Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding

• URL: http://arxiv.org/abs/2603.04514v1
• Date: Wed, 04 Mar 2026 19:04:22 GMT
• Title: Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding
• Abstract summary: 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.
• Score: 18.99795632160924
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice, leading to substantial redundant refinement and motivating refinement control over the denoising process. Existing approaches typically assess refinement necessity from instantaneous, step-level signals under a fixed decoding process. In contrast, whether a token has converged is defined by how its prediction changes along its future refinement trajectory. Moreover, changing the refinement rule reshapes future refinement trajectories, which in turn determine how refinement rules should be formulated, making refinement control inherently dynamic. We propose \emph{Progressive Refinement Regulation} (PRR), a progressive, trajectory-grounded refinement control framework that derives a token-level notion of empirical convergence progress from full decoding rollouts. Based on this signal, PRR learns a lightweight token-wise controller to regulate refinement via temperature-based distribution shaping under a progressive self-evolving training scheme. Experiments show that PRR substantially accelerates diffusion language model decoding while preserving generation quality.

Related papers

• SATB-VR: Training Few-Step Video Restoration Diffusion Model using SNR-Aware Trajectory Blending [55.764018145256216]
  We present SATB-VR, a few-step paradigm that jump-starts the denoising process via an auxiliary predictor.<n>We show that SATB-VR performs favorably against existing approaches on synthetic, real-world, and AIGC benchmarks.
  arXiv  Detail & Related papers  (2026-06-27T01:32:16Z)
• Constrained Code Generation with Discrete Diffusion [40.46661913038948]
  Constrained Diffusion for Code (CDC) is a training-free neurosymbolic inference framework for code generation.<n>CDC integrates constraint satisfaction directly into the reverse denoising process.<n>CDC consistently improves constraint satisfaction in functional correctness, security, and even syntax.
  arXiv  Detail & Related papers  (2026-05-16T06:15:47Z)
• AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers [24.937985157569823]
  We argue that such timestep-agnostic alignment is suboptimal because the useful granularity of representation supervision changes systematically with the signal-to-noise ratio.<n>In high-noise regimes, diffusion models benefit more from coarse semantic and layout-level anchoring, whereas in low-noise regimes, the training signal should emphasize spatially detailed and structurally faithful refinement.<n>This non-stationary alignment behavior creates a representational mismatch for static single-level supervisors.
  arXiv  Detail & Related papers  (2026-05-05T03:07:29Z)
• A$^{2}$V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production [0.9384603486206738]
  A$2$V-SLP learns articulator-wise disentangled latent distributions rather than deterministic embeddings.<n>A disentangled Variational Autoencoder encodes ground-truth sign pose sequences and extracts articulator-specific mean and variance vectors.
  arXiv  Detail & Related papers  (2026-02-12T12:07:32Z)
• Reversible Diffusion Decoding for Diffusion Language Models [69.10149777322108]
  Reversible Diffusion Decoding (RDD) is a decoding framework that introduces reversibility into block-wise diffusion generation.<n>RDD detects stagnation as a state-dependent failure of the reverse process and enables efficient backtracking to earlier blocks.<n> Experiments show that RDD improves generation robustness and quality over baselines with minimal computational overhead.
  arXiv  Detail & Related papers  (2026-01-29T12:52:33Z)
• ILRR: Inference-Time Steering Method for Masked Diffusion Language Models [8.458339111154585]
  We introduce Iterative Latent Representation Refinement (ILRR), a learning-free framework for steering DLMs using a single reference sequence.<n>ILRR guides generation by dynamically aligning the internal activations of the generated sequence with those of a given reference throughout the denoising process.<n>We further introduce Spatially Modulated Steering, an extension that enables steering long texts using shorter references by regulating guidance intensity across the sequence.
  arXiv  Detail & Related papers  (2026-01-29T12:48:59Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• 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)
• From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model [72.73512218682187]
  We introduce ReDiff, a refining-enhanced diffusion framework that teaches the model to identify and correct its own errors.<n>Our approach features a two-stage training process: first, we instill a foundational revision capability by training the model to revise synthetic errors; second, we implement a novel online self-correction loop.<n>This mistake-driven learning endows the model with the crucial ability to revisit and refine its already generated output, effectively breaking the error cascade.
  arXiv  Detail & Related papers  (2025-10-22T06:58:55Z)
• Confidence-Modulated Speculative Decoding for Large Language Models [0.0]
  This paper proposes an information-theoretic framework for speculative decoding based on confidence-modulated drafting.<n> Experiments on machine translation and summarization tasks demonstrate significant speedups over standard speculative decoding.
  arXiv  Detail & Related papers  (2025-08-21T09:06:31Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching [56.30231216917128]
  FELLE is an autoregressive model that integrates language modeling with token-wise flow matching.<n>For each continuous-valued token, FELLE modifies the general prior distribution in flow matching by incorporating information from the previous step.<n>FELLE generates continuous-valued tokens hierarchically, conditioned on the language model's output.
  arXiv  Detail & Related papers  (2025-02-16T13:54:32Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)

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.