DARE: Diffusion Language Model Activation Reuse for Efficient Inference

• URL: http://arxiv.org/abs/2605.08134v1
• Date: Fri, 01 May 2026 19:15:45 GMT
• Title: DARE: Diffusion Language Model Activation Reuse for Efficient Inference
• Abstract summary: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models.<n>We introduce DARE, with two complementary mechanisms: DARE-KV, which reuses cached key-value (KV) activations, and DARE-O, which reuses output activations.<n>DARE achieves up to 1.20x per-layer latency reduction and reuses up to 87% of attention activations, with negligible degradation on reasoning and code-generation benchmarks.
• Score: 26.967107786841936
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel generation and faster inference. However, open-source dLLMs remain immature, lagging behind AR models in both efficiency and quality. We identify an underexplored property of dLLMs: *token-wise redundancy* in bi-directional self-attention. Self-attention activations are highly correlated across tokens, and temporal changes in query representations can predict redundancy in corresponding key, value, and output activations. We introduce DARE, with two complementary mechanisms: DARE-KV, which reuses cached key-value (KV) activations, and DARE-O, which reuses output activations to reduce redundant computation while preserving quality. DARE achieves up to 1.20x per-layer latency reduction and reuses up to 87% of attention activations, with negligible degradation on reasoning and code-generation benchmarks. DARE-KV and DARE-O incur average performance drops of only 2.0% and 1.2%, respectively. Combined with techniques such as prefix caching and Fast-dLLM, DARE provides additive gains without retraining. These results establish token-wise reuse as an effective strategy for improving the efficiency of diffusion-based LLMs while preserving generation fidelity. Code: https://github.com/enyac-group/DARE

Related papers

• FLARE: Diffusion for Hybrid Language Model [72.60770374799634]
  FLARE is a systematic conversion framework for hybrid-attention large language models.<n>It combines a token-equal AR-and-diffusion objective, hardware-aware kernels, and unified inference, enabling one checkpoint to support both AR-style verified decoding and diffusion-style parallel denoising.<n>Our results suggest practical dLLMs are limited not only by decoding algorithms, but also by transfer data quality and the training inefficiency of current block-diffusion objectives.
  arXiv  Detail & Related papers  (2026-06-01T06:58:15Z)
• $R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction [28.068667649331246]
  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.
  arXiv  Detail & Related papers  (2026-04-21T02:26:08Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• Causal Autoregressive Diffusion Language Model [70.7353007255797]
  CARD reformulates the diffusion process within a strictly causal attention mask, enabling dense, per-token supervision in a single forward pass.<n>Our results demonstrate that CARD achieves ARM-level data efficiency while unlocking the latency benefits of parallel generation.
  arXiv  Detail & Related papers  (2026-01-29T17:38:29Z)
• Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models [13.32858759983739]
  Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating text inconsistent with visual inputs.<n>Existing inference-time interventions to mitigate this issue present a challenging trade-off.<n>We present Residual-Update Directed DEcoding Regulation (RUDDER), a framework that steers LVLMs towards visually-grounded generation.
  arXiv  Detail & Related papers  (2025-11-13T13:29:38Z)
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model [98.35868970993232]
  Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm.<n>We introduce efficient Sampling with Adaptive acceleration and Backtracking Enhanced Remasking (i.e., Saber) to achieve better inference speed and output quality in code generation.
  arXiv  Detail & Related papers  (2025-10-20T23:38:12Z)
• 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)
• Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models [30.7855782696894]
  Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot control through natural language instructions.<n>We propose FlashVLA, the first training-free and plug-and-play acceleration framework that enables action reuse in VLA models.
  arXiv  Detail & Related papers  (2025-05-27T13:47:18Z)
• R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference [77.47238561728459]
  R-Sparse is a training-free activation sparsity approach capable of achieving high sparsity levels in advanced LLMs.<n> Experiments on Llama-2/3 and Mistral models across ten diverse tasks demonstrate that R-Sparse achieves comparable performance at 50% model-level sparsity.
  arXiv  Detail & Related papers  (2025-04-28T03:30:32Z)
• LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization [17.190984773586745]
  Current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. We propose efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance.
  arXiv  Detail & Related papers  (2024-11-26T07:32:36Z)

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.