Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models

• URL: http://arxiv.org/abs/2606.16700v1
• Date: Mon, 15 Jun 2026 13:34:38 GMT
• Title: Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models
• Abstract summary: Mask Diffusion Models (MDMs) naturally supports explicit local edits on previous outputs.<n>We propose Reflective Masking (RM), which elicits intrinsic reasoning capability in MDMs via lightweight post-training.
• Score: 40.620031617929406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While reasoning on autoregressive (AR) models is often performed by chain-of-thought reasoning and reflection, their refinement of previous outputs still relies on fully sequential generation, even when only local edits are needed. In contrast, the masking mechanism in Mask Diffusion Models (MDMs) naturally supports explicit local edits on previous outputs, allowing selective refinement without discarding previous answers and generating another from scratch. While this property more closely aligns with how humans correct mistakes by iterative local refinement, existing MDMs do not support multi-turn masking and denoising. We propose Reflective Masking (RM), which elicits such an intrinsic reasoning capability in MDMs via lightweight post-training. RM provides a native test-time scaling, where an MDM iteratively revisits and revises its prior outputs based on evolving context. To exploit insights from previous turns like AR reasoning, we further introduce History Reference, a parameter-free mechanism that leverages intermediate denoising states during revision. Our approach requires no architectural changes and is easily applicable to existing MDMs. Across diverse tasks and modalities, including text generation, Sudoku, and image editing, Reflective Masking consistently outperforms standard masking-based baselines and demonstrates strong generality, positioning RM as a fundamental primitive for reasoning on MDMs.

Related papers

• Machine Unlearning for Masked Diffusion Language Models [14.122398562530032]
  Masked diffusion language models (MDLMs) generate text by iteratively denoising masked positions in parallel.<n>We propose Masked Diffusion Unlearning (MDU), the first unlearning framework for MDLMs.<n>MDU minimizes a forward KL divergence from the prompt-conditional prediction to a prompt-masked unconditional anchor at every masked response position.
  arXiv  Detail & Related papers  (2026-05-18T11:54:11Z)
• Infinite Mask Diffusion for Few-Step Distillation [16.340935269530842]
  Masked Diffusion Models (MDMs) have emerged as a promising alternative to autoregressive models in language modeling.<n>We propose the Infinite Mask Diffusion Model (IMDM) to mitigate the theoretical bound while inheriting the benefits of MDMs.<n>IMDM surpasses existing few-step distillation methods at small step counts on LM1B and OpenWebText.
  arXiv  Detail & Related papers  (2026-05-11T13:07:03Z)
• 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)
• Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models [60.25003813232697]
  We propose Adaptive Retrieval-Augmented Masked Diffusion (ARAM) as a training-free adaptive guidance framework for Masked Diffusion Models (MDMs)<n>ARAM calibrates the guidance scale during denoising according to the Signal-to-Noise Ratio (SNR) of the distributional shift induced by retrieved context.<n>Experiments on multiple knowledge-intensive QA benchmarks show that ARAM improves overall QA performance over competitive RAG baselines.
  arXiv  Detail & Related papers  (2026-03-18T12:54:50Z)
• Unifying Masked Diffusion Models with Various Generation Orders and Beyond [56.70289720766803]
  Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation.<n>We propose order-expressive masked diffusion model (OeMDM) for a broad class of diffusion generative processes.<n>We introduce learnable-order masked diffusion model (LoMDM) which jointly learns the generation ordering and diffusion backbone.
  arXiv  Detail & Related papers  (2026-02-02T13:54:32Z)
• 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)
• Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models [19.847438086389616]
  Masked Diffusion Language Models have emerged as a promising alternative to Autoregressive Language Models.<n>We show that MDLMs exhibit a strong locality bias, favouring local over distant context.<n>We introduce a mask-agnostic loss function that encourages predictions to remain invariant to the number of appended masks.
  arXiv  Detail & Related papers  (2025-11-26T12:44:29Z)
• Fine-Tuning Masked Diffusion for Provable Self-Correction [28.338622227684453]
  Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces.<n>We introduce PRISM--Plug-in Remasking for Inference-time Self-correction of Masked Diffusions.
  arXiv  Detail & Related papers  (2025-10-01T19:15:25Z)
• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [88.65168366064061]
  We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference. Our framework leads to a family of three novel objectives that are all simulation-free, and thus scalable. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.
  arXiv  Detail & Related papers  (2024-10-10T17:18:30Z)

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.