# Latent Denoising Makes Good Tokenizers

arXiv: https://arxiv.org/abs/2507.15856 · HTML: https://mlsanity.com/paper/2507.15856/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 66 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [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)
- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [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)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [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)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers](https://mlsanity.com/paper/2401.08740/) (2024)

## Built on by (most cited first, 20 of 20)

- [NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale](https://mlsanity.com/paper/2508.10711/) (2025)
- [Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation](https://mlsanity.com/paper/2602.11401/) (2026)
- [Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation](https://mlsanity.com/paper/2604.24763/) (2026)
- [Hyperspherical Latents Improve Continuous-Token Autoregressive Generation](https://mlsanity.com/paper/2509.24335/) (2025)
- [RAE-NWM: Navigation World Model in Dense Visual Representation Space](https://mlsanity.com/paper/2603.09241/) (2026)
- [SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows](https://mlsanity.com/paper/2512.04084/) (2025)
- [RecTok: Reconstruction Distillation along Rectified Flow](https://mlsanity.com/paper/2512.13421/) (2025)
- [Diffusion As Self-Distillation: End-to-End Latent Diffusion In One Model](https://mlsanity.com/paper/2511.14716/) (2025)
- [Adaptive 1D Video Diffusion Autoencoder](https://mlsanity.com/paper/2602.04220/) (2026)
- [Decoupling Complexity from Scale in Latent Diffusion Model](https://mlsanity.com/paper/2511.16117/) (2025)
- [Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration](https://mlsanity.com/paper/2512.10954/) (2025)
- [RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model](https://mlsanity.com/paper/2512.12083/) (2025)
- [MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation](https://mlsanity.com/paper/2606.26016/) (2026)
- [Unifying Distributional Training for One-Step Visual Generation](https://mlsanity.com/paper/2609.35763/) (2026)
- [PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation](https://mlsanity.com/paper/2609.38597/) (2026)
- [Video Generation with Predictive Latents](https://mlsanity.com/paper/2605.02134/) (2026)
- [STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation](https://mlsanity.com/paper/2606.07036/) (2026)
- [One-Step Generative Modeling via Unbalanced Optimal Transport](https://mlsanity.com/paper/2609.32708/) (2026)
- [Image Tokenizers Should Be Trained Between Images](https://mlsanity.com/paper/2610.16759/) (2026)
- [Efficient Fr'echet Distributional Decoder Alignment for Latent Generative Models](https://mlsanity.com/paper/2610.17466/) (2026)

## Abstract (arXiv)

Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing clean signals from corrupted inputs, such as signals degraded by Gaussian noise or masking -- a process we term denoising. Motivated by this insight, we propose aligning tokenizer embeddings directly with the downstream denoising objective, encouraging latent embeddings that remain reconstructable even under significant corruption. To achieve this, we introduce the Latent Denoising Tokenizer (l-DeTok), a simple yet highly effective tokenizer trained to reconstruct clean images from latent embeddings corrupted via interpolative noise or random masking. Extensive experiments on class-conditioned (ImageNet 256x256 and 512x512) and text-conditioned (MSCOCO) image generation benchmarks demonstrate that our l-DeTok consistently improves generation quality across six representative generative models compared to prior tokenizers. Our findings highlight denoising as a fundamental design principle for tokenizer development, and we hope it could motivate new perspectives for future tokenizer design.