Trajectory-Level Speculative Decoding for Diffusion Language Models

• URL: http://arxiv.org/abs/2608.27514v1
• Date: Thu, 27 Aug 2026 09:42:20 GMT
• Title: Trajectory-Level Speculative Decoding for Diffusion Language Models
• Abstract summary: Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence.<n>We develop a trajectory-level speculative framework that constructs draft denoising trajectories via confidence-stratified tree exploration.<n>Our framework reduces denoising by 30-40% and increases tokens-per-step from 2.6 to 4.3, achieving 7-14x speedup over vanilla dLLMs and 1.3x over Fast-dLLM with less than 1% accuracy change across reasoning and code benchmarks.
• Score: 16.97093186372498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based language models (dLLMs) enable parallel token generation through iterative denoising, but existing decoding strategies collapse to single-token generation under low confidence, severely limiting throughput. Unlike autoregressive models where speculative decoding operates on token sequences in a fixed left-to-right order, dLLMs require speculating over denoising trajectories-sequences of multi-token updates with explicit positions and unmasking orders. We develop a trajectory-level speculative framework that constructs draft denoising trajectories via confidence-stratified tree exploration and verifies them through blockwise parallel evaluation with bidirectional attention masking. Our method further introduces inter-block speculation, exploiting diffusion models' bidirectional structure to perform cross-block lookahead. We formally characterize when this approach is exact and identify trajectory drift as the fundamental cost of increased parallelism. Building on Fast-dLLM's dual-cache infrastructure, our framework reduces denoising iterations by 30-40% and increases tokens-per-step from 2.6 to 4.3, achieving 7-14x speedup over vanilla dLLMs and 1.3x over Fast-dLLM with less than 1% accuracy change across reasoning and code benchmarks.

Related papers

• Early-Bird Decoding: Accelerating Diffusion LLMs with Learnable Block Sizes and Parallel Sampling [11.823547220829083]
  Diffusion large language models (dLLMs) offer a promising parallel decoding paradigm as an alternative to autoregressive generation.<n>We propose an "early-bird (EB)" decoding framework, motivated by the observation that tokens with similarly low entropy tend to cluster.<n>EB-Decode integrates two key enablers: (1) a learnable network that adaptively groups tokens with similar uncertainty into variable-length blocks, rather than relying on fixed block sizes; and (2) a position-aware sampler that learns to unmask tokens in parallel using fewer decoding steps within predicted variable-length blocks.
  arXiv  Detail & Related papers  (2026-09-15T00:12:37Z)
• SimSD: Simple Speculative Decoding in Diffusion Language Models [61.33773959352141]
  Diffusion large language models (dLLMs) offer faster inference through parallel or blockwise decoding.<n>Their masked language modeling formulation remains incompatible with standard token-level speculative decoding.<n>We propose a speculative decoding algorithm for dLLMs, named SimSD, that equips dLLMs with temporally valid token-level contexts.<n>Our method achieves up to 7.46x higher decoding throughput while maintaining and even improving average generation quality.
  arXiv  Detail & Related papers  (2026-06-01T17:46:46Z)
• 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)
• Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation [15.129362213838974]
  We propose a trace-aware decoding framework with two components.<n>First, Temporal-Spatial Parallel Decoding (TSPD) uses a lightweight temporalspatial controller that consumes per-token trajectory features, including confidence, entropy, and momentum, together with token position, to decide when a token has converged and can be safely fixed.<n>Second, we introduce Confidence Extrapolation (CE), a training-free state-space module that forecasts future logit trends with uncertainty to support proactive decisions.
  arXiv  Detail & Related papers  (2026-05-29T02:29:28Z)
• DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention [2.7422645382944935]
  We present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only salient tokens.<n>Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6x higher throughput.
  arXiv  Detail & Related papers  (2026-03-09T07:02:01Z)
• 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)
• 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)
• CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credits [37.06886078519443]
  CreditDecoding is a training-free parallel decoding algorithm that accelerates the confidence convergence of correct but underconfident tokens.<n>On eight benchmarks, CreditDecoding achieves a 5.48 times speedup and a 0.48 performance improvement over LLaDA-8B-Instruct.
  arXiv  Detail & Related papers  (2025-10-07T17:08:33Z)
• dParallel: Learnable Parallel Decoding for dLLMs [77.24184219948337]
  Diffusion large language models (dLLMs) offer parallel token prediction and lower inference latency.<n>Existing open-source models still require nearly token-length decoding steps to ensure performance.<n>We introduce dParallel, a simple and effective method that unlocks the inherent parallelism of dLLMs for fast sampling.
  arXiv  Detail & Related papers  (2025-09-30T16:32:52Z)
• Fast-dLLM v2: Efficient Block-Diffusion LLM [64.38006546510337]
  Fast-dLLM v2 is a block diffusion language model that adapts pretrained AR models into dLLMs for parallel text generation.<n>This represents a 500x reduction in training data compared to full-attention diffusion LLMs such as Dream (580B tokens)
  arXiv  Detail & Related papers  (2025-09-30T14:40:18Z)

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.