mlsanityData to 14 Oct 2026

Effective and Efficient Masked Image Generation Models

arXiv 2503.07197 ↗First posted 10 Mar 2025cs.CV cs.LGcited by 13

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Although masked image generation models and masked diffusion models are designed with different motivations and objectives, we observe that they can be unified within a single framework. Building upon this insight, we carefully explore the design space of training and sampling, identifying key factors that contribute to both performance and efficiency. Based on the improvements observed during this exploration, we develop our model, referred to as eMIGM. Empirically, eMIGM demonstrates strong performance on ImageNet generation, as measured by Fr'echet Inception Distance (FID). In particular, on ImageNet 256×256, with similar number of function evaluations (NFEs) and model parameters, eMIGM outperforms the seminal VAR. Moreover, as NFE and model parameters increase, eMIGM achieves performance comparable to the state-of-the-art continuous diffusion model REPA while requiring less than 45% of the NFE. Additionally, on ImageNet 512×512, eMIGM outperforms the strong continuous diffusion model EDM2. Code is available at https://github.com/ML-GSAI/eMIGM.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 48 of its 55 references that are in the map. First posted on arXiv 10 Mar 2025.

Builds on

48 of 55 references.

Closest ancestors · 23

Same direction, newest first

  1. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models14 Oct
  2. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models14 Oct
  3. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think9 Oct
  4. 2024Analysis of Classifier-Free Guidance Weight Schedulers19 Apr
  5. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models11 Apr
  6. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
  7. 2023DiffiT: Diffusion Vision Transformers for Image Generation4 Dec
  8. 2023Diffusion Models Without Attention30 Nov
  9. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling26 Oct
  10. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation1 Mar
  11. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  12. 2022Scalable Diffusion Models with Transformers19 Dec
11 more
  1. 2022Score-based Continuous-time Discrete Diffusion Models30 Nov
  2. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models2 Nov
  3. 2022All are Worth Words: A ViT Backbone for Diffusion Models25 Sep
  4. 2022Classifier-Free Diffusion Guidance26 Jul
  5. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps2 Jun
  6. 2022A Continuous Time Framework for Discrete Denoising Models30 May
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  8. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  11. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 25

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  7. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  8. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  9. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  10. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  11. 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
  12. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
13 more
  1. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  2. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  4. 2024Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Datacited by 381
  5. 2024Discrete Flow Matchingcited by 317
  6. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 305
  7. 2022MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesiscited by 227
  8. 2022DiffusionBERT: Improving Generative Masked Language Models with Diffusion Modelscited by 214
  9. 2024Scaling up Masked Diffusion Models on Textcited by 199
  10. 2023A Reparameterized Discrete Diffusion Model for Text Generationcited by 152
  11. 2024HART: Efficient Visual Generation with Hybrid Autoregressive Transformercited by 132
  12. 2024AdaNAT: Exploring Adaptive Policy for Token-Based Image Generationcited by 13
  13. 2024Bag of Design Choices for Inference of High-Resolution Masked Generative Transformercited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 7.

13 papers.

Sort:

By area:

  1. 2025LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuningcited by 148
  2. 2025Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspectivecited by 34
  3. 2026LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Modelcited by 10
  4. 2025Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Boundscited by 8
  5. 2025Plug-and-Play Context Feature Reuse for Efficient Masked Generationcited by 5
  6. 2026Fixed-Point Masked Generative Modelingcited by 5
  7. 2025Masked Diffusion Models as Energy Minimizationcited by 3
  8. 2026Masked Diffusion Generative Recommendationcited by 2
  9. 2025DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Modelscited by 0
  10. 2026Accelerating Masked Image Generation by Learning Controlled Latent Dynamicscited by 0
  11. 2026Diffusion Image Generation with Explicit Modeling of Data Manifold Geometrycited by 0
  12. 2026Where Does Generative Difficulty Reside? An Empirical Study of Target Representationscited by 0
1 more
  1. 2026Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Masked Diffusion Models Are Fast Distribution Learners
  2. 2025Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Ability
  3. 2025Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion
  4. 2025Dimathtt[M]O: Distilling Masked Diffusion Models into One-step Generator
  5. 2024Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt
  6. 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
  7. 2024On Improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
  8. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices