# Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

arXiv: https://arxiv.org/abs/2512.17909 · HTML: https://mlsanity.com/paper/2512.17909/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 39 of its 43 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Placed in

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

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [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)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://mlsanity.com/paper/2408.11039/) (2024)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [Step1X-Edit: A Practical Framework for General Image Editing](https://mlsanity.com/paper/2504.17761/) (2025)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [UniTok: A Unified Tokenizer for Visual Generation and Understanding](https://mlsanity.com/paper/2502.20321/) (2025)
- [OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision](https://mlsanity.com/paper/2411.07199/) (2024)
- [LMFusion: Adapting Pretrained Language Models for Multimodal Generation](https://mlsanity.com/paper/2412.15188/) (2024)
- [DDT: Decoupled Diffusion Transformer](https://mlsanity.com/paper/2504.05741/) (2025)
- [EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling](https://mlsanity.com/paper/2502.09509/) (2025)
- [Latent Diffusion Model without Variational Autoencoder](https://mlsanity.com/paper/2510.15301/) (2025)

## Built on by (most cited first, 22 of 22)

- [Beyond Language Modeling: An Exploration of Multimodal Pretraining](https://mlsanity.com/paper/2603.03276/) (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)
- [What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion](https://mlsanity.com/paper/2605.07915/) (2026)
- [RPiAE: A Representation-Pivoted Autoencoder Enhancing Both Image Generation and Editing](https://mlsanity.com/paper/2603.19206/) (2026)
- [Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models](https://mlsanity.com/paper/2605.21573/) (2026)
- [SemBind: Binding Diffusion Watermarks to Semantics Against Black-Box Forgery Attacks](https://mlsanity.com/paper/2601.20310/) (2026)
- [WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling](https://mlsanity.com/paper/2605.06407/) (2026)
- [Self-Consistent Flow: Unifying Velocity and Endpoint Prediction for Rectified Flow Models](https://mlsanity.com/paper/2607.12171/) (2026)
- [ForensicConcept: Transferable Forensic Concepts for AIGI Detection](https://mlsanity.com/paper/2606.07034/) (2026)
- [Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis](https://mlsanity.com/paper/2605.20808/) (2026)
- [SPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models](https://mlsanity.com/paper/2606.23041/) (2026)
- [FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders](https://mlsanity.com/paper/2609.31620/) (2026)
- [Video Generation with Predictive Latents](https://mlsanity.com/paper/2605.02134/) (2026)
- [SRC-Flow: Compact Semantic Representations Enable Normalizing Flows for Image Generation](https://mlsanity.com/paper/2605.18267/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)
- [LeapBot-WA: World-Anchor Action Models via Predictive Latent Alignments](https://mlsanity.com/paper/2607.23969/) (2026)
- [SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents](https://mlsanity.com/paper/2608.01306/) (2026)
- [SlotDiT: Object-Centric Representations for Diffusion Transformers](https://mlsanity.com/paper/2609.17414/) (2026)
- [On the Diffusibility of High-Dimensional Latents](https://mlsanity.com/paper/2609.28473/) (2026)
- [Visual Representation and History Modeling for Navigation World Models](https://mlsanity.com/paper/2609.29555/) (2026)
- [Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation](https://mlsanity.com/paper/2610.00575/) (2026)

## Abstract (arXiv)

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend is to adopt high-dimensional features from representation encoders as generative latents. However, we empirically identify two fundamental obstacles in this paradigm: (1) the discriminative feature space lacks compact regularization, making diffusion models prone to off-manifold latents that lead to inaccurate object structures; and (2) the encoder's inherently weak pixel-level reconstruction hinders the generator from learning accurate fine-grained geometry and texture. In this paper, we propose a systematic framework to adapt understanding-oriented encoder features for generative tasks. We introduce a semantic-pixel reconstruction objective to regularize the latent space, enabling the compression of both semantic information and fine-grained details into a highly compact representation (96 channels with 16x16 spatial downsampling). This design ensures that the latent space remains semantically rich and achieves state-of-the-art image reconstruction, while remaining compact enough for accurate generation. Leveraging this representation, we design a unified Text-to-Image (T2I) and image editing model. Benchmarking against various feature spaces, we demonstrate that our approach achieves state-of-the-art reconstruction, faster convergence, and substantial performance gains in both T2I and editing tasks, validating that representation encoders can be effectively adapted into robust generative components.