# Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

arXiv: https://arxiv.org/abs/2507.01467 · HTML: https://mlsanity.com/paper/2507.01467/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 55 of its 60 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Placed in

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

## Builds on (most cited first, 30 of 55)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (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)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [All are Worth Words: A ViT Backbone for Diffusion Models](https://mlsanity.com/paper/2209.12152/) (2022)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Diffusion Autoencoders: Toward a Meaningful and Decodable Representation](https://mlsanity.com/paper/2111.15640/) (2021)
- [Simple diffusion: End-to-end diffusion for high resolution images](https://mlsanity.com/paper/2301.11093/) (2023)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation](https://mlsanity.com/paper/2303.00848/) (2023)
- [VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance](https://mlsanity.com/paper/2204.08583/) (2022)
- [Unleashing Text-to-Image Diffusion Models for Visual Perception](https://mlsanity.com/paper/2303.02153/) (2023)

## Built on by (most cited first, 30 of 102)

- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [Latent Diffusion Model without Variational Autoencoder](https://mlsanity.com/paper/2510.15301/) (2025)
- [Representation Fr'echet Loss for Visual Generation](https://mlsanity.com/paper/2604.28190/) (2026)
- [Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis](https://mlsanity.com/paper/2603.06507/) (2026)
- [Improved Baselines with Representation Autoencoders](https://mlsanity.com/paper/2605.18324/) (2026)
- [One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation](https://mlsanity.com/paper/2512.07829/) (2025)
- [D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models](https://mlsanity.com/paper/2605.05204/) (2026)
- [Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion](https://mlsanity.com/paper/2512.04926/) (2025)
- [VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models](https://mlsanity.com/paper/2510.18457/) (2025)
- [Guiding a Diffusion Transformer with the Internal Dynamics of Itself](https://mlsanity.com/paper/2512.24176/) (2025)
- [PixelGen: Improving Pixel Diffusion with Perceptual Supervision](https://mlsanity.com/paper/2602.02493/) (2026)
- [Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders](https://mlsanity.com/paper/2602.10099/) (2026)
- [SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder](https://mlsanity.com/paper/2512.11749/) (2025)
- [Stable Velocity: A Variance Perspective on Flow Matching](https://mlsanity.com/paper/2602.05435/) (2026)
- [3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image](https://mlsanity.com/paper/2604.04406/) (2026)
- [Representation Distribution Matching for One-Step Visual Generation](https://mlsanity.com/paper/2607.02375/) (2026)
- [RefAlign: Representation Alignment for Reference-to-Video Generation](https://mlsanity.com/paper/2603.25743/) (2026)
- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training](https://mlsanity.com/paper/2601.17830/) (2026)
- [What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion](https://mlsanity.com/paper/2605.07915/) (2026)
- [UniChange: Unifying Change Detection with Multimodal Large Language Model](https://mlsanity.com/paper/2511.02607/) (2025)
- [DivControl: Knowledge Diversion for Controllable Image Generation](https://mlsanity.com/paper/2507.23620/) (2025)
- [Semantic Context Matters: Improving Conditioning for Autoregressive Models](https://mlsanity.com/paper/2511.14063/) (2025)
- [Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation](https://mlsanity.com/paper/2601.22904/) (2026)
- [Laminating Representation Autoencoders for Efficient Diffusion](https://mlsanity.com/paper/2602.04873/) (2026)
- [MeanFlow Transformers with Representation Autoencoders](https://mlsanity.com/paper/2511.13019/) (2025)
- [DeRA: Decoupled Representation Alignment for Video Tokenization](https://mlsanity.com/paper/2512.04483/) (2025)
- [SemanticGen: Video Generation in Semantic Space](https://mlsanity.com/paper/2512.20619/) (2025)
- [Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment](https://mlsanity.com/paper/2605.06885/) (2026)
- [REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion](https://mlsanity.com/paper/2512.16636/) (2025)

## Abstract (arXiv)

REPA and its variants effectively mitigate training challenges in diffusion models by incorporating external visual representations from pretrained models, through alignment between the noisy hidden projections of denoising networks and foundational clean image representations. We argue that the external alignment, which is absent during the entire denoising inference process, falls short of fully harnessing the potential of discriminative representations. In this work, we propose a straightforward method called Representation Entanglement for Generation (REG), which entangles low-level image latents with a single high-level class token from pretrained foundation models for denoising. REG acquires the capability to produce coherent image-class pairs directly from pure noise, substantially improving both generation quality and training efficiency. This is accomplished with negligible additional inference overhead, requiring only one single additional token for denoising (<0.5% increase in FLOPs and latency). The inference process concurrently reconstructs both image latents and their corresponding global semantics, where the acquired semantic knowledge actively guides and enhances the image generation process. On ImageNet 256×256, SiT-XL/2 + REG demonstrates remarkable convergence acceleration, achieving 63× and 23× faster training than SiT-XL/2 and SiT-XL/2 + REPA, respectively. More impressively, SiT-L/2 + REG trained for merely 400K iterations outperforms SiT-XL/2 + REPA trained for 4M iterations (10× longer). Code is available at: https://github.com/Martinser/REG.