Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models

• URL: http://arxiv.org/abs/2506.19037v3
• Date: Thu, 24 Jul 2025 20:58:50 GMT
• Title: Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models
• Authors: Omer Luxembourg, Haim Permuter, Eliya Nachmani,
• Abstract summary: Masked diffusion language models promise fast, non-autoregressive text generation.<n>Existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel.<n>We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-free method that partitions sequence positions into non-adjacent dilated groups and unmasked them in parallel.
• Score: 13.575063025878208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow, autoregressive behavior. We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-free method that partitions sequence positions into non-adjacent dilated groups and unmasked them in parallel so as to minimize an upper bound on joint entropy gain at each denoising step. By explicitly trading off the number of network calls against generation quality, DUS recovers most of the performance lost under traditional parallel unmasking strategies. Across math (GSM8K, MATH500), code (HumanEval, MBPP) and general-knowledge benchmarks (BBH, MMLU-Pro), DUS outperforms confidence-based planners, without modifying the underlying denoiser, and reveals the true speed-quality frontier of MDLMs.

Related papers

• Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models [24.78455014605002]
  Diffusion Language Models generate text by iteratively denoising a masked sequence.<n>Standard decoding follows a greedy rule: unmask the most confident positions.<n>We present SOAR, a training-free decoding algorithm that adapts its behavior to the model's uncertainty.
  arXiv  Detail & Related papers  (2026-02-11T15:41:09Z)
• 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)
• dUltra: Ultra-Fast Diffusion Language Models via Reinforcement Learning [36.12942468805232]
  Masked diffusion language models offer potential for parallel token generation.<n>Open-source MDLMs decode fewer than 5 tokens per model forward pass.<n>dUltra learns unmasking strategies for efficient parallel decoding.
  arXiv  Detail & Related papers  (2025-12-24T23:31:48Z)
• Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models [63.50827603618498]
  We propose Sparse-LaViDa, a modeling framework that truncates unnecessary masked tokens at each inference step to accelerate MDM sampling.<n>Built upon the state-of-the-art unified MDM LaViDa-O, Sparse-LaViDa achieves up to a 2x speedup across diverse tasks.
  arXiv  Detail & Related papers  (2025-12-16T02:06:06Z)
• 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)
• Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction [10.813064862132379]
  We present STAMP: Simultaneous Textual All-Mask Prediction, an MLLM that embodies this paradigm.<n>After generating a textual response, STAMP predicts an entire segmentation mask in a single forward pass by treating it as a parallel "fill-in-the-blank" task over image patches.<n>This design maintains the MLLM's dialogue ability by avoiding conflicting objectives, enables high segmentation performance by leveraging rich, bidirectional spatial context for all mask tokens, and achieves exceptional speed.
  arXiv  Detail & Related papers  (2025-11-29T08:52:41Z)
• Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models [51.12873073612084]
  Masked Diffusion Models (MDMs) as language models generate by iteratively unmasking tokens, yet their performance depends on the inference time order of unmasking.<n>We propose Lookahead Unmasking (LookUM), which addresses these concerns by reformulating sampling as path selection over all possible unmasking orders.<n>LookUM requires only two to three paths to achieve peak performance, demonstrating remarkably efficient path selection.
  arXiv  Detail & Related papers  (2025-11-04T02:37:37Z)
• Soft-Masked Diffusion Language Models [35.191030145577145]
  We introduce soft-masking (SM), a novel method that dynamically blends the embedding of the mask token with the embeddings of the top-$k$ predicted tokens.<n>We demonstrate that continuing pretraining a 169M parameter model with SM leads to improved perplexity and MAUVE scores.<n>We finetune two state-of-the-art diffusion models, Dream-7B and Dream-Coder-7B, with SM.
  arXiv  Detail & Related papers  (2025-10-20T06:42:03Z)
• Sampling from Your Language Model One Byte at a Time [82.71473348639489]
  Tokenization can introduce distortion into the model's generations.<n> mismatching tokenizers often hinder model composition and interoperability.<n>We present an inference-time method to convert any autoregressive LM with a BPE tokenizer into a character-level or byte-level LM.
  arXiv  Detail & Related papers  (2025-06-17T02:37:04Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [50.9948753314669]
  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)
• Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking [17.511240770486452]
  Masked diffusion models (MDMs) have shown competitive performance compared to autoregressive models (ARMs) for language modeling.<n>We introduce EB-Sampler, a drop-in replacement for existing samplers, utilizing an Entropy Bounded unmasking procedure.<n> EB-Sampler accelerates sampling from current state of the art MDMs by roughly 2-3x on standard coding and math reasoning benchmarks without loss in performance.
