# DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders

arXiv: https://arxiv.org/abs/2605.22777 · HTML: https://mlsanity.com/paper/2605.22777/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 37 of its 42 references that are in the map.
- First posted on arXiv 21 May 2026.

## Placed in

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

## Builds on (most cited first, 30 of 37)

- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (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)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Diffusion Transformers with Representation Autoencoders](https://mlsanity.com/paper/2510.11690/) (2025)
- [REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers](https://mlsanity.com/paper/2504.10483/) (2025)
- [StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis](https://mlsanity.com/paper/2301.09515/) (2023)
- [Fast Training of Diffusion Models with Masked Transformers](https://mlsanity.com/paper/2306.09305/) (2023)
- [Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think](https://mlsanity.com/paper/2507.01467/) (2025)
- [Latent Diffusion Model without Variational Autoencoder](https://mlsanity.com/paper/2510.15301/) (2025)
- [What matters for Representation Alignment: Global Information or Spatial Structure?](https://mlsanity.com/paper/2512.10794/) (2025)
- [UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing](https://mlsanity.com/paper/2507.23278/) (2025)
- [DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies](https://mlsanity.com/paper/2503.14324/) (2025)
- [AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models](https://mlsanity.com/paper/2509.25162/) (2025)
- [Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens](https://mlsanity.com/paper/2504.14666/) (2025)

## Built on by (most cited first, 2 of 2)

- [HiRAE: Hierarchical Representation Autoencoding with Residual Budgets](https://mlsanity.com/paper/2609.37775/) (2026)
- [Enhancing Autoregressive Video Generation via Representation Adversarial Distillation](https://mlsanity.com/paper/2609.40037/) (2026)

## Abstract (arXiv)

Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergence and high-quality generation in latent diffusion models. However, freezing the VFM inherently constrains its spatial reconstruction capacity, limiting fine-grained generation and image editing; in contrast, incorporating reconstruction-oriented signals via fine-tuning disrupts the pretrained semantic space and degrades generative fidelity. To address this trade-off, we propose DecQ, a simple yet effective framework for RAEs. Specifically, DecQ introduces lightweight detail-condensing queries that extract fine-grained information from intermediate VFM features through condenser modules. These queries are incorporated into the decoder to support reconstruction and are jointly generated with patch tokens during generative modeling. By aggregating information from both shallow and deep layers, DecQ effectively mitigates the reconstruction--generation trade-off, improving both reconstruction quality and generative performance. Our experiments demonstrate that: (1) with only 8 additional queries and 3.9% extra computation, DecQ improves reconstruction over the frozen DINOv2-based RAE, increasing PSNR from 19.13 dB to 22.76 dB; and (2) for generative modeling, DecQ achieves 3.3× faster convergence than RAE, attaining an FID of 1.41 without guidance and 1.05 with guidance.