# DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation

arXiv: https://arxiv.org/abs/2410.08159 · HTML: https://mlsanity.com/paper/2410.08159/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 47 of its 55 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [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)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [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)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Stochastic Interpolants: A Unifying Framework for Flows and Diffusions](https://mlsanity.com/paper/2303.08797/) (2023)

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

- [HART: Efficient Visual Generation with Hybrid Autoregressive Transformer](https://mlsanity.com/paper/2410.10812/) (2024)
- [Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression](https://mlsanity.com/paper/2411.16575/) (2024)
- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation](https://mlsanity.com/paper/2502.20388/) (2025)
- [ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer](https://mlsanity.com/paper/2412.07720/) (2024)
- [Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient](https://mlsanity.com/paper/2411.17787/) (2024)
- [Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis](https://mlsanity.com/paper/2412.01819/) (2024)
- [STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis](https://mlsanity.com/paper/2506.06276/) (2025)
- [Causal Diffusion Transformers for Generative Modeling](https://mlsanity.com/paper/2412.12095/) (2024)
- [CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction](https://mlsanity.com/paper/2412.06782/) (2024)
- [Next Patch Prediction for Autoregressive Visual Generation](https://mlsanity.com/paper/2412.15321/) (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)
- [The Power of Context: How Multimodality Improves Image Super-Resolution](https://mlsanity.com/paper/2503.14503/) (2025)
- [Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective](https://mlsanity.com/paper/2410.22217/) (2024)
- [Text-to-Image Synthesis: A Decade Survey](https://mlsanity.com/paper/2411.16164/) (2024)
- [Autoregressive Distillation of Diffusion Transformers](https://mlsanity.com/paper/2504.11295/) (2025)
- [MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning](https://mlsanity.com/paper/2505.12742/) (2025)
- [ARFlow: Autoregressive Flow with Hybrid Linear Attention](https://mlsanity.com/paper/2501.16085/) (2025)
- [SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation](https://mlsanity.com/paper/2505.19151/) (2025)
- [Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation](https://mlsanity.com/paper/2510.08994/) (2025)
- [SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows](https://mlsanity.com/paper/2512.04084/) (2025)
- [EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models](https://mlsanity.com/paper/2603.12252/) (2026)
- [Next Visual Granularity Generation](https://mlsanity.com/paper/2508.12811/) (2025)
- [GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation](https://mlsanity.com/paper/2504.20409/) (2025)
- [From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation](https://mlsanity.com/paper/2505.16324/) (2025)
- [Normalizing Trajectory Models](https://mlsanity.com/paper/2605.08078/) (2026)
- [LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling](https://mlsanity.com/paper/2512.03796/) (2025)
- [CAM-Seg: A Continuous-valued Embedding Approach for Semantic Image Generation](https://mlsanity.com/paper/2503.15617/) (2025)
- [D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens](https://mlsanity.com/paper/2503.17155/) (2025)

## Abstract (arXiv)

Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that the Markovian property limits the model's ability to fully utilize the generation trajectory, leading to inefficiencies during training and inference. In this paper, we propose DART, a transformer-based model that unifies autoregressive (AR) and diffusion within a non-Markovian framework. DART iteratively denoises image patches spatially and spectrally using an AR model that has the same architecture as standard language models. DART does not rely on image quantization, which enables more effective image modeling while maintaining flexibility. Furthermore, DART seamlessly trains with both text and image data in a unified model. Our approach demonstrates competitive performance on class-conditioned and text-to-image generation tasks, offering a scalable, efficient alternative to traditional diffusion models. Through this unified framework, DART sets a new benchmark for scalable, high-quality image synthesis.