  arXiv  Detail & Related papers  (2025-05-30T17:52:55Z)
• Partition Generative Modeling: Masked Modeling Without Masks [1.4110007887109783]
  Partition Generative Models (PGMs) is a novel approach to masked generative modeling (MGMs)<n>Experiments on OpenWebText with a context length of 1024 tokens demonstrate that PGMs deliver at least 5x improvements in both latency and throughput.
  arXiv  Detail & Related papers  (2025-05-24T21:44:32Z)
• Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking [17.371579113481644]
  Masked diffusion models (MDM) are powerful generative models for discrete data that generate samples by progressively unmasking tokens in a sequence.<n>We propose the Partial masking scheme (Prime), which augments MDM by allowing tokens to take intermediate states between the masked and unmasked states.<n>Our method demonstrates superior performance across a diverse set of generative modeling tasks.
  arXiv  Detail & Related papers  (2025-05-24T04:16:40Z)
• Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions [41.45689715854447]
  We introduce Insertion Language Models (ILMs), which learn to insert tokens at arbitrary positions in a sequence.<n>ILMs can represent strong dependencies between tokens, and their ability to generate sequences in arbitrary order allows them to accurately model sequences.
  arXiv  Detail & Related papers  (2025-05-09T03:29:15Z)
• Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding [55.2480439325792]
  In arbitrary-order language models, it is an open question how to sample tokens in parallel from the correct joint distribution.<n>We find that a different class of models, any-subset autoregressive models (AS-ARMs), holds the solution.<n>We show that AS-ARMs achieve state-of-the-art performance among sub-200M parameter models on infilling benchmark tasks, and nearly match the performance of models 50X larger on code generation.
  arXiv  Detail & Related papers  (2025-04-29T06:33:13Z)
• Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection [49.15148871877941]
  Next-token distribution outputs offer a theoretically appealing approach for detection of large language models (LLMs)<n>We propose the Perplexity Attention Weighted Network (PAWN), which uses the last hidden states of the LLM and positions to weight the sum of a series of features based on metrics from the next-token distribution across the sequence length.<n>PAWN shows competitive and even better performance in-distribution than the strongest baselines with a fraction of their trainable parameters.
  arXiv  Detail & Related papers  (2025-01-07T17:00:49Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy [28.62712217754428]
  We present dynamic alignment Mask CTC. We introduce two methods: (1) Aligned Cross Entropy (AXE), finding the monotonic alignment that minimizes the cross-entropy loss through dynamic programming, (2) Dynamic Rectification, creating new training samples by replacing some masks with model predicted tokens. Our experiments on WSJ dataset demonstrated that not only AXE loss but also the rectification method could improve the WER performance of Mask CTC.
  arXiv  Detail & Related papers  (2023-03-14T08:01:21Z)
• Efficient Masked Autoencoders with Self-Consistency [34.7076436760695]
  Masked image modeling (MIM) has been recognized as a strong self-supervised pre-training method in computer vision. We propose efficient masked autoencoders with self-consistency (EMAE) to improve the pre-training efficiency. EMAE consistently obtains state-of-the-art transfer ability on a variety of downstream tasks, such as image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2023-02-28T09:21:12Z)
• Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models [57.20432226304683]
  Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. We propose a novel end-to-end streaming NAR speech recognition system. We show that the proposed method improves online ASR recognition in low latency conditions.
  arXiv  Detail & Related papers  (2021-07-20T11:42:26Z)
• Masksembles for Uncertainty Estimation [60.400102501013784]
  Deep neural networks have amply demonstrated their prowess but estimating the reliability of their predictions remains challenging. Deep Ensembles are widely considered as being one of the best methods for generating uncertainty estimates but are very expensive to train and evaluate. MC-Dropout is another popular alternative, which is less expensive, but also less reliable.
  arXiv  Detail & Related papers  (2020-12-15T14:39:57Z)
• Improving Self-supervised Pre-training via a Fully-Explored Masked Language Model [57.77981008219654]
  Masked Language Model (MLM) framework has been widely adopted for self-supervised language pre-training. We propose a fully-explored masking strategy, where a text sequence is divided into a certain number of non-overlapping segments.
  arXiv  Detail & Related papers  (2020-10-12T21:28:14Z)
• Semi-Autoregressive Training Improves Mask-Predict Decoding [119.8412758943192]
  We introduce a new training method for conditional masked language models, SMART, which mimics the semi-autoregressive behavior of mask-predict. Models trained with SMART produce higher-quality translations when using mask-predict decoding, effectively closing the remaining performance gap with fully autoregressive models.
  arXiv  Detail & Related papers  (2020-01-23T19:56:35Z)

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.