English
Related papers

Related papers: SOFT: Softmax-free Transformer with Linear Complex…

200 papers

At the core of the popular Transformer architecture is the self-attention mechanism, which dynamically assigns softmax weights to each input token so that the model can focus on the most salient information. However, the softmax structure…

Machine Learning · Computer Science 2025-05-27 Fanqi Yan , Huy Nguyen , Pedram Akbarian , Nhat Ho , Alessandro Rinaldo

Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computations in order to compete with convolutional neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-10-04 Pranav Jeevan , Amit Sethi

Recently, vision transformers have become very popular. However, deploying them in many applications is computationally expensive partly due to the Softmax layer in the attention block. We introduce a simple but effective, Softmax-free…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Soroush Abbasi Koohpayegani , Hamed Pirsiavash

The quadratic complexity of the attention mechanism represents one of the biggest hurdles for processing long sequences using Transformers. Current methods, relying on sparse representations or stateful recurrence, sacrifice token-to-token…

Machine Learning · Computer Science 2025-06-06 Tobias Christian Nauen , Sebastian Palacio , Andreas Dengel

Transformers have transformed the field of natural language processing. This performance is largely attributed to the use of stacked self-attention layers, each of which consists of matrix multiplies as well as softmax operations. As a…

Hardware Architecture · Computer Science 2021-03-18 Jacob R. Stevens , Rangharajan Venkatesan , Steve Dai , Brucek Khailany , Anand Raghunathan

The softmax function is crucial in Transformer attention, which normalizes each row of the attention scores with summation to one, achieving superior performances over other alternative functions. However, the softmax function can face a…

Computation and Language · Computer Science 2025-02-26 Chuanyang Zheng , Yihang Gao , Guoxuan Chen , Han Shi , Jing Xiong , Xiaozhe Ren , Chao Huang , Xin Jiang , Zhenguo Li , Yu Li

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Sucheng Ren , Daquan Zhou , Shengfeng He , Jiashi Feng , Xinchao Wang

Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In…

Computer Vision and Pattern Recognition · Computer Science 2022-11-09 Daquan Zhou , Zhiding Yu , Enze Xie , Chaowei Xiao , Anima Anandkumar , Jiashi Feng , Jose M. Alvarez

Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax…

Machine Learning · Computer Science 2025-12-15 Etienne Boursier , Claire Boyer

Vision Transformer (ViT) has recently demonstrated promise in computer vision problems. However, unlike Convolutional Neural Networks (CNN), it is known that the performance of ViT saturates quickly with depth increasing, due to the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Peihao Wang , Wenqing Zheng , Tianlong Chen , Zhangyang Wang

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…

Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent…

Computer Vision and Pattern Recognition · Computer Science 2022-11-17 Leijie Wu , Song Guo , Yaohong Ding , Junxiao Wang , Wenchao Xu , Richard Yida Xu , Jie Zhang

The self-attention mechanism distinguishes transformer-based large language models (LLMs) apart from convolutional and recurrent neural networks. Despite the performance improvement, achieving real-time LLM inference on silicon remains…

Hardware Architecture · Computer Science 2024-11-18 Shiwei Liu , Guanchen Tao , Yifei Zou , Derek Chow , Zichen Fan , Kauna Lei , Bangfei Pan , Dennis Sylvester , Gregory Kielian , Mehdi Saligane

Visual attention mechanisms are widely used in multimodal tasks, as visual question answering (VQA). One drawback of softmax-based attention mechanisms is that they assign some probability mass to all image regions, regardless of their…

Computation and Language · Computer Science 2021-07-09 Pedro Henrique Martins , Vlad Niculae , Zita Marinho , André Martins

Recently, Transformer networks have demonstrated outstanding performance in the field of image restoration due to the global receptive field and adaptability to input. However, the quadratic computational complexity of Softmax-attention…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Zhi Jin , Yuwei Qiu , Kaihao Zhang , Hongdong Li , Wenhan Luo

Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs' attention measures global similarities and thus has a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Haoran You , Yunyang Xiong , Xiaoliang Dai , Bichen Wu , Peizhao Zhang , Haoqi Fan , Peter Vajda , Yingyan Celine Lin

Vision Transformer (ViT) has made significant advancements in computer vision, thanks to its token mixer's sophisticated ability to capture global dependencies between all tokens. However, the quadratic growth in computational demands as…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Guoan Xu , Wenfeng Huang , Wenjing Jia , Jiamao Li , Guangwei Gao , Guo-Jun Qi

Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear…

Machine Learning · Computer Science 2025-07-08 Naoki Nishikawa , Rei Higuchi , Taiji Suzuki

Self-attention module shows outstanding competence in capturing long-range relationships while enhancing performance on vision tasks, such as image classification and image captioning. However, the self-attention module highly relies on the…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Guangyang Zhu , Jianfeng Zhang , Yuanzhi Feng , Hai Lan

Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching…

Hardware Architecture · Computer Science 2025-01-15 Rya Sanovar , Srikant Bharadwaj , Renee St. Amant , Victor Rühle , Saravan Rajmohan