English
Related papers

Related papers: The Devil in Linear Transformer

200 papers

Differential Transformer has recently gained significant attention for its impressive empirical performance, often attributed to its ability to perform noise canceled attention. However, precisely how differential attention achieves its…

Machine Learning · Computer Science 2025-10-22 Chaerin Kong , Jiho Jang , Nojun Kwak

Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank projection methods such as Linformer and kernel-based…

Computation and Language · Computer Science 2022-10-14 Yizhe Zhang , Deng Cai

Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, training and deploying these models can be prohibitively costly for long sequences,…

Machine Learning · Computer Science 2020-06-16 Sinong Wang , Belinda Z. Li , Madian Khabsa , Han Fang , Hao Ma

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

Transformers have become foundational architectures for both natural language and computer vision tasks. However, the high computational cost makes it quite challenging to deploy on resource-constraint devices. This paper investigates the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Jialong Guo , Xinghao Chen , Yehui Tang , Yunhe Wang

The attention mechanism is an important reason for the success of transformers. It relies on computing pairwise relations between tokens. To reduce the high computational cost of standard quadratic attention, linear attention has been…

Artificial Intelligence · Computer Science 2026-02-13 Hanno Ackermann , Hong Cai , Mohsen Ghafoorian , Amirhossein Habibian

While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution…

Computer Vision and Pattern Recognition · Computer Science 2021-08-06 Guanglei Yang , Hao Tang , Mingli Ding , Nicu Sebe , Elisa Ricci

Layer Normalization (LayerNorm) is an inherent component in all Transformer-based models. In this paper, we show that LayerNorm is crucial to the expressivity of the multi-head attention layer that follows it. This is in contrast to the…

Machine Learning · Computer Science 2023-05-12 Shaked Brody , Uri Alon , Eran Yahav

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Machine Learning · Computer Science 2023-05-09 Riccardo Ughi , Eugenio Lomurno , Matteo Matteucci

The quadratic complexity of softmax attention presents a major obstacle for scaling Transformers to high-resolution vision tasks. Existing linear attention variants often replace the softmax with Gaussian kernels to reduce complexity, but…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Zhe Feng , Sen Lian , Changwei Wang , Muyang Zhang , Tianlong Tan , Rongtao Xu , Weiliang Meng , Xiaopeng Zhang

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide…

Computation and Language · Computer Science 2020-05-05 Qingqing Cao , Harsh Trivedi , Aruna Balasubramanian , Niranjan Balasubramanian

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim

Widely adopted in modern Vision Transformer designs, Softmax attention can effectively capture long-range visual information; however, it incurs excessive computational cost when dealing with high-resolution inputs. In contrast, linear…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Dongchen Han , Yifan Pu , Zhuofan Xia , Yizeng Han , Xuran Pan , Xiu Li , Jiwen Lu , Shiji Song , Gao Huang

Since the proposal of transformers, these models have been limited to bounded input lengths, because of their need to attend to every token in the input. In this work, we propose Unlimiformer: a general approach that wraps any existing…

Computation and Language · Computer Science 2023-11-01 Amanda Bertsch , Uri Alon , Graham Neubig , Matthew R. Gormley

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Despite the great success of Large Vision-Language Models (LVLMs), they inevitably suffer from hallucination. As we know, both the visual encoder and the Large Language Model (LLM) decoder in LVLMs are Transformer-based, allowing the model…

Computation and Language · Computer Science 2025-11-07 Xuan Gong , Tianshi Ming , Xinpeng Wang , Zhihua Wei

This research endeavors to offer insights into unlocking the further potential of transformer-based architectures. One of the primary motivations is to offer a geometric interpretation for the attention mechanism in transformers. In our…

Machine Learning · Computer Science 2025-12-16 Zhongping Ji

Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attention mechanism's linear…

Machine Learning · Computer Science 2026-04-22 Weijie Zhao , Mingquan Liu , Bolun Wang , Simo Wu , Nuobei Xie , Rui-Jie Zhu , Peng Zhou