English
Related papers

Related papers: FIT: Far-reaching Interleaved Transformers

200 papers

The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales quadratically with the sequence length, serving as a major bottleneck in long-context…

Computation and Language · Computer Science 2026-04-28 Yusheng Zhao , Hourun Li , Bohan Wu , Yichun Yin , Lifeng Shang , Jingyang Yuan , Meng Zhang , Ming Zhang

Attention mechanisms, primarily designed to capture pairwise correlations between words, have become the backbone of machine learning, expanding beyond natural language processing into other domains. This growth in adaptation comes at the…

Machine Learning · Computