mlsanityData to 14 Oct 2026

MASQ: Accelerating Masked Diffusion via Stage-Wise Multi-Precision Quantization

arXiv 2605.23226 ↗First posted 22 May 2026cs.ARcited by 0

Not on the map. Why?

Abstract (arXiv)

Masked diffusion enables region-specific image synthesis but suffers from computational redundancy, since the entire image is processed each timestep even though only the masked region requires generation. To address this, we introduce MASQ, a hardware-software co-designed accelerator for masked diffusion. Our approach performs stage-wise MXINT8/4/2 precision assignment that dynamically reflects spatial and semantic importance, complemented by timestep-aware scheduling and optimized non-matrix operations. MASQ features a block-wise multi-precision compute engine and mask management unit, efficiently handling our approach. It achieves up to 16.06x and 5.39x speedup and 4.18x and 4.93x energy-efficiency gain over A100 and Orin NX, respectively, while preserving quality.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 38 references that are in the map. First posted on arXiv 22 May 2026.

Builds on

15 of 38 references.

References · 15

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  5. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  8. 2016Improved Techniques for Training GANscited by 2,970
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  10. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  11. 2021A White Paper on Neural Network Quantizationcited by 472
  12. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 336
3 more
  1. 2022SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Modelcited by 278
  2. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 233
  3. 2023DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Modelscited by 31

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TreeQ: Pushing the Quantization Boundary of Diffusion Transformer via Tree-Structured Mixed-Precision Search
  2. 2025SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity
  3. 2025Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling
  4. 2026DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction
  5. 2025MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantization
  6. 2026APT: Accelerating Diffusion Transformers via Attention Probability-Guided Pruning and Quantization
  7. 2026CentriQ: Calibration-Free Quantization of Diffusion Transformers via Exact Mean Centering
  8. 2026TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models