Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation

• URL: http://arxiv.org/abs/2510.26200v1
• Date: Thu, 30 Oct 2025 07:21:05 GMT
• Title: Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
• Abstract summary: We describe update forgetting, in which uniform and context updates induce token level fluctuations across timesteps.<n>We propose Token Timestep Allocation (TTA), which realizes soft and semantic token ordering via per token timestep schedules.
• Score: 9.670831676453673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While diffusion language models (DLMs) enable fine-grained refinement, their practical controllability remains fragile. We identify and formally characterize a central failure mode called update forgetting, in which uniform and context agnostic updates induce token level fluctuations across timesteps, erasing earlier semantic edits and disrupting the cumulative refinement process, thereby degrading fluency and coherence. As this failure originates in uniform and context agnostic updates, effective control demands explicit token ordering. We propose Token Timestep Allocation (TTA), which realizes soft and semantic token ordering via per token timestep schedules: critical tokens are frozen early, while uncertain tokens receive continued refinement. This timestep based ordering can be instantiated as either a fixed policy or an adaptive policy driven by task signals, thereby supporting a broad spectrum of refinement strategies. Because it operates purely at inference time, it applies uniformly across various DLMs and naturally extends to diverse supervision sources. Empirically, TTA improves controllability and fluency: on sentiment control, it yields more than 20 percent higher accuracy and nearly halves perplexity using less than one fifth the steps; in detoxification, it lowers maximum toxicity (12.2 versus 14.5) and perplexity (26.0 versus 32.0). Together, these results demonstrate that softened ordering via timestep allocation is the critical lever for mitigating update forgetting and achieving stable and controllable diffusion text generation.

