English
Related papers

Related papers: Transformers without Normalization

200 papers

Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wise function DyT…

Machine Learning · Computer Science 2026-04-01 Mingzhi Chen , Taiming Lu , Jiachen Zhu , Mingjie Sun , Zhuang Liu

Accurate trajectory prediction is a cornerstone for the safe operation of autonomous driving systems, where understanding the dynamic behavior of surrounding agents is crucial. Transformer-based architectures have demonstrated significant…

Machine Learning · Computer Science 2025-05-07 JianLin Zhu , HongKuo Niu

Layer normalization (LN) is an essential component of modern neural networks. While many alternative techniques have been proposed, none of them have succeeded in replacing LN so far. The latest suggestion in this line of research is a…

Machine Learning · Computer Science 2026-04-15 Felix Stollenwerk

Vision Transformer (ViT) and its variants (e.g., Swin, PVT) have achieved great success in various computer vision tasks, owing to their capability to learn long-range contextual information. Layer Normalization (LN) is an essential…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Wenqi Shao , Yixiao Ge , Zhaoyang Zhang , Xuyuan Xu , Xiaogang Wang , Ying Shan , Ping Luo

Skip connections and normalisation layers form two standard architectural components that are ubiquitous for the training of Deep Neural Networks (DNNs), but whose precise roles are poorly understood. Recent approaches such as Deep Kernel…

Machine Learning · Computer Science 2023-02-22 Bobby He , James Martens , Guodong Zhang , Aleksandar Botev , Andrew Brock , Samuel L Smith , Yee Whye Teh

Dynamic Tanh (DyT) removes LayerNorm by bounding activations with a learned tanh(alpha x). We show that this bounding is a regime-dependent implicit regularizer, not a uniformly beneficial replacement. Across GPT-2-family models spanning…

Machine Learning · Computer Science 2026-04-28 Lucky Verma

Pre-Layer Normalization (Pre-LN) is the de facto choice for large language models (LLMs) and is crucial for stable pretraining and effective transfer learning. However, Pre-LN is inefficient due to repeated statistical calculations and…

Computation and Language · Computer Science 2026-02-04 Hoyoon Byun , Youngjun Choi , Taero Kim , Sungrae Park , Kyungwoo Song

Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer…

Machine Learning · Computer Science 2024-01-11 Fanfei Meng , Lele Zhang , Yu Chen , Yuxin Wang

Normalization is a key point in transformer training . In Dynamic Tanh (DyT), the author demonstrated that Tanh can be used as an alternative layer normalization (LN) and confirmed the effectiveness of the idea. But Tanh itself faces…

Machine Learning · Computer Science 2025-11-14 Daryl Noupa Yongueng , Hamidou Tembine

Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT), and employed flow-matching for improved training and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Omri Avrahami , Or Patashnik , Ohad Fried , Egor Nemchinov , Kfir Aberman , Dani Lischinski , Daniel Cohen-Or

Transformers have become the de facto backbone of modern deep learning, yet their training typically demands an advanced optimizer with adaptive learning rate like AdamW, rather than a momentum SGDW (mSGDW). Previous works show that it is…

Machine Learning · Computer Science 2025-07-24 Xianbiao Qi , Marco Chen , Wenjie Xiao , Jiaquan Ye , Yelin He , Chun-Guang Li , Zhouchen Lin

Normalization layers are critical components of modern AI systems, such as ChatGPT, Gemini, DeepSeek, etc. Empirically, they are known to stabilize training dynamics and improve generalization ability. However, the underlying theoretical…

Machine Learning · Computer Science 2026-02-24 Khoat Than

Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is…

Computer Vision and Pattern Recognition · Computer Science 2023-04-14 Kangliang Liu , Xiangcheng Du , Sijie Liu , Yingbin Zheng , Xingjiao Wu , Cheng Jin

Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called…

Machine Learning · Computer Science 2023-04-18 Mengdi Xu , Yuchen Lu , Yikang Shen , Shun Zhang , Ding Zhao , Chuang Gan

Normalization layers are a staple in state-of-the-art deep neural network architectures. They are widely believed to stabilize training, enable higher learning rate, accelerate convergence and improve generalization, though the reason for…

Machine Learning · Computer Science 2019-03-13 Hongyi Zhang , Yann N. Dauphin , Tengyu Ma

Recently deep neural networks based on tanh activation function have shown their impressive power in image denoising. In this letter, we try to use rectifier function instead of tanh and propose a dual-pathway rectifier neural network by…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Keting Zhang , Liqing Zhang

We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 William Peebles , Saining Xie

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional…

Machine Learning · Computer Science 2022-12-13 Yuxuan Li , James L. McClelland

Some conventional transforms such as Discrete Walsh-Hadamard Transform (DWHT) and Discrete Cosine Transform (DCT) have been widely used as feature extractors in image processing but rarely applied in neural networks. However, we found that…

Computer Vision and Pattern Recognition · Computer Science 2019-07-01 Joonhyun Jeong , Sung-Ho Bae

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Kun Yuan , Shaopeng Guo , Ziwei Liu , Aojun Zhou , Fengwei Yu , Wei Wu
‹ Prev 1 2 3 10 Next ›