mlsanityData to 7 Oct 2026

DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs

arXiv 2602.05992 ↗First posted 5 Feb 2026cs.CLcited by 7

On the map: Efficient LLM inference and serving → Diffusion LLM and MoE inference

Abstract (arXiv)

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in global bidirectional decoding and improving output quality. However, the widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency: it can force premature commitments to uncertain positions while delaying easy positions near block boundaries. In this work, we analyze the limitations of naive block scheduling and disclose the importance of dynamically adapting the schedule to semantic difficulty for reliable and efficient inference. Motivated by this, we propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block. To further improve efficiency, we introduce DSB Cache, a training-free KV-cache mechanism tailored to DSB. Extensive experiments across multiple models and benchmarks demonstrate that DSB, together with DSB Cache, consistently improves both generation quality and inference efficiency for dLLMs. Code is released at https://github.com/lizhuo-luo/DSB.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Diffusion LLM and MoE inference, one of 12 directions in Efficient LLM inference and serving. Builds on 29 of its 35 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

29 of 35 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Accelerating Diffusion LLM Inference via Local Determinism Propagation8 Oct
  2. 2025dParallel: Learnable Parallel Decoding for dLLMs30 Sep
  3. 2025AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Size30 Sep
  4. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding28 May
  5. 2025dKV-Cache: The Cache for Diffusion Language Models21 May

Other references · 24

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  5. 2021Program Synthesis with Large Language Modelscited by 3,509
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  7. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  8. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  9. 2025Large Language Diffusion Modelscited by 872
  10. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  11. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  12. 2025Dream 7B: Diffusion Large Language Modelscited by 515
12 more
  1. 2024SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformerscited by 331
  2. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  3. 2025Mercury: Ultra-Fast Language Models Based on Diffusioncited by 225
  4. 2025Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inferencecited by 173
  5. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  6. 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmaskingcited by 128
  7. 2025Fast-dLLM v2: Efficient Block-Diffusion LLMcited by 128
  8. 2025KLASS: KL-Guided Fast Inference in Masked Diffusion Modelscited by 44
  9. 2025WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inferencecited by 38
  10. 2025Beyond Fixed: Training-Free Variable-Length Denoising for Diffusion Large Language Modelscited by 32
  11. 2025Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Waycited by 22
  12. 2025WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inferencecited by 1
  2. 2026VoidPadding: Let [VOID] Handle Padding in Masked Diffusion Language Models so that [EOS] Can Focus on Semantic Terminationcited by 1
  3. 2026Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrastcited by 0
  4. 2026SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMscited by 0
  5. 2026Affix Cache for Diffusion Large Language Modelscited by 0
  6. 2026Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Samplingcited by 0
  7. 2026Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
  2. 2026BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference
  3. 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
  4. 2026BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
  5. 2026Rethinking the Generation Order of Block Diffusion Language Models
  6. 2026Multi-Block Diffusion Language Models
  7. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
  8. 2025Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models