Discrete Stochastic Localization for Non-autoregressive Generation

• URL: http://arxiv.org/abs/2602.16169v1
• Date: Wed, 18 Feb 2026 04:05:40 GMT
• Title: Discrete Stochastic Localization for Non-autoregressive Generation
• Authors: Yunshu Wu, Jiayi Cheng, Partha Thakuria, Rob Brekelmans, Evangelos E. Papalexakis, Greg Ver Steeg,
• Abstract summary: We show that emphtraining alone can substantially improve the step-efficiency of MDLM/ReMDM sampling.<n>On OpenWebText, textsc fine-tuning yields large MAUVE gains at low step budgets, surpassing the MDLM+ReMDM.<n>Analyses show improved self-correction and uncertainty calibration, making remasking markedly more compute-efficient.
• Score: 17.56505846228918
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Non-autoregressive (NAR) generation reduces decoding latency by predicting many tokens in parallel, but iterative refinement often suffers from error accumulation and distribution shift under self-generated drafts. Masked diffusion language models (MDLMs) and their remasking samplers (e.g., ReMDM) can be viewed as modern NAR iterative refinement, where generation repeatedly revises a partially observed draft. In this work we show that \emph{training alone} can substantially improve the step-efficiency of MDLM/ReMDM sampling. We propose \textsc{DSL} (Discrete Stochastic Localization), which trains a single SNR-invariant denoiser across a continuum of corruption levels, bridging intermediate draft noise and mask-style endpoint corruption within one Diffusion Transformer. On OpenWebText, \textsc{DSL} fine-tuning yields large MAUVE gains at low step budgets, surpassing the MDLM+ReMDM baseline with \(\sim\)4$\times$ fewer denoiser evaluations, and matches autoregressive quality at high budgets. Analyses show improved self-correction and uncertainty calibration, making remasking markedly more compute-efficient.

Related papers

• Learn from Your Mistakes: Self-Correcting Masked Diffusion Models [31.536464269884103]
  Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models.<n>We propose a framework that trains a model to perform both unmasking and correction.<n>We name our training and sampling method Progressive Self-Correction (ProSeCo) for its unique ability to iteratively refine an entire sequence.
  arXiv  Detail & Related papers  (2026-02-12T05:17:31Z)
• Training-Free Self-Correction for Multimodal Masked Diffusion Models [61.84305395626145]
  We propose a training-free self-correction framework that exploits the inductive biases of pre-trained masked diffusion models.<n>Our method significantly improves generation quality on text-to-image generation and multimodal understanding tasks with reduced sampling steps.
  arXiv  Detail & Related papers  (2026-02-02T23:58:15Z)
• Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models [58.946955321428845]
  This work presents self-rewarding sequential Monte Carlo (SMC)<n>Our algorithm stems from the observation that most existing MDLMs rely on a confidence-based sampling strategy.<n>We introduce the trajectory-level confidence as a self-rewarding signal for assigning particle importance weights.
  arXiv  Detail & Related papers  (2026-02-02T09:21:45Z)
• Teach Diffusion Language Models to Learn from Their Own Mistakes [45.68746718883178]
  Masked Diffusion Language Models (DLMs) achieve significant speed by generating multiple tokens in parallel.<n> parallel sampling approach will introduce strong dependency errors and cause quality to deteriorate rapidly as the generation step size grows.<n>We propose Decoupled Self-Correction to maintain high-quality multi-token generation.
  arXiv  Detail & Related papers  (2026-01-10T05:04:33Z)
• Learning Unmasking Policies for Diffusion Language Models [33.44995119635116]
  Language Models (dLLMs) now match the downstream performance of their autoregressive counterparts on many tasks.<n>One particularly successful variant is masked discrete diffusion, in which a buffer filled with special mask tokens is progressively replaced with tokens sampled from the model's vocabulary.<n>In this work, we propose to train sampling procedures using reinforcement learning.
  arXiv  Detail & Related papers  (2025-12-09T20:44:33Z)
• Continuous Autoregressive Language Models [56.49239051750678]
  We introduce Continuous Autoregressive Language Models (CALM)<n>CALM uses a high-fidelity autoencoder to compress a chunk of K tokens into a single continuous vector.<n>We develop a comprehensive likelihood-free framework that enables robust training, evaluation, and controllable sampling.
  arXiv  Detail & Related papers  (2025-10-31T17:58:11Z)
• Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall [28.243098541421755]
  We introduce Loopholing, a novel and simple mechanism that preserves information via a deterministic latent pathway.<n>LDDMs achieve substantial gains-reducing generative perplexity by up to 61% over prior baselines.<n>Results also indicate that loopholing mitigates idle steps and oscillations, providing a scalable path toward high-quality non-autoregressive text generation.
  arXiv  Detail & Related papers  (2025-10-22T07:08:47Z)
• 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)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation [92.42032403795879]
  We show that pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts. We attribute their overestimation of token-level repetition probabilities to the learning bias. We find that LMs use longer-range dependencies to predict repetitive tokens than non-repetitive ones, which may be the cause of sentence-level repetition loops.
  arXiv  Detail & Related papers  (2023-07-04T07:53:55Z)
• An EM Approach to Non-autoregressive Conditional Sequence Generation [49.11858479436565]
  Autoregressive (AR) models have been the dominating approach to conditional sequence generation. Non-autoregressive (NAR) models have been recently proposed to reduce the latency by generating all output tokens in parallel. This paper proposes a new approach that jointly optimize both AR and NAR models in a unified Expectation-Maximization framework.
  arXiv  Detail & Related papers  (2020-06-29T20:58:57Z)

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.