# Scalable Autoregressive Image Generation with Mamba

arXiv: https://arxiv.org/abs/2408.12245 · HTML: https://mlsanity.com/paper/2408.12245/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Placed in

- State-space sequence models (S4, Mamba) / [Video, motion and generative Mamba models](https://mlsanity.com/ssm/video-motion-and-generative-mamba-models/)

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (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)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (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)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [Transformer-VQ: Linear-Time Transformers via Vector Quantization](https://mlsanity.com/paper/2309.16354/) (2023)

## Built on by (most cited first, 26 of 26)

- [Masked Autoencoders Are Effective Tokenizers for Diffusion Models](https://mlsanity.com/paper/2502.03444/) (2025)
- [ImageFolder: Autoregressive Image Generation with Folded Tokens](https://mlsanity.com/paper/2410.01756/) (2024)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer](https://mlsanity.com/paper/2412.10958/) (2024)
- [ControlAR: Controllable Image Generation with Autoregressive Models](https://mlsanity.com/paper/2410.02705/) (2024)
- [Autoregressive Models in Vision: A Survey](https://mlsanity.com/paper/2411.05902/) (2024)
- [Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient](https://mlsanity.com/paper/2411.17787/) (2024)
- [FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction](https://mlsanity.com/paper/2502.20313/) (2025)
- [Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression](https://mlsanity.com/paper/2505.19602/) (2025)
- [Autoregressive Image Generation with Randomized Parallel Decoding](https://mlsanity.com/paper/2503.10568/) (2025)
- [SCALAR: Scale-wise Controllable Visual Autoregressive Learning](https://mlsanity.com/paper/2507.19946/) (2025)
- [XQ-GAN: An Open-source Image Tokenization Framework for Autoregressive Generation](https://mlsanity.com/paper/2412.01762/) (2024)
- [OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models](https://mlsanity.com/paper/2503.08686/) (2025)
- [Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis](https://mlsanity.com/paper/2503.08354/) (2025)
- [Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation](https://mlsanity.com/paper/2507.13032/) (2025)
- [Semantic Context Matters: Improving Conditioning for Autoregressive Models](https://mlsanity.com/paper/2511.14063/) (2025)
- [Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective](https://mlsanity.com/paper/2507.01652/) (2025)
- [Learning Human Motion with Temporally Conditional Mamba](https://mlsanity.com/paper/2510.12573/) (2025)
- [AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers](https://mlsanity.com/paper/2511.16047/) (2025)
- [Visual Autoregressive Modelling for Monocular Depth Estimation](https://mlsanity.com/paper/2512.22653/) (2025)
- [Binary Diffusion Probabilistic Model](https://mlsanity.com/paper/2501.13915/) (2025)
- [FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry](https://mlsanity.com/paper/2505.14062/) (2025)
- [LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling](https://mlsanity.com/paper/2512.03796/) (2025)
- [Self-control: A Better Conditional Mechanism for Masked Autoregressive Model](https://mlsanity.com/paper/2412.13635/) (2024)
- [Rethinking Training Dynamics in Scale-wise Autoregressive Generation](https://mlsanity.com/paper/2512.06421/) (2025)
- [From "What" to "How": Constrained Reasoning for Autoregressive Image Generation](https://mlsanity.com/paper/2603.02712/) (2026)

## Abstract (arXiv)

We introduce AiM, an autoregressive (AR) image generative model based on Mamba architecture. AiM employs Mamba, a novel state-space model characterized by its exceptional performance for long-sequence modeling with linear time complexity, to supplant the commonly utilized Transformers in AR image generation models, aiming to achieve both superior generation quality and enhanced inference speed. Unlike existing methods that adapt Mamba to handle two-dimensional signals via multi-directional scan, AiM directly utilizes the next-token prediction paradigm for autoregressive image generation. This approach circumvents the need for extensive modifications to enable Mamba to learn 2D spatial representations. By implementing straightforward yet strategically targeted modifications for visual generative tasks, we preserve Mamba's core structure, fully exploiting its efficient long-sequence modeling capabilities and scalability. We provide AiM models in various scales, with parameter counts ranging from 148M to 1.3B. On the ImageNet1K 256*256 benchmark, our best AiM model achieves a FID of 2.21, surpassing all existing AR models of comparable parameter counts and demonstrating significant competitiveness against diffusion models, with 2 to 10 times faster inference speed. Code is available at https://github.com/hp-l33/AiM