DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding

• URL: http://arxiv.org/abs/2609.06498v1
• Date: Sun, 06 Sep 2026 09:25:56 GMT
• Title: DFlow: Enabling Verifier Information Flow in Block Diffusion Speculative Decoding
• Abstract summary: We propose DFlow, a framework that enables verifier information to flow across drafting rounds.<n>DFlow reuses the hidden states produced by the target verifier for the rejected suffix to guide subsequent drafting.<n>Experiments on Qwen3 models across diverse benchmarks demonstrate that DFlow consistently improves draft quality and acceptance length over DFlash.
• Score: 25.203742152821548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Block diffusion speculative decoding improves LLM inference efficiency by proposing a block of future tokens in parallel and verifying them with a single forward pass through the target model. However, existing methods retain only the accepted prefix and discard the rejected suffix, preventing the computation spent on these positions from benefiting subsequent drafting rounds and forcing the drafter to repeatedly reconstruct representations for future tokens from scratch. We observe that rejection only determines whether a proposed token can be committed, while the verifier representations at rejected positions can still provide useful information for subsequent predictions. Based on this observation, we propose DFlow, a simple yet effective framework that enables verifier information to flow across drafting rounds. DFlow reuses the hidden states produced by the target verifier for the rejected suffix to guide subsequent drafting without additional target computation. To effectively learn this information flow across drafting rounds, we introduce a self-condition train strategy that feeds verifier representations from earlier predictions back into subsequent predictions. Experiments on Qwen3 models across diverse benchmarks demonstrate that DFlow consistently improves draft quality and acceptance length over DFlash.

Related papers

• Verification-Aware Training for Speculative Decoding [57.84976863792784]
  We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision.<n>VAT modifies only the training objective, so it can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure.<n>VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks.
  arXiv  Detail & Related papers  (2026-08-31T01:42:10Z)
• ReTrace: Rejected-Trajectory Conditioning for Speculative Decoding [46.17292752074153]
  We show that rejected positions in a rejected suffix may still align with the target continuation.<n>textbfReTrace, a rejected-trajectory conditioning method, conditions each draft block on the rejected suffix from the previous round.<n>ReTrace consistently improves average acceptance length and end-to-end decoding speed over its DFlash backbone.
  arXiv  Detail & Related papers  (2026-08-30T12:20:54Z)
• ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping [79.1905186547363]
  ResiSpec is a framework that strategically reforms the proposal distribution during verification.<n>It prevents candidate obsolescence and achieves up to 1.92$times$ speedup over state-of-the-art multi-candidate methods.
  arXiv  Detail & Related papers  (2026-08-25T11:25:55Z)
• DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding [26.72775347772003]
  We show that the accepted draft length degrades as the entropy of the target sampling distribution increases.<n>We propose a dependent block drafter based on a low-rank latent mixture over token positions, complemented by an acceptance-oriented training objective.
  arXiv  Detail & Related papers  (2026-08-05T22:49:54Z)
• Accepted Prefixes Are Not All You Need: A Negative Result on PEFT-Based Block-Diffusion Drafting [0.0]
  Speculative decoding uses a cheap drafter to propose multiple future tokens and a target model to verify them.<n>We study a negative result for this direction through PEFT-BD, a same-backbone speculative decoding method.<n>Our results isolate a simple but important condition for successful speculative decoding: the drafter must be substantially cheaper to execute than the verifier.
  arXiv  Detail & Related papers  (2026-07-14T06:48:33Z)
• Accelerating Speculative Diffusions via Block Verification [77.23389794645801]
  Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme.<n>Existing diffusion adaptations either use inefficient sampling techniques or rely on an alternative scheme.<n>We introduce a novel scheme that efficiently implements the original speculative sampling mechanism for diffusion models.
  arXiv  Detail & Related papers  (2026-06-11T14:54:13Z)
• Draft-OPD: On-Policy Distillation for Speculative Draft Models [49.23782868133977]
  Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verified in parallel.<n>We propose Draft-OPD, which uses target-assisted rollout for stable continuations and replays drafting from the verification-exposed error positions.
  arXiv  Detail & Related papers  (2026-05-28T04:30:22Z)
• Make Every Draft Count: Hidden State based Speculative Decoding [7.373716645300893]
  We propose a novel system that transforms discarded drafts into reusable tokens.<n>Our key insight is to perform auto-regressive prediction at the hidden states level.<n>We demonstrate up to a 3.3x speedup against standard speculative decoding.
  arXiv  Detail & Related papers  (2026-02-02T08:25:21Z)
• Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding [48.52389201779425]
  Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in parallel.<n>Existing verification methods rely heavily on distributional consistency while overlooking semantic correctness.<n>We propose Reflective Verification, a training-free and semantics-aware approach that achieves a better trade-off between correctness and efficiency.
  arXiv  Detail & Related papers  (2025-05-24T10:26:27Z)

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.