# Transformers without Normalization

arXiv: https://arxiv.org/abs/2503.10622 · HTML: https://mlsanity.com/paper/2503.10622/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Builds on 66 of its 88 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Builds on (most cited first, 30 of 66)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)

## Built on by (most cited first, 30 of 70)

- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping](https://mlsanity.com/paper/2505.18738/) (2025)
- [A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training](https://mlsanity.com/paper/2601.22966/) (2026)
- [NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2504.12711/) (2025)
- [Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting](https://mlsanity.com/paper/2506.23424/) (2025)
- [Stronger Normalization-Free Transformers](https://mlsanity.com/paper/2512.10938/) (2025)
- [Towards Fully FP8 GEMM LLM Training at Scale](https://mlsanity.com/paper/2505.20524/) (2025)
- [SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm](https://mlsanity.com/paper/2602.08064/) (2026)
- [Subspace-Boosted Model Merging](https://mlsanity.com/paper/2506.16506/) (2025)
- [FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation](https://mlsanity.com/paper/2509.16195/) (2025)
- [Learning in Compact Spaces with Approximately Normalized Transformer](https://mlsanity.com/paper/2505.22014/) (2025)
- [Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers](https://mlsanity.com/paper/2509.22445/) (2025)
- [SeeDNorm: Self-Rescaled Dynamic Normalization](https://mlsanity.com/paper/2510.22777/) (2025)
- [Weight-Space Linear Recurrent Neural Networks](https://mlsanity.com/paper/2506.01153/) (2025)
- [Learning Relativistic Geodesics and Chaotic Dynamics via Stabilized Lagrangian Neural Networks](https://mlsanity.com/paper/2601.12519/) (2026)
- [On Surjectivity of Neural Networks: Can you elicit any behavior from your model?](https://mlsanity.com/paper/2508.19445/) (2025)
- [Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers](https://mlsanity.com/paper/2602.10408/) (2026)
- [Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models](https://mlsanity.com/paper/2605.26895/) (2026)
- [Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs](https://mlsanity.com/paper/2505.20155/) (2025)
- [Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation](https://mlsanity.com/paper/2507.06363/) (2025)
- [Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification](https://mlsanity.com/paper/2508.07577/) (2025)
- [Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging](https://mlsanity.com/paper/2510.23641/) (2025)
- [PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2602.00654/) (2026)
- [SAME: A Semantically-Aligned Music Autoencoder](https://mlsanity.com/paper/2605.18613/) (2026)
- [DyTTP: Trajectory Prediction with Normalization-Free Transformers](https://mlsanity.com/paper/2504.05356/) (2025)
- [Just One Layer Norm Guarantees Stable Extrapolation](https://mlsanity.com/paper/2505.14512/) (2025)
- [Guarded Query Routing for Large Language Models](https://mlsanity.com/paper/2505.14524/) (2025)
- [Taming LLMs by Scaling Learning Rates with Gradient Grouping](https://mlsanity.com/paper/2506.01049/) (2025)
- [A Mathematical Explanation of Transformers](https://mlsanity.com/paper/2510.03989/) (2025)
- [Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models](https://mlsanity.com/paper/2601.09719/) (2025)

## Abstract (arXiv)

Normalization layers are ubiquitous in modern neural networks and have long been considered essential. This work demonstrates that Transformers without normalization can achieve the same or better performance using a remarkably simple technique. We introduce Dynamic Tanh (DyT), an element-wise operation DyT(x) = tanh(α x), as a drop-in replacement for normalization layers in Transformers. DyT is inspired by the observation that layer normalization in Transformers often produces tanh-like, S-shaped input-output mappings. By incorporating DyT, Transformers without normalization can match or exceed the performance of their normalized counterparts, mostly without hyperparameter tuning. We validate the effectiveness of Transformers with DyT across diverse settings, ranging from recognition to generation, supervised to self-supervised learning, and computer vision to language models. These findings challenge the conventional understanding that normalization layers are indispensable in modern neural networks, and offer new insights into their role in deep networks.