# Improved Masked Image Generation with Knowledge-Augmented Token Representations

arXiv: https://arxiv.org/abs/2511.12032 · HTML: https://mlsanity.com/paper/2511.12032/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 15 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [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)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [Improved Masked Image Generation with Token-Critic](https://mlsanity.com/paper/2209.04439/) (2022)
- [Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens](https://mlsanity.com/paper/2501.07730/) (2025)
- [A Formal Evaluation of PSNR as Quality Measurement Parameter for Image Segmentation Algorithms](https://mlsanity.com/paper/1605.07116/) (2016)
- [Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis](https://mlsanity.com/paper/2406.05478/) (2024)
- [AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation](https://mlsanity.com/paper/2409.00342/) (2024)
- [Node Co-occurrence based Graph Neural Networks for Knowledge Graph Link Prediction](https://mlsanity.com/paper/2104.07396/) (2021)
- [LG-VQ: Language-Guided Codebook Learning](https://mlsanity.com/paper/2405.14206/) (2024)
- [Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text](https://mlsanity.com/paper/2503.01261/) (2025)
- [Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance](https://mlsanity.com/paper/2410.13136/) (2024)
- [AsyncDSB: Schedule-Asynchronous Diffusion Schr"odinger Bridge for Image Inpainting](https://mlsanity.com/paper/2412.08149/) (2024)

## Built on by (most cited first, 1 of 1)

- [Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation](https://mlsanity.com/paper/2605.20600/) (2026)

## Abstract (arXiv)

Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual token sequences. However, directly learning such semantic dependencies from data is challenging because the individual tokens lack clear semantic meanings, and these sequences are usually long. To address this limitation, we propose a novel Knowledge-Augmented Masked Image Generation framework, named KA-MIG, which introduces explicit knowledge of token-level semantic dependencies (i.e., extracted from the training data) as priors to learn richer representations for improving performance. In particular, we explore and identify three types of advantageous token knowledge graphs, including two positive and one negative graphs (i.e., the co-occurrence graph, the semantic similarity graph, and the position-token incompatibility graph). Based on three prior knowledge graphs, we design a graph-aware encoder to learn token and position-aware representations. After that, a lightweight fusion mechanism is introduced to integrate these enriched representations into the existing MIG methods. Resorting to such prior knowledge, our method effectively enhances the model's ability to capture semantic dependencies, leading to improved generation quality. Experimental results demonstrate that our method improves upon existing MIG for class-conditional image generation on ImageNet.