Pith. sign in

REVIEW 9 cited by

Transformers without Normalization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.10622 v2 pith:UM4W6O4T submitted 2025-03-13 cs.LG cs.AIcs.CLcs.CV

classification cs.LGcs.AIcs.CLcs.CV
keywords normalizationtransformerswithoutlayersnetworksmodernneuralperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

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(\alpha $x$)$, 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Subcritical Signal Propagation at Initialization in Normalization-Free Transformers

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    Transformers using elementwise tanh-like nonlinearities instead of LayerNorm show stretched-exponential APJN growth at large depth, indicating subcritical signal propagation unlike the power-law growth in pre-LayerNor...

  2. Key and Value Weights Are Probably All You Need: On the Necessity of the Query, Key, Value weight Triplet in Self-Attention Transformers

    cs.LG 2025-10 unverdicted novelty 7.0 of 10

    One of the Q, K or V weights in transformer self-attention is redundant and replaceable by the identity matrix under mild assumptions, reducing parameters by 25 percent with no loss in small-model performance.

  3. Do Transformers Need Three Projections? Systematic Study of QKV Variants

    cs.LG 2026-06 conditional novelty 6.0 of 10

    Q-K=V projection sharing in transformers matches standard QKV performance with 50% KV cache reduction and combines with GQA/MQA for up to 96.9% reduction across vision and language tasks.

  4. Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers

    cs.LG 2026-02 unverdicted novelty 6.0 of 10

    TaperNorm gradually removes internal normalization in pre-norm transformers via learned gates that reach zero, revealing final norm as a scale anchor and enabling up to 1.18x faster KV-cached decoding with small loss ...

  5. FlashNorm: Fast Normalization for Transformers

    cs.LG 2024-07 accept novelty 6.0 of 10

    FlashNorm is an exact algebraic reformulation of RMSNorm plus linear projection that folds weights and defers normalization to allow parallel execution, plus scale-invariance simplifications that remove redundant norm...

  6. When Does Removing LayerNorm Help? Activation Bounding as a Regime-Dependent Implicit Regularizer

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    DyT improves validation loss 27% at 64M params/1M tokens but worsens it 19% at 118M tokens, with saturation levels predicting the sign of the effect.

  7. Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging

    cs.LG 2025-10 unverdicted novelty 5.0 of 10

    SAL-T enhances the linformer with spatially aware kinematic partitioning and convolutions to match full-attention transformer performance on jet tagging while keeping linear complexity and lower latency.

  8. A Mathematical Explanation of Transformers

    cs.LG 2025-10 unverdicted novelty 5.0 of 10

    The Transformer is interpreted as discretization of a structured integro-differential equation in continuous domains for tokens and features, unifying attention, feedforward, and normalization via operator and variati...

  9. Exploiting Layer Normalization Fine-tuning in Visual Transformer Foundation Models for Classification

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    LayerNorm parameter shifts after fine-tuning encode domain-transition information; rescaling them via an FSR-dependent scalar lambda plus a cyclic step improves ViT classification under data scarcity and domain shift.

Pith tools