mlsanityData to 7 Oct 2026

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

arXiv 2602.06161 ↗First posted 5 Feb 2026cs.CL cs.AIcited by 6

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 31 of its 38 references that are in the map. First posted on arXiv 5 Feb 2026.

Builds on

31 of 38 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model20 Oct
  2. 2025Dream-Coder 7B: An Open Diffusion Language Model for Code1 Sep
  3. 2025Dream 7B: Diffusion Large Language Models21 Aug
  4. 2025Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing8 Aug
  5. 2025Large Language Diffusion Models14 Feb
  6. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  7. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data6 Jun
  8. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution25 Oct
  9. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control31 Oct
  10. 2022DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models17 Oct

Other references · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2023Let's Verify Step by Stepcited by 3,598
  6. 2021Program Synthesis with Large Language Modelscited by 3,509
  7. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  8. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  10. 2025Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decodingcited by 404
  11. 2025LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Modelscited by 273
  12. 2025MMaDA: Multimodal Large Diffusion Language Modelscited by 241
9 more
  1. 2025dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Cachingcited by 168
  2. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decodingcited by 108
  3. 2023Can Large Language Models Really Improve by Self-critiquing Their Own Plans?cited by 107
  4. 2023GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problemscited by 88
  5. 2025Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Evictioncited by 64
  6. 2025dParallel: Learnable Parallel Decoding for dLLMscited by 59
  7. 2025Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMscited by 45
  8. 2025Accelerating Diffusion LLM Inference via Local Determinism Propagationcited by 21
  9. 2025Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief Statescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inferencecited by 4
  2. 2026Re-evaluating Confidence Remasking in Masked Diffusion Language Modelscited by 1
  3. 2026Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokenscited by 1
  4. 2026SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decodingcited by 0
  5. 2026Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMscited by 0
  6. 2026FastGuide: Accelerating Reward Guidance for Diffusion Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
  2. 2026CORE: Context-Robust Remasking for Diffusion Language Models
  3. 2026Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs
  4. 2026Reversible Diffusion Decoding for Diffusion Language Models
  5. 2026AsyncLane: Decoupling Refinement from Advancement in Diffusion Language Model Decoding
  6. 2026Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
  7. 2026CAI-DLLM: Convergence Aware Inference for Diffusion Language Models
  8. 2026Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding