# Halton Scheduler For Masked Generative Image Transformer

arXiv: https://arxiv.org/abs/2503.17076 · HTML: https://mlsanity.com/paper/2503.17076/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 78 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 30 of 53)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Pseudo Numerical Methods for Diffusion Models on Manifolds](https://mlsanity.com/paper/2202.09778/) (2022)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)

## Built on by (most cited first, 30 of 32)

- [Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking](https://mlsanity.com/paper/2505.24857/) (2025)
- [Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation](https://mlsanity.com/paper/2602.11401/) (2026)
- [Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization](https://mlsanity.com/paper/2510.08233/) (2025)
- [Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2509.19244/) (2025)
- [Planner Aware Path Learning in Diffusion Language Models Training](https://mlsanity.com/paper/2509.23405/) (2025)
- [Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing](https://mlsanity.com/paper/2510.21961/) (2025)
- [MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization](https://mlsanity.com/paper/2504.00999/) (2025)
- [Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation](https://mlsanity.com/paper/2507.01957/) (2025)
- [Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion](https://mlsanity.com/paper/2510.04525/) (2025)
- [Learnable Sampler Distillation for Discrete Diffusion Models](https://mlsanity.com/paper/2509.19962/) (2025)
- [Partition Generative Modeling: Masked Modeling Without Masks](https://mlsanity.com/paper/2505.18883/) (2025)
- [Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings](https://mlsanity.com/paper/2509.22925/) (2025)
- [Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models](https://mlsanity.com/paper/2512.14008/) (2025)
- [Fixed-Point Masked Generative Modeling](https://mlsanity.com/paper/2605.31215/) (2026)
- [Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling](https://mlsanity.com/paper/2510.17171/) (2025)
- [Categorical Reparameterization with Denoising Diffusion models](https://mlsanity.com/paper/2601.00781/) (2026)
- [Adapting Diffusion Language Models for Lossless Pixel-Level Image Transmission](https://mlsanity.com/paper/2606.06273/) (2026)
- [Tensor-Train Joint Modeling for Few-Step Discrete Diffusion](https://mlsanity.com/paper/2607.03788/) (2026)
- [From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion](https://mlsanity.com/paper/2609.01043/) (2026)
- [UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation](https://mlsanity.com/paper/2508.05399/) (2025)
- [Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation](https://mlsanity.com/paper/2509.19592/) (2025)
- [BIGFix: Bidirectional Image Generation with Token Fixing](https://mlsanity.com/paper/2510.12231/) (2025)
- [MixAR: Mixture Autoregressive Image Generation](https://mlsanity.com/paper/2511.12181/) (2025)
- [Spanning Tree Autoregressive Visual Generation](https://mlsanity.com/paper/2511.17089/) (2025)
- [DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models](https://mlsanity.com/paper/2511.21415/) (2025)
- [FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation](https://mlsanity.com/paper/2601.23182/) (2026)
- [Accelerating Masked Image Generation by Learning Controlled Latent Dynamics](https://mlsanity.com/paper/2602.23996/) (2026)
- [Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems](https://mlsanity.com/paper/2606.28398/) (2026)
- [Context-weighted Discrete Flow Matching](https://mlsanity.com/paper/2607.21427/) (2026)
- [IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion Models](https://mlsanity.com/paper/2610.03641/) (2026)

## Abstract (arXiv)

Masked Generative Image Transformers (MaskGIT) have emerged as a scalable and efficient image generation framework, able to deliver high-quality visuals with low inference costs. However, MaskGIT's token unmasking scheduler, an essential component of the framework, has not received the attention it deserves. We analyze the sampling objective in MaskGIT, based on the mutual information between tokens, and elucidate its shortcomings. We then propose a new sampling strategy based on our Halton scheduler instead of the original Confidence scheduler. More precisely, our method selects the token's position according to a quasi-random, low-discrepancy Halton sequence. Intuitively, that method spreads the tokens spatially, progressively covering the image uniformly at each step. Our analysis shows that it allows reducing non-recoverable sampling errors, leading to simpler hyper-parameters tuning and better quality images. Our scheduler does not require retraining or noise injection and may serve as a simple drop-in replacement for the original sampling strategy. Evaluation of both class-to-image synthesis on ImageNet and text-to-image generation on the COCO dataset demonstrates that the Halton scheduler outperforms the Confidence scheduler quantitatively by reducing the FID and qualitatively by generating more diverse and more detailed images. Our code is at https://github.com/valeoai/Halton-MaskGIT.