Pith. sign in

REVIEW 8 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). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD

    cs.LG 2025-07 conditional novelty 6.0 of 10

    DNT is a transformer with InputNorm, PreNorm, MidNorm, and QKNorm that trains successfully with vanilla mSGDW, reaching performance close to AdamW on ImageNet and OpenWebText.

  2. Accurate Parameter-Efficient Test-Time Adaptation for Time Series Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    PETSA adapts frozen time-series forecasters at test time using gated low-rank input and output calibration modules and a combined robust, frequency, and structural loss, matching or beating full-model TTA with far few...

  3. BinConv: A Neural Architecture for Ordinal Encoding in Time-Series Forecasting

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A paper combines a cumulative binary encoding of target values with a lightweight convolutional architecture to improve time series forecasting accuracy and speed.

  4. 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.

  5. Discontinuity-aware KAN-based physics-informed neural networks

    physics.comp-ph 2025-07 conditional novelty 5.0 of 10

    A discontinuity-aware PINN with adaptive Fourier features, DyT-plus-spline KAN activations, and learned local viscosity captures shocks with errors between 0.9% and 5% on benchmark PDEs and airfoil flows.

  6. Taming LLMs by Scaling Learning Rates with Gradient Grouping

    cs.LG 2025-06 conditional novelty 5.0 of 10

    An optimizer wrapper that clusters per-layer momentum and scales learning rates by cluster-wise median deviations improves perplexity and accuracy across LLM and MLLM training, and lets LoRA pretraining approach full-...

  7. Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Pangu Light prunes LLMs across width, depth, and attention heads, then re-initializes remaining weights, achieving up to 4.2x throughput with modest benchmark loss.

  8. EyeSim-VQA: A Free-Energy-Guided Eye Simulation Framework for Video Quality Assessment

    cs.CV 2025-06 conditional novelty 4.0 of 10

    A VQA model that combines free-energy-inspired frame restoration with a scan-and-gaze prediction head reports competitive results on five benchmarks, though the claimed state-of-the-art performance is not uniformly supported.

Pith tools