DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees

• URL: http://arxiv.org/abs/2608.13524v1
• Date: Thu, 13 Aug 2026 17:43:44 GMT
• Title: DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
• Abstract summary: Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel.<n>Dartree is a training-free speculative decoding method that extends a pretrained AR correction head from chains to trees.
• Score: 40.61855455828842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency by predicting an entire token block in parallel, but their position-wise distributions are marginal rather than conditioned on tokens selected along each draft path. Existing recurrent correction incorporates causal information along a single draft chain, whereas diffusion-based tree construction broadens candidate coverage without carrying this correction along individual branches. We introduce DARTree, a training-free speculative decoding method that extends a pretrained AR correction head from chains to trees. DARTree first constructs a fixed-width candidate tree by expanding and scoring all nodes at each depth in a single batch, and then only applies best-first pruning to select the verification tree, decoupling AR-head inference from sequential heap operations. Across seven math, code, and chat benchmarks, DARTree achieves the highest average acceptance length and speedup in all four model--temperature configurations, accepting up to 12.97 tokens per verification round, 98.6\% more than DFlash and 27.9\% more than Domino in the same setting, and reaching up to 9.73$\times$ lossless speedup over locally measured autoregressive decoding.

Related papers

• DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding [6.82231493613379]
  We introduce DominoTree, a training-free best-first draft tree scored by Domino's conditional, non-factorized correction along each root-to-node path.<n>DominoTree reaches up to 6.6x speedup over greedy decoding and the highest mean accepted length of any evaluated method.
  arXiv  Detail & Related papers  (2026-07-09T16:16:35Z)
• PRESTO: Prefix-Aligned Tree Drafting for Diffusion Speculative Decoding [98.71600061506206]
  We propose PRESTO, a principled framework that extends tree-based drafting to diffusion drafters.<n> PRESTO achieves up to an average of $1.5times$ end-to-end throughput speedup on the state-of-the-art dedicated diffusion drafter SD.
  arXiv  Detail & Related papers  (2026-06-20T14:32:14Z)
• TreeFlash: Parallel AR-Approximation for Faster Speculative Decoding [32.75269650141292]
  One-shot block drafters for speculative decoding generate the full draft in a single forward pass.<n>They predict each draft token conditioned only on the prefix context, with no dependence on previously drafted tokens.<n>This non-autoregressive conditioning causes the drafter's distribution to diverge from the verifier's true autoregressive distribution as draft depth grows.<n>We propose TreeFlash, which addresses this by incorporating a layer conditioned on the drafter's hidden state and the previous token to approximate an autoregressive distribution.
  arXiv  Detail & Related papers  (2026-06-02T16:00:18Z)
• Cost-Aware Diffusion Draft Trees for Speculative Decoding [17.900184934329666]
  We introduce textbfCaDDTree (Cost-aware Diffusion Draft Tree), a method that directly optimize token throughput (expected tokens generated per unit time) by jointly selecting the tree structure and node budget.<n>Experiments on Qwen3-4B and Qwen3-8B across eight benchmarks spanning reasoning, coding, and instruction-following tasks show that caDDTree matches or surpasses DDTree with oracle budget selection on nearly all tasks.
  arXiv  Detail & Related papers  (2026-06-01T07:29:56Z)
• TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding [4.5881678566958985]
  Using a diffusion model for parallel drafting is a promising approach for speculative decoding.<n>This shifts the bottleneck to verification: verifying a single sequence limits acceptance length, while verifying large draft trees incurs excessive target-model latency.<n>We propose TAPS, a target-aware prefix selection method that turns diffusion marginals into path-conditioned acceptance estimates.
  arXiv  Detail & Related papers  (2026-05-30T02:39:40Z)
• D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting [59.204113363599994]
  Speculative decoding accelerates inference by having a small drafter propose tokens that a larger target model verifies in parallel.<n>Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward pass, enabling deeper drafters and longer accepted blocks.<n>We derive per-position training weights from a differentiable surrogate of expected accepted draft length, matching the weight of each position to its log-probability contribution.<n>Across six benchmarks, two Qwen3-4B draft depths, two decoding temperatures, and two additional target models, D-PACE consistently improves both wall-clock speedup and average
  arXiv  Detail & Related papers  (2026-05-12T06:27:57Z)
• Accelerating Speculative Decoding with Block Diffusion Draft Trees [20.28933257827737]
  Speculative decoding accelerates autoregressive language models by using a lightweight drafter to propose multiple future tokens.<n>DFlash shows that a block diffusion drafter can generate an entire draft block in a single forward pass.<n> Vanilla DFlash verifies only a single drafted trajectory per round, potentially limiting its acceptance length.<n>We introduce DDTree, a method that constructs a draft tree directly from the per-position distributions of a block diffusion drafter.
  arXiv  Detail & Related papers  (2026-04-14T17:23:14Z)
• Fast Inference of Visual Autoregressive Model with Adjacency-Adaptive Dynamical Draft Trees [50.230925890958936]
  We propose an adjacency-adaptive dynamic draft tree that adjusts draft tree depth and width by leveraging adjacent token states and prior acceptance rates.<n>ADT-Tree achieves speedups of 3.13xand 3.05x, respectively, and integrates seamlessly with relaxed sampling methods such as LANTERN.
  arXiv  Detail & Related papers  (2025-12-26T04:45:49Z)
• DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding [66.40658898418316]
  We present DiffuSpec, a training-free drop-in framework that uses a pretrained diffusion language model (DLM) to produce multi-token drafts in a single forward pass.<n>Across benchmarks, DiffuSpec yields up to 3x wall-clock speedup, establishing diffusion-based drafting as a robust alternative to autoregressive drafters for speculative decoding.
  arXiv  Detail & Related papers  (2025-09-28T07:00:15Z)
• Pipeline Parallelism is All You Need for Optimized Early-Exit Based Self-Speculative Decoding [73.67253077506672]
  Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost.<n>Early-exit based self-speculative decoding (EESD) has emerged to mitigate this cost.<n>We propose Pipeline-Parallel Self-Speculative Decoding (PPSD) that fully pipelines the draft and verification work.
  arXiv  Detail & Related papers  (2025-09-19T04:51:41Z)
• An Efficient Adversarial Attack for Tree Ensembles [91.05779257472675]
  adversarial attacks on tree based ensembles such as gradient boosting decision trees (DTs) and random forests (RFs) We show that our method can be thousands of times faster than the previous mixed-integer linear programming (MILP) based approach. Our code is available at https://chong-z/tree-ensemble-attack.
  arXiv  Detail & Related papers  (2020-10-22T10:59:49Z)

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.