$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

• URL: http://arxiv.org/abs/2604.18995v1
• Date: Tue, 21 Apr 2026 02:26:08 GMT
• Title: $R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
• Abstract summary: We propose a unified framework for reducing decoding redundancy from both inference and training perspectives.<n>$R2$-dLLM consistently reduces the number of decoding steps by up to 75% compared to existing decoding strategies.
• Score: 28.068667649331246
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment. In this work, we observe that a substantial part of this inefficiency comes from recurring redundancy in the decoding process, including spatial redundancy caused by confidence clusters and positional ambiguity, and temporal redundancy caused by repeatedly remasking predictions that have already stabilized. Motivated by these patterns, we propose $R^2$-dLLM, a unified framework for reducing decoding redundancy from both inference and training perspectives. At inference time, we introduce training-free decoding rules that aggregate local confidence and token predictions, and finalize temporally stable tokens to avoid redundant decoding steps. We further propose a redundancy-aware supervised fine-tuning pipeline that aligns the model with efficient decoding trajectories and reduces reliance on manually tuned thresholds. Experiments demonstrate that $R^2$-dLLM consistently reduces the number of decoding steps by up to 75% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks. These results validate that decoding redundancy is a central bottleneck in dLLMs, and that explicitly reducing it yields substantial practical efficiency gains.

Related papers

• Penelope: Localized Latent Recurrence for Efficient Structured Reasoning [26.549641831847982]
  Penelope is an efficient latent-reasoning framework for pretrained decoder-only Transformers.<n>It localizes recurrent computation to a selected decoder interval.<n>It attains competitive accuracy relative to established latent-reasoning models.
  arXiv  Detail & Related papers  (2026-07-28T16:06:46Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding [32.0980373186604]
  We argue that left-to-right causal generation is an artifact of serialization rather than an intrinsic property of the task.<n>We propose MinerU-Diffusion, a unified diffusion-based framework that replaces autoregressive sequential decoding with parallel diffusion denoising.<n>Experiments demonstrate that MinerU-Diffusion consistently improves robustness while achieving up to 3.2x faster decoding compared to autoregressive baselines.
  arXiv  Detail & Related papers  (2026-03-23T18:25:17Z)
• Residual Context Diffusion Language Models [90.07635240595926]
  Residual Context Diffusion (RCD) is a module that converts discarded token representations into contextual residuals and injects them back for the next denoising step.<n>RCD consistently improves frontier dLLMs by 5-10 points in accuracy with minimal extra computation overhead.
  arXiv  Detail & Related papers  (2026-01-30T13:16:32Z)
• Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
  Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
  arXiv  Detail & Related papers  (2025-12-26T07:53:41Z)
• Arbitrage: Efficient Reasoning via Advantage-Aware Speculation [71.45710345765528]
  Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens.<n>But due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks.<n>We propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models.
  arXiv  Detail & Related papers  (2025-12-04T17:50:53Z)
• Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models [8.407364705777587]
  We introduce Free Draft-and-Verification (FreeDave), a novel fast decoding algorithm tailored forDLLMs.<n>FreeDave is proven to boost the inference throughput up to $3.78times$ without performance degradation.
  arXiv  Detail & Related papers  (2025-09-30T21:28:04Z)
• READER: Retrieval-Assisted Drafter for Efficient LLM Inference [0.0386965802948046]
  Autoregressive Language Models instantiate a factorized likelihood over token sequences, yet their strictly sequential decoding process imposes an intrinsic lower bound on latency inference.<n>This bottleneck has emerged as a central obstacle to the scalable deployment of large-scale generative models.<n>We present READER, a speculative decoding framework that bypasses the training of the auxiliary draft model.
  arXiv  Detail & Related papers  (2025-08-12T16:47:48Z)
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [80.104336426172]
  Chain-of-thought (CoT) enhances problem-solving ability of large language models.<n>CoT incurs substantial inference cost due to long autoregressive trajectories.<n>We introduce R-Stitch, a training-free hybrid decoding framework.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding [51.711605076319216]
  Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities.<n>We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.<n>We propose a confidence-aware parallel decoding strategy that selectively decodes tokens exceeding a confidence threshold, mitigating dependency violations and maintaining generation quality.
  arXiv  Detail & Related papers  (2025-05-28T17:39:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.