Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding

• URL: http://arxiv.org/abs/2602.06161v1
• Date: Thu, 05 Feb 2026 19:58:48 GMT
• Title: Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion Decoding
• Authors: Yanzheng Xiang, Lan Wei, Yizhen Yao, Qinglin Zhu, Hanqi Yan, Chen Jin, Philip Alexander Teare, Dandan Zhang, Lin Gui, Amrutha Saseendran, Yulan He,
• Abstract summary: COVER performs leave-one-out verification and stable drafting within a single forward pass.<n>It balances uncertainty, downstream influence, and cache drift, and it adapts the number of verified seeds per step.<n>Across benchmarks, COVER reduces unnecessary revisions and yields faster decoding while preserving output quality.
• Score: 28.23607623451461
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelism often harms quality. Revocable decoding mitigates this by rechecking earlier tokens, yet we observe that existing verification schemes frequently trigger flip-flop oscillations, where tokens are remasked and later restored unchanged. This behaviour slows inference in two ways: remasking verified positions weakens the conditioning context for parallel drafting, and repeated remask cycles consume the revision budget with little net progress. We propose COVER (Cache Override Verification for Efficient Revision), which performs leave-one-out verification and stable drafting within a single forward pass. COVER constructs two attention views via KV cache override: selected seeds are masked for verification, while their cached key value states are injected for all other queries to preserve contextual information, with a closed form diagonal correction preventing self leakage at the seed positions. COVER further prioritises seeds using a stability aware score that balances uncertainty, downstream influence, and cache drift, and it adapts the number of verified seeds per step. Across benchmarks, COVER markedly reduces unnecessary revisions and yields faster decoding while preserving output quality.

Related papers

• Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes [10.877713536966601]
  Longestahead Prefix (LSP) scheduler is a training-free and model-agnostic inference paradigm based on monolithic prefix absorption.<n>LSP evaluates token stability via a single forward pass, dynamically identifies a contiguous left-aligned block of stable predictions.<n>It snaps its boundary to natural linguistic or structural acceptances before an atomic commitment.
  arXiv  Detail & Related papers  (2026-03-05T18:25:26Z)
• Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference [58.189320101488725]
  DLLMs promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding.<n>We address this by integrating continuous representations into the discrete decoding process, as they preserve rich inter-position dependency.<n>We propose ReMix, a framework that introduces a novel Continuous Mixing State as an intermediate between the initial masked state and the final decoded token state.
  arXiv  Detail & Related papers  (2026-02-26T11:08:11Z)
• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference [44.87788417755154]
  We propose WeDLM, a diffusion decoding framework built entirely on standard causal attention.<n>We show that WeDLM preserves the quality of strong AR backbones while delivering substantial speedups.
  arXiv  Detail & Related papers  (2025-12-28T01:25:48Z)
• 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)
• Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling [87.34677262370924]
  Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token.<n>This creates an 'information void' where semantic information that could be inferred from unmasked tokens is lost between denoising steps.<n>We introduce Continuously Augmented Discrete Diffusion, a framework that augments the discrete state space with a paired diffusion in a continuous latent space.
  arXiv  Detail & Related papers  (2025-10-01T18:00:56Z)
• Rectified Sparse Attention [61.7702154360081]
  Efficient long-sequence generation is a critical challenge for Large Language Models.<n>We propose Rectified Sparse Attention (ReSA), a simple yet effective method that combines block-sparse attention with periodic dense rectification.<n> Experiments across math reasoning, language modeling, and retrieval tasks demonstrate that ReSA achieves near-lossless generation quality.
  arXiv  Detail & Related papers  (2025-06-04T16:01:48Z)
• 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)
• ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy [8.962703809086628]
  ThinkLess is an inference-efficient framework that terminates reasoning generation early and maintains output quality without modifying the model.<n>We show that ThinkLess achieves comparable accuracy to full-length Chain-of-Thought (CoT) decoding while greatly reducing decoding time and memory consumption.
  arXiv  Detail & Related papers  (2025-05-21T15:58:16Z)

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.