# Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

arXiv: https://arxiv.org/abs/2601.16208 · HTML: https://mlsanity.com/paper/2601.16208/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 81 of its 93 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 81)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)

## Built on by (most cited first, 30 of 53)

- [Beyond Language Modeling: An Exploration of Multimodal Pretraining](https://mlsanity.com/paper/2603.03276/) (2026)
- [LongCat-Next: Lexicalizing Modalities as Discrete Tokens](https://mlsanity.com/paper/2603.27538/) (2026)
- [Improved Baselines with Representation Autoencoders](https://mlsanity.com/paper/2605.18324/) (2026)
- [Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models](https://mlsanity.com/paper/2605.06388/) (2026)
- [Repurposing Geometric Foundation Models for Multi-view Diffusion](https://mlsanity.com/paper/2603.22275/) (2026)
- [Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching](https://mlsanity.com/paper/2602.05951/) (2026)
- [What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion](https://mlsanity.com/paper/2605.07915/) (2026)
- [Image Generation with a Sphere Encoder](https://mlsanity.com/paper/2602.15030/) (2026)
- [Asymmetric Flow Models](https://mlsanity.com/paper/2605.12964/) (2026)
- [PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion](https://mlsanity.com/paper/2605.23902/) (2026)
- [Stable Audio 3](https://mlsanity.com/paper/2605.17991/) (2026)
- [Continuous Adversarial Flow Models](https://mlsanity.com/paper/2604.11521/) (2026)
- [Representation Forcing for Bottleneck-Free Unified Multimodal Models](https://mlsanity.com/paper/2605.31604/) (2026)
- [UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer](https://mlsanity.com/paper/2606.16255/) (2026)
- [Steering Visual Generation in Unified Multimodal Models with Understanding Supervision](https://mlsanity.com/paper/2605.05781/) (2026)
- [WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling](https://mlsanity.com/paper/2605.06407/) (2026)
- [Distilling Drifting Transformers with Representation Autoencoders](https://mlsanity.com/paper/2606.15553/) (2026)
- [Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes](https://mlsanity.com/paper/2608.05000/) (2026)
- [V-RAE: Rethinking Video Latent Spaces for Generation](https://mlsanity.com/paper/2608.13556/) (2026)
- [Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models](https://mlsanity.com/paper/2603.14186/) (2026)
- [V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising](https://mlsanity.com/paper/2603.16792/) (2026)
- [RiT: Vanilla Diffusion Transformers Suffice in Representation Space](https://mlsanity.com/paper/2605.21981/) (2026)
- [i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models](https://mlsanity.com/paper/2606.11289/) (2026)
- [HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers](https://mlsanity.com/paper/2606.13289/) (2026)
- [RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space](https://mlsanity.com/paper/2606.14700/) (2026)
- [Kelix Technical Report](https://mlsanity.com/paper/2602.09843/) (2026)
- [RAE-AR: Taming Autoregressive Models with Representation Autoencoders](https://mlsanity.com/paper/2604.01545/) (2026)
- [Taming Outlier Tokens in Diffusion Transformers](https://mlsanity.com/paper/2605.05206/) (2026)
- [Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis](https://mlsanity.com/paper/2605.20808/) (2026)
- [SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion](https://mlsanity.com/paper/2606.22568/) (2026)

## Abstract (arXiv)

Representation Autoencoders (RAEs) have shown distinct advantages in diffusion modeling on ImageNet by training in high-dimensional semantic latent spaces. In this work, we investigate whether this framework can scale to large-scale, freeform text-to-image (T2I) generation. We first scale RAE decoders on the frozen representation encoder (SigLIP-2) beyond ImageNet by training on web, synthetic, and text-rendering data, finding that while scale improves general fidelity, targeted data composition is essential for specific domains like text. We then rigorously stress-test the RAE design choices originally proposed for ImageNet. Our analysis reveals that scaling simplifies the framework: while dimension-dependent noise scheduling remains critical, architectural complexities such as wide diffusion heads and noise-augmented decoding offer negligible benefits at scale Building on this simplified framework, we conduct a controlled comparison of RAE against the state-of-the-art FLUX VAE across diffusion transformer scales from 0.5B to 9.8B parameters. RAEs consistently outperform VAEs during pretraining across all model scales. Further, during finetuning on high-quality datasets, VAE-based models catastrophically overfit after 64 epochs, while RAE models remain stable through 256 epochs and achieve consistently better performance. Across all experiments, RAE-based diffusion models demonstrate faster convergence and better generation quality, establishing RAEs as a simpler and stronger foundation than VAEs for large-scale T2I generation. Additionally, because both visual understanding and generation can operate in a shared representation space, the multimodal model can directly reason over generated latents, opening new possibilities for unified models.