English
Related papers

Related papers: Simplifying Transformer Blocks

200 papers

Transformers have achieved remarkable success across a wide range of applications, a feat often attributed to their scalability. Yet training them without skip (residual) connections remains notoriously difficult. While skips stabilize…

Machine Learning · Computer Science 2025-10-02 Yiping Ji , James Martens , Jianqiao Zheng , Ziqin Zhou , Peyman Moghadam , Xinyu Zhang , Hemanth Saratchandran , Simon Lucey

Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been ad-hoc. In this paper, we conduct a principled study on the…

Machine Learning · Computer Science 2025-10-14 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Krishna Kumar , Markos A. Katsoulakis

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Deepak Sridhar , Yunsheng Li , Nuno Vasconcelos

Transformation-based learning has been successfully employed to solve many natural language processing problems. It achieves state-of-the-art performance on many natural language processing tasks and does not overtrain easily. However, it…

Computation and Language · Computer Science 2007-05-23 Grace Ngai , Radu Florian

Large Language Models (LLMs) have made significant strides in natural language processing, and a precise understanding of the internal mechanisms driving their success is essential. In this work, we analyze the trajectories of token…

Machine Learning · Computer Science 2025-03-06 Murdock Aubry , Haoming Meng , Anton Sugolov , Vardan Papyan

Recent advances in the area of long document matching have primarily focused on using transformer-based models for long document encoding and matching. There are two primary challenges associated with these models. Firstly, the performance…

Computation and Language · Computer Science 2023-02-09 Akshita Jha , Adithya Samavedhi , Vineeth Rakesh , Jaideep Chandrashekar , Chandan K. Reddy

Large language models exhibit sophisticated capabilities, yet understanding how they work internally remains a central challenge. A fundamental obstacle is that training selects for behavior, not circuitry, so many weight configurations can…

Machine Learning · Computer Science 2026-02-27 Joshua S. Schiffman

Self-attention and transformer architectures have become foundational components in modern deep learning. Recent efforts have integrated transformer blocks into compact neural architectures for computer vision, giving rise to various…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Yancheng Wang , Yingzhen Yang

In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps…

Machine Learning · Computer Science 2022-07-22 Sankalan Pal Chowdhury , Adamos Solomou , Avinava Dubey , Mrinmaya Sachan

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and…

Computer Vision and Pattern Recognition · Computer Science 2022-03-21 Hugo Touvron , Matthieu Cord , Alaaeldin El-Nouby , Jakob Verbeek , Hervé Jégou

The Transformer architecture has inarguably revolutionized deep learning, overtaking classical architectures like multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs). At its core, the attention block differs in form and…

Machine Learning · Computer Science 2025-03-18 Weronika Ormaniec , Felix Dangel , Sidak Pal Singh

End-to-end training with full-depth backpropagation remains the dominant paradigm for optimizing deep neural networks, but its efficiency deteriorates as models grow deeper. Since every block must be executed and differentiated under a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Yuming Zhang , Peizhe Wang , Tianyang Han , Hengyu Shi , Junhao Su , Dongzhi Guan , Jiabin Liu , Jiaji Wang

The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper,…

Machine Learning · Computer Science 2026-02-10 Ambroise Odonnat , Laetitia Chapel , Romain Tavenard , Ievgen Redko

Despite the remarkable success of Transformer-based architectures in various sequential modeling tasks, such as natural language processing, computer vision, and robotics, their ability to learn basic sequential models, like Hidden Markov…

Machine Learning · Computer Science 2024-06-07 Jiachen Hu , Qinghua Liu , Chi Jin

Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or…

Machine Learning · Computer Science 2021-09-10 Ye Lin , Yanyang Li , Tong Xiao , Jingbo Zhu

Transformers have proved effective in many NLP tasks. However, their training requires non-trivial efforts regarding designing cutting-edge optimizers and learning rate schedulers carefully (e.g., conventional SGD fails to train…

Machine Learning · Computer Science 2023-10-03 Liyuan Liu , Xiaodong Liu , Jianfeng Gao , Weizhu Chen , Jiawei Han

Deep learning (DL) models based on the transformer architecture have revolutionized many DL applications such as large language models (LLMs), vision transformers, audio generation, and time series prediction. Much of this progress has been…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-20 Quentin Anthony , Benjamin Michalowicz , Jacob Hatef , Lang Xu , Mustafa Abduljabbar , Aamir Shafi , Hari Subramoni , Dhabaleswar Panda

Transformer-based large language models have achieved remarkable performance across various natural language processing tasks. However, they often struggle with seemingly easy tasks like arithmetic despite their vast capabilities. This…

Computation and Language · Computer Science 2024-07-23 Luyu Qiu , Jianing Li , Chi Su , Chen Jason Zhang , Lei Chen

The Transformer and its variants have been proven to be efficient sequence learners in many different domains. Despite their staggering success, a critical issue has been the enormous number of parameters that must be trained (ranging from…

Machine Learning · Computer Science 2021-10-28 Subhabrata Dutta , Tanya Gautam , Soumen Chakrabarti , Tanmoy Chakraborty
‹ Prev 1 4 5 6 7 8 10 Next ›