Understanding and Accelerating the Training of Masked Diffusion Language Models

• URL: http://arxiv.org/abs/2605.13026v1
• Date: Wed, 13 May 2026 05:29:38 GMT
• Title: Understanding and Accelerating the Training of Masked Diffusion Language Models
• Abstract summary: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling.<n>We show how to accelerate standard MDM training while maintaining its final performance.<n>We also show faster improvements in generative perplexity, zero-shot perplexity, and downstream task performance on various benchmarks.
• Score: 104.60946175023008
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more slowly than ARMs, which may become problematic when scaling MDMs to larger models. Therefore, we ask the following question: how can we accelerate standard MDM training while maintaining its final performance? To this end, we first provide a detailed analysis of why MDM training is slow. We find that the main factor is the locality bias of language: the predictive information for a token is concentrated in nearby positions. We further investigate how this bias slows learning and suggest a simple yet effective remedy: bell-shaped time sampling as a training strategy. Notably, MDMs trained with our training recipe reach the same validation negative log-likelihood (NLL) up to $\sim4\times$ faster than standard training on One Billion Word Benchmark (LM1B). We also show faster improvements in generative perplexity, zero-shot perplexity, and downstream task performance on various benchmarks.

Related papers

• On the Trainability of Masked Diffusion Language Models via Blockwise Locality [58.92209096047332]
  Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs)<n>We study blockwise MDMs and compare them with AR-LLMs on three controlled tasks that stress different aspects of structured generation.<n>We find that standard random-masking MDMs fail to reliably learn linear regression, exhibit high variance training dynamics on graph path-finding, while outperforming AR-LLMs on Sudoku.
  arXiv  Detail & Related papers  (2026-04-27T17:44:26Z)
• Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model [74.99242687133408]
  Masked Diffusion Models (MDMs) have shown promising potential across vision, language, and cross-modal generation.<n>We introduce Co-GRPO, which reformulates MDM generation as a unified Markov Decision Process (MDP) that jointly incorporates both the model and the inference schedule.
  arXiv  Detail & Related papers  (2025-12-25T12:06:04Z)
• MDiff4STR: Mask Diffusion Model for Scene Text Recognition [59.79818820650126]
  Mask Diffusion Models (MDMs) have emerged as a promising alternative to auto-regressive models (ARMs) for vision-language tasks.<n>We show that vanilla MDM lags behind ARMs in terms of accuracy, although it improves recognition efficiency.<n>We propose MDiff4STR, a Mask Diffusion model enhanced with two key improvement strategies tailored for Scene Text Recognition.
  arXiv  Detail & Related papers  (2025-12-01T08:57:51Z)
• Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models [8.964977926797173]
  Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs)<n>High variance leads to noisier gradient estimates and unstable optimization, so even equally strong pretrained MDMs and ARMs often diverge after task-specific training.<n>We derive the first decomposition of MDM training variance into three sources: (A) masking pattern noise, (B) masking rate noise, and (C) data noise.
  arXiv  Detail & Related papers  (2025-11-22T19:04:47Z)
• MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models [28.79185891706149]
  Diffusion language models suffer from a key discrepancy between training and inference.<n>We propose a novel Masked Diffusion Policy Optimization (MDPO) to exploit the Markov property diffusion.<n>Our findings establish great potential for investigating the discrepancy between pre-training and inference of MDLMs.
  arXiv  Detail & Related papers  (2025-08-18T17:58:13Z)
• Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions [14.85882273040068]
  Masked diffusion models (MDMs) have emerged as a promising alternative approach for generative modeling over discrete domains.<n>We show that adaptive inference can boost solving accuracy in pretrained MDMs from $7$% to $approx 90$%, even outperforming ARMs with $7times$ as many parameters.
  arXiv  Detail & Related papers  (2025-02-10T18:47:21Z)
• Scaling up Masked Diffusion Models on Text [43.16800764711572]
  Masked diffusion models (MDMs) have shown promise in language modeling.<n>This paper establishes the first scaling law for MDMs.<n>We train a family of MDMs with up to 1.1 billion (B) parameters to evaluate their performance against larger sizes.
  arXiv  Detail & Related papers  (2024-10-24T08:01:22Z)
• Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling [47.82616476928464]
  Masked diffusion models (MDMs) have emerged as a popular research topic for generative modeling of discrete data.<n>We show that both training and sampling of MDMs are theoretically free from the time variable.<n>We identify, for the first time, an underlying numerical issue, even with the commonly used 32-bit floating-point precision.
  arXiv  Detail & Related papers  (2024-09-04T17:48:19Z)
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning [80.24059713295165]
  The Logarithm of Maximum Evidence (LogME) can be used to assess pre-trained models for transfer learning. Compared to brute-force fine-tuning, LogME brings over $3000times$ speedup in wall-clock time.
  arXiv  Detail & Related papers  (2021-02-22T13:58:11Z)

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.