No Compute Left Behind: Rethinking Reasoning and Sampling with Masked Diffusion Models

• URL: http://arxiv.org/abs/2510.19990v1
• Date: Wed, 22 Oct 2025 19:41:27 GMT
• Title: No Compute Left Behind: Rethinking Reasoning and Sampling with Masked Diffusion Models
• Authors: Zachary Horvitz, Raghav Singhal, Hao Zou, Carles Domingo-Enrich, Zhou Yu, Rajesh Ranganath, Kathleen McKeown,
• Abstract summary: Masked diffusion language models are trained to in-fill positions in randomly masked sequences.<n>We propose reasoning-as-infilling and multi-token entropy decoding.<n>Our work demonstrates that the training and compute used by MDLMs unlock many new inference and post-training methods.
• Score: 42.158430350703505
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Masked diffusion language models (MDLMs) are trained to in-fill positions in randomly masked sequences, in contrast to next-token prediction models. Discussions around MDLMs focus on two benefits: (1) any-order decoding and 2) multi-token decoding. However, we observe that for math and coding tasks, any-order algorithms often underperform or behave similarly to left-to-right sampling, and standard multi-token decoding significantly degrades performance. At inference time, MDLMs compute the conditional distribution of all masked positions. A natural question is: How can we justify this additional compute when left-to-right one-token-at-a-time decoding is on par with any-order decoding algorithms? First, we propose reasoning-as-infilling. By using MDLMs to infill a reasoning template, we can structure outputs and distinguish between reasoning and answer tokens. In turn, this enables measuring answer uncertainty during reasoning, and early exits when the model converges on an answer. Next, given an answer, reasoning-as-infilling enables sampling from the MDLM posterior over reasoning traces conditioned on the answer, providing a new source of high-quality data for post-training. On GSM8k, we observe that fine-tuning LLaDA-8B Base on its posterior reasoning traces provides a performance boost on par with fine-tuning on human-written reasoning traces. Additionally, given an answer, reasoning-as-infilling provides a method for scoring the correctness of the reasoning process at intermediate steps. Second, we propose multi-token entropy decoding (MED), a simple adaptive sampler that minimizes the error incurred by decoding positions in parallel based on the conditional entropies of those positions. MED preserves performance across benchmarks and leads to 2.7x fewer steps. Our work demonstrates that the training and compute used by MDLMs unlock many new inference and post-training methods.

Related papers

• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow [30.201913054064363]
  Masked Diffusion Language Models promise parallel token generation and arbitrary-order decoding.<n>We characterize MDLM behavior along two dimensions -- parallelism strength and generation order.<n>We evaluate eight mainstream MDLMs on 58 benchmarks spanning knowledge, reasoning, and programming.
  arXiv  Detail & Related papers  (2026-01-22T02:39:36Z)
• 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)
• Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding [21.609237262034636]
  Autoregressive decoding in large language models (LLMs) requires $mathcalO(n)$ sequential steps for $n$ tokens.<n>We propose Learning to Parallel Decode (Learn2PD), a framework that trains a lightweight and adaptive filter model to predict, for each token position, whether the current prediction matches the final output.<n>This learned filter approximates an oracle parallel decoding strategy that unmasks tokens only when correctly predicted.
  arXiv  Detail & Related papers  (2025-09-29T17:59:54Z)
• Diffusion Language Models Know the Answer Before Decoding [56.96815863705218]
  Diffusion language models (DLMs) have emerged as an alternative to autoregressive approaches.<n>Our work highlights and leverage an overlooked property of DLMs early answer convergence.<n>We introduce Prophet, a training-free fast decoding paradigm that enables early commit decoding.
  arXiv  Detail & Related papers  (2025-08-27T15:40:25Z)
• Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition [11.858707687894757]
  Large Reasoning Models (LRMs) are criticized for the excessively lengthy Chain-of-Thought (CoT) to derive the final answer.<n>This paper introduces Multi-Turn Decomposition (MinD) to decode conventional CoT into a sequence of explicit, structured, and turn-wise interactions.<n>MinD can achieve up to 70% reduction in both output token usage and time to first token (TTFT)
  arXiv  Detail & Related papers  (2025-05-26T10:18:57Z)
• 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)
• Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning [53.57895922042783]
  Large Language Models (LLMs) excel at reasoning and planning when trained on chainof-thought (CoT) data.<n>We propose a hybrid representation of the reasoning process, where we partially abstract away the initial reasoning steps using latent discrete tokens.
  arXiv  Detail & Related papers  (2025-02-05T15:33:00Z)
• GRACE: Discriminator-Guided Chain-of-Thought Reasoning [75.35436025709049]
  We propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE) to steer the decoding process towards producing correct reasoning steps. GRACE employs a discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates.
  arXiv  Detail & Related papers  (2023-05-24T09:16:51Z)

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.