mlsanityData to 14 Oct 2026

STDec: Spatio-Temporal Stability Guided Decoding for dLLMs

arXiv 2604.06330 ↗First posted 7 Apr 2026cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Diffusion Large Language Models (dLLMs) have achieved rapid progress, viewed as a promising alternative to the autoregressive paradigm. However, most dLLM decoders still adopt a global confidence threshold, and do not explicitly model local context from neighboring decoded states or temporal consistency of predicted token IDs across steps. To address this issue, we propose a simple spatio-temporal stability guided decoding approach, named STDec. We observe strong spatio-temporal stability in dLLM decoding: newly decoded tokens tend to lie near decoded neighbors, and their predicted IDs often remain consistent across several denoising steps. Inspired by this stability, our STDec includes spatial-aware decoding and temporal-aware decoding. The spatial-aware decoding dynamically generates the token-adaptive threshold by aggregating the decoded states of nearby tokens. The temporal-aware decoding relaxes the decoding thresholds for tokens whose predicted token IDs remain consistent over denoising steps. Our STDec is training-free and remains compatible with cache-based acceleration methods. Across textual reasoning and multimodal understanding benchmarks, STDec substantially improves throughput while maintaining comparable task performance score. Notably, on MBPP with LLaDA, STDec achieves up to 14.17x speedup with a comparable score. Homepage: https://yzchen02.github.io/STDec.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

27 of 36 references.

References · 27

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  6. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contextscited by 1,614
  7. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Datasetcited by 526
  8. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 420
  9. 2023DeepCache: Accelerating Diffusion Models for Freecited by 359
  10. 2024Scaling Diffusion Language Models via Adaptation from Autoregressive Modelscited by 274
  11. 2025Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusionscited by 214
  12. 2024Scaling up Masked Diffusion Models on Textcited by 199
15 more
  1. 2025Remasking Discrete Diffusion Models with Inference-Time Scalingcited by 189
  2. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 169
  3. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcingcited by 116
  4. 2025Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decodingcited by 101
  5. 2025Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understandingcited by 88
  6. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusioncited by 77
  7. 2025Diffusion Language Models Know the Answer Before Decodingcited by 70
  8. 2025Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Evictioncited by 65
  9. 2024Think While You Generate: Discrete Diffusion with Planned Denoisingcited by 63
  10. 2025Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principlescited by 45
  11. 2025DPad: Efficient Diffusion Language Models with Suffix Dropoutcited by 39
  12. 2025TESS 2: A Large-Scale Generalist Diffusion Language Modelcited by 30
  13. 2025Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decodingcited by 27
  14. 2025Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inferencecited by 17
  15. 2024Conditional [MASK] Discrete Diffusion Language Modelcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Modelscited by 0