Related papers

• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• Where and When to Commit: Candidate-Aware Decoding for Diffusion Language Models [29.849017661114342]
  Diffusion language models expose a provisional prediction at every denoising step.<n>Generation-time early exit stops decoding before the schedule is exhausted.<n>We introduce a training-free, candidate-aware early-exit framework that keeps the two axes separate and matches each decision to evidence of its own scope.
  arXiv  Detail & Related papers  (2026-07-30T13:04:47Z)
• SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation [65.81476183180527]
  We introduce SegDiff, a closed-loop visuomotor policy that integrates the strengths of both paradigms.<n>SegDiff decomposes demonstrations into motion segments between keyposes and learns to predict the continuous trajectory from the current state to the next keypose.<n>SegDiff demonstrates significant performance gains over existing approaches across various simulated and real-world scenarios.
  arXiv  Detail & Related papers  (2026-07-13T02:48:03Z)
• 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)
• SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning [23.62252234067012]
  Large Language Models (LLMs) are prone to logical hallucinations and drifts during long-chain reasoning.<n>We propose SPREG (Structured Plan-guided Real-time Entropy Gating), a lightweight inference-time framework for surgical error rectification.<n>Our experiments demonstrate significant gains, notably a 20.0% absolute accuracy improvement on AIME25.
  arXiv  Detail & Related papers  (2026-04-20T06:55:26Z)
• Stability-Weighted Decoding for Diffusion Language Models [8.670026899042483]
  Existing decoding strategies rely on static confidence metrics computed at a single denoising step, ignoring temporal history and often leading to premature unmasking of unstable tokens.<n>We propose Stability-Weighted Decoding (SWD), a training-free, plug-and-play strategy that incorporates temporal stability into token scoring and acts as a universal modulator for arbitrary score-based decoding policies.
  arXiv  Detail & Related papers  (2026-04-18T17:04:10Z)
• Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding [18.99795632160924]
  We propose emphProgressive Refinement Regulation (PRR), a trajectory-grounded refinement control framework.<n>PRR learns a lightweight token-wise controller to regulate refinement via temperature-based distribution shaping.<n> Experiments show that PRR substantially accelerates diffusion language model decoding while preserving generation quality.
  arXiv  Detail & Related papers  (2026-03-04T19:04:22Z)
• Just on Time: Token-Level Early Stopping for Diffusion Language Models [0.0]
  Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient.<n>We introduce a training-free, token-level early stopping approach that identifies convergence independently at each position.<n>This yields adaptive per-token freezing without task-specific fine-tuning, substantially reducing the total number of diffusion steps required.
  arXiv  Detail & Related papers  (2026-02-11T18:44:04Z)
• 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)
• EDIT: Early Diffusion Inference Termination for dLLMs Based on Dynamics of Training Gradients [6.736735746633275]
  Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete.<n>We propose EDIT, an inference-time criterion that adaptively stops denoising once sufficient reasoning stability relative to training-time reasoning is detected.
  arXiv  Detail & Related papers  (2025-11-29T23:47:47Z)
• $\mathcal{E}_0$: Enhancing Generalization and Fine-Grained Control in VLA Models via Continuized Discrete Diffusion [65.77755100137728]
  We introduce E0, a continuized discrete diffusion framework that formulates action generation as iterative denoising over quantized action tokens.<n>E0 achieves state-of-the-art performance across 14 diverse environments, outperforming strong baselines by 10.7% on average.
  arXiv  Detail & Related papers  (2025-11-26T16:14:20Z)
• WavefrontDiffusion: Dynamic Decoding Schedule or Improved Reasoning [39.57157800995735]
  We present WavefrontDiffusion, a dynamic decoding approach that expands a wavefront of active tokens outward from finalized positions.<n>Across four benchmarks in reasoning and code generation, WavefrontDiffusion achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-22T07:33:00Z)
• GateRA: Token-Aware Modulation for Parameter-Efficient Fine-Tuning [51.79350934271497]
  GateRA is a unified framework that introduces token-aware modulation to dynamically adjust the strength of PEFT updates.<n>By incorporating adaptive gating into standard PEFT branches, GateRA enables selective, token-level adaptation.<n> Experiments on multiple commonsense reasoning benchmarks demonstrate that GateRA consistently outperforms or matches prior PEFT methods.
  arXiv  Detail & Related papers  (2025-11-15T17:55:47Z)
• SPAN: Continuous Modeling of Suspicion Progression for Temporal Intention Localization [26.07264704956791]
  We propose the Suspicion Progression Analysis Network (SPAN), which shifts from discrete classification to continuous regression.<n>SPAN achieves a 2.74% mAP gain in low-frequency cases, demonstrating its superior ability to capture subtle behavioral changes.
  arXiv  Detail & Related papers  (2025-10-23T04:20:07Z)
• 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)
• Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing [77.75609817898035]
  Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content.<n>We propose textscAutoregressive textscReward textscGuided textscRe presentation textscEditing (ARGRE)<n>ARGRE explicitly models toxicity transitions within the latent representation space, enabling stable and precise reward-guided editing.
  arXiv  Detail & Related papers  (2025-09-24T03:40:32Z)
• BayesTTA: Continual-Temporal Test-Time Adaptation for Vision-Language Models via Gaussian Discriminant Analysis [41.09181390655176]
  Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but degrade significantly under textittemporally evolving distribution shifts common in real-world scenarios.<n>We formalize this practical problem as textitContinual-Temporal Test-Time Adaptation (CT-TTA), where test distributions evolve gradually over time.<n>We propose textitBayesTTA, a Bayesian adaptation framework that enforces temporally consistent predictions and dynamically aligns visual representations.
  arXiv  Detail & Related papers  (2025-07-11T14:02:54Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization [57.69385990442078]
  Large language models (LLMs) exhibit varying levels of confidence across input prompts (questions)<n>Semantic entropy measures the diversity of meaning in multiple generated answers given a prompt and uses this to modulate the magnitude of policy updates.
  arXiv  Detail & Related papers  (2025-05-18T10:20:59Z)
• Large Continual Instruction Assistant [59.585544987096974]
  Continual Instruction Tuning (CIT) is adopted to instruct Large Models to follow human intent data by data.<n>Existing update gradient would heavily destroy the performance on previous datasets during CIT process.<n>We propose a general continual instruction tuning framework to address the challenge.
  arXiv  Detail & Related papers  (2024-10-08T11:24:59Z)
• Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling [73.5602474095954]
  We study the non-asymptotic performance of approximation schemes with delayed updates under Markovian sampling. Our theoretical findings shed light on the finite-time effects of delays for a broad class of algorithms.
  arXiv  Detail & Related papers  (2024-02-19T03:08:02Z)
• StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR [46.69852287267763]
  We propose a simple alignment-free regularization method, StableEmit, to encourage MoChA to emit tokens earlier. We show that StableEmit significantly reduces the recognition errors and the emission latency simultaneously.
  arXiv  Detail & Related papers  (2021-07-01T17:49:31Z)

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.