# Frequency Autoregressive Image Generation with Continuous Tokens

arXiv: https://arxiv.org/abs/2503.05305 · HTML: https://mlsanity.com/paper/2503.05305/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 54 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 30 of 47)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [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)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [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)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://mlsanity.com/paper/2408.11039/) (2024)

## Built on by (most cited first, 27 of 27)

- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective](https://mlsanity.com/paper/2507.08801/) (2025)
- [FARMER: Flow AutoRegressive Transformer over Pixels](https://mlsanity.com/paper/2510.23588/) (2025)
- [VideoMAR: Autoregressive Video Generatio with Continuous Tokens](https://mlsanity.com/paper/2506.14168/) (2025)
- [NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering](https://mlsanity.com/paper/2503.07076/) (2025)
- [Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy](https://mlsanity.com/paper/2510.09012/) (2025)
- [Continuous Visual Autoregressive Generation via Score Maximization](https://mlsanity.com/paper/2505.07812/) (2025)
- [FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens](https://mlsanity.com/paper/2506.01583/) (2025)
- [Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation](https://mlsanity.com/paper/2506.18226/) (2025)
- [Context-Aware Autoregressive Models for Multi-Conditional Image Generation](https://mlsanity.com/paper/2505.12274/) (2025)
- [Next Visual Granularity Generation](https://mlsanity.com/paper/2508.12811/) (2025)
- [Learning to Refine: Spectral-Decoupled Iterative Refinement Framework for Precipitation Nowcasting](https://mlsanity.com/paper/2606.02661/) (2026)
- [DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning](https://mlsanity.com/paper/2506.09644/) (2025)
- [MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation](https://mlsanity.com/paper/2604.06966/) (2026)
- [Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal](https://mlsanity.com/paper/2605.27919/) (2026)
- [Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and Generation](https://mlsanity.com/paper/2511.01593/) (2025)
- [Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm](https://mlsanity.com/paper/2511.11727/) (2025)
- [LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling](https://mlsanity.com/paper/2512.03796/) (2025)
- [RAE-AR: Taming Autoregressive Models with Representation Autoencoders](https://mlsanity.com/paper/2604.01545/) (2026)
- [Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution](https://mlsanity.com/paper/2605.26032/) (2026)
- [Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models](https://mlsanity.com/paper/2509.23919/) (2025)
- [DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models](https://mlsanity.com/paper/2511.21415/) (2025)
- [Guiding Visual Autoregressive Models through Spectrum Weakening](https://mlsanity.com/paper/2511.22991/) (2025)
- [Rethinking Training Dynamics in Scale-wise Autoregressive Generation](https://mlsanity.com/paper/2512.06421/) (2025)
- [MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts](https://mlsanity.com/paper/2607.00371/) (2026)
- [Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning](https://mlsanity.com/paper/2608.02432/) (2026)
- [Efficient Training with Foresight: Multi-Token Auxiliary Supervision for Autoregressive Image Generation](https://mlsanity.com/paper/2608.25386/) (2026)

## Abstract (arXiv)

Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap, image autoregressive models may require a systematic reevaluation from two perspectives: tokenizer format and regression direction. In this paper, we introduce the frequency progressive autoregressive (FAR) paradigm and instantiate FAR with the continuous tokenizer. Specifically, we identify spectral dependency as the desirable regression direction for FAR, wherein higher-frequency components build upon the lower one to progressively construct a complete image. This design seamlessly fits the causality requirement for autoregressive models and preserves the unique spatial locality of image data. Besides, we delve into the integration of FAR and the continuous tokenizer, introducing a series of techniques to address optimization challenges and improve the efficiency of training and inference processes. We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset and verify its potential on text-to-image generation.