mlsanityData to 14 Oct 2026

d2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching

arXiv 2509.23094 ↗First posted 27 Sep 2025cs.CLcited by 25

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

Abstract (arXiv)

Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard key-value (KV) cache as autoregressive models (ARMs) do. To tackle this issue, we introduce textitDual aDaptive Cache (d2Cache), which is a training-free approximate KV cache framework for accelerating dLLM inference. d2Cache features a two-stage fine-grained selection strategy to identify tokens and adaptively update their KV states at each decoding step, while caching the KV states of the remaining tokens for reuse. Furthermore, d2Cache naturally offers a more reliable decoding alternative, which can enable quasi left-to-right generation and mitigate premature overconfidence in tokens at the end of the sequence. Extensive experimental results on two representative dLLMs (ie, LLaDA and Dream) demonstrate that d2Cache not only achieves substantial inference speedups, but also yields consistent improvements in generation quality. The code is available at https://github.com/Kamichanw/d2Cache.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Placed in Diffusion LLM and MoE inference, one of 12 directions in Efficient LLM inference and serving. Builds on 32 of its 35 references that are in the map. First posted on arXiv 27 Sep 2025.

Builds on

32 of 35 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding28 May
  2. 2025dKV-Cache: The Cache for Diffusion Language Models21 May

Other references · 30

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2021Program Synthesis with Large Language Modelscited by 3,637
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2022Video Diffusion Modelscited by 2,305
  9. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  10. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  11. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  12. 2025Large Language Diffusion Modelscited by 912
18 more
  1. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  2. 2020Quantifying Attention Flow in Transformerscited by 775
  3. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  4. 2025Dream 7B: Diffusion Large Language Modelscited by 544
  5. 2024PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funnelingcited by 432
  6. 2025Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Modelscited by 409
  7. 2023The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"cited by 407
  8. 2024Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inferencecited by 235
  9. 2024Scaling up Masked Diffusion Models on Textcited by 199
  10. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 169
  11. 2024A Survey on Large Language Model Acceleration based on KV Cache Managementcited by 131
  12. 2025A Survey on Diffusion Language Modelscited by 78
  13. 2025FlashDLM: Accelerating Diffusion Language Model Inference via Efficient KV Caching and Guided Diffusioncited by 77
  14. 2025Diffusion Language Models Know the Answer Before Decodingcited by 70
  15. 2025Roll the dice & look before you leap: Going beyond the creative limits of next-token predictioncited by 29
  16. 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Maskingcited by 21
  17. 2025Empirical Analysis of Decoding Biases in Masked Diffusion Modelscited by 19
  18. 2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 20.

25 papers.

Sort:

By area:

  1. 2025Learning Unmasking Policies for Diffusion Language Modelscited by 30
  2. 2025Encoder-Decoder Diffusion Language Models for Efficient Training and Inferencecited by 24
  3. 2025Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Waycited by 22
  4. 2025Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedulescited by 11
  5. 2026TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Accelerationcited by 8
  6. 2025Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Modelscited by 5
  7. 2026FOCUS: DLLMs Know How to Tame Their Compute Boundcited by 3
  8. 2026DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attentioncited by 3
  9. 2026EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Modelscited by 3
  10. 2026MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoningcited by 2
  11. 2026TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLMcited by 2
  12. 2026Reversible Diffusion Decoding for Diffusion Language Modelscited by 1
13 more
  1. 2026SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Modelscited by 1
  2. 2026DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inferencecited by 1
  3. 2026Stability-Weighted Decoding for Diffusion Language Modelscited by 1
  4. 2026Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMscited by 1
  5. 2026The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Modelscited by 1
  6. 2026WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filteringcited by 1
  7. 2026Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMscited by 1
  8. 2026AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decodingcited by 0
  9. 2026LESS Is More: Mutual-Stability Sampling for Diffusion Language Modelscited by 0
  10. 2026Understanding Evaluation Illusion in Diffusion Large Language Modelscited by 0
  11. 2026Affix Cache for Diffusion Large Language Modelscited by 0
  12. 2026What does FFN compression change downstream? Same-state causal restoration in diffusion language modelscited by 0
  13. 2026Time-Anchored Diffusion Language Models: Latent-Space Caching for Fast Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM
  2. 2025Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
  3. 2026Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs
  4. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
  5. 2025Attention Is All You Need for KV Cache in Diffusion LLMs
  6. 2025Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
  7. 2026GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference
  8. 2025Fast-dLLM v2: Efficient Block-Diffusion LLM