performance over standard greedy decoding, attaining state-of-the-art results among diffusion-based samplers. We further validate KLASS across diverse domains, including text, image, and molecular generation, showing its effectiveness as a broadly applicable sampler across different models.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 42 of its 54 references that are in the map. First posted on arXiv 7 Nov 2025.

Builds on

42 of 54 references.

Closest ancestors · 17

Same direction, newest first

  1. 2025Diffusion Language Models Know the Answer Before Decoding27 Aug
  2. 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking30 May
  3. 2025Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding22 May
  4. 2025Remasking Discrete Diffusion Models with Inference-Time Scaling1 Mar
  5. 2025Implicit Search via Discrete Diffusion: A Study on Chess27 Feb
  6. 2025Large Language Diffusion Models14 Feb
  7. 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions10 Feb
  8. 2025Path Planning for Masked Diffusion Model Sampling5 Feb
  9. 2024Energy-Based Diffusion Language Models for Text Generation28 Oct
  10. 2024Beyond Autoregression: Fast LLMs via Self-Distillation Through Time28 Oct
  11. 2024Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning18 Oct
  12. 2024Think While You Generate: Discrete Diffusion with Planned Denoising8 Oct
5 more
  1. 2024Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling4 Sep
  2. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  3. 2024Simplified and Generalized Masked Diffusion for Discrete Data6 Jun
  4. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data6 Jun
  5. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct

Other references · 25

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  8. 2021Program Synthesis with Large Language Modelscited by 3,637
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  10. 2016Improved Techniques for Training GANscited by 2,970
  11. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  12. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
13 more
  1. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  2. 2023One-step Diffusion with Distribution Matching Distillationcited by 1,019
  3. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  4. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 451
  5. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  6. 2024Simple Guidance Mechanisms for Discrete Diffusion Modelscited by 155
  7. 2022Concrete Score Matching: Generalized Score Matching for Discrete Datacited by 148
  8. 2024Informed Correctors for Discrete Diffusion Modelscited by 57
  9. 2024How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Frameworkcited by 48
  10. 2024Distillation of Discrete Diffusion through Dimensional Correlationscited by 48
  11. 2025Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithmscited by 47
  12. 2024Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformizationcited by 44
  13. 2024MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problemscited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 46.

47 papers.

Sort:

By area:

  1. 2025Learning Unmasking Policies for Diffusion Language Modelscited by 30
  2. 2026DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMscited by 14
  3. 2026DAWN: Dependency-Aware Fast Inference for Diffusion LLMscited by 13
  4. 2026Learn from Your Mistakes: Self-Correcting Masked Diffusion Modelscited by 13
  5. 2026DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmaskingcited by 9
  6. 2026Dependency-Guided Parallel Decoding in Discrete Diffusion Language Modelscited by 8
  7. 2026DSB: Dynamic Sliding Block Scheduling for Diffusion LLMscited by 7
  8. 2026Improving Sampling for Masked Diffusion Models via Information Gaincited by 7
  9. 2026Safety-Guided Flow (SGF): A Unified Framework for Negative Guidance in Safe Generationcited by 6
  10. 2026Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Modelscited by 5
  11. 2026A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Modelscited by 5
  12. 2026Breaking Block Boundaries: Anchor-based History-stable Decoding for Diffusion Large Language Modelscited by 4
35 more
  1. 2026Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Modelscited by 4
  2. 2026TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Modelscited by 3
  3. 2026Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokenscited by 3
  4. 2026TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decodingcited by 3
  5. 2026Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Modelscited by 2
  6. 2026Training-Free Self-Correction for Multimodal Masked Diffusion Modelscited by 2
  7. 2026Just on Time: Token-Level Early Stopping for Diffusion Language Modelscited by 2
  8. 2026DOS: Dependency-Oriented Sampler for Masked Diffusion Language Modelscited by 2
  9. 2026Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Modelscited by 2
  10. 2026Attention-Discounted Adaptive Sampler for Masked Diffusion Language Modelscited by 2
  11. 2026GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Modelscited by 1
  12. 2026Attention-Based Sampler for Diffusion Language Modelscited by 1
  13. 2026Supportive Token Revealing for Fast Diffusion Language Model Decodingcited by 1
  14. 2026Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMscited by 1
  15. 2026Pixel-Space Diffusion Transformerscited by 1
  16. 2026Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Modelscited by 1
  17. 2026CForce: Boosting Parallel Decoding for dLLMs via Consistency Forcingcited by 1
  18. 2026Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Modelscited by 1
  19. 2026MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Modelscited by 0
  20. 2026Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrastcited by 0
  21. 2026Path-Dependent Denoising: A Non-Conservative Field Perspective on Order Collapse in Diffusion Language Modelscited by 0
  22. 2026LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detectioncited by 0
  23. 2026Mean-Field Parallel Decoding for Discrete Diffusion Language Modelscited by 0
  24. 2026Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Modelscited by 0
  25. 2026Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Modelscited by 0
  26. 2026CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inferencecited by 0
  27. 2026Accelerating Diffusion Language Models via Structured Suffix Modelingcited by 0
  28. 2026Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Modelscited by 0
  29. 2026Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reportedcited by 0
  30. 2026Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMscited by 0
  31. 2026FastGuide: Accelerating Reward Guidance for Diffusion Large Language Modelscited by 0
  32. 2026Fine-Tuning Diffusion Language Models with Context Selection and Target Weightingcited by 0
  33. 2026Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Modelscited by 0
  34. 2026CoDR: Training-Free Confidence-Drift Remasking for Diffusion Language Modelscited by 0
  35. 2026Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusion
  2. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  3. 2026FastDiSS: Few-step Match Many-step Diffusion Language Model on Sequence-to-Sequence Generation--Full Version
  4. 2026LESS Is More: Mutual-Stability Sampling for Diffusion Language Models
  5. 2026Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language Models
  6. 2026Free Lunch for Pass@k? Low Cost Diverse Sampling for Diffusion Language Models
  7. 2026CORE: Context-Robust Remasking for Diffusion Language Models
  8. 2026Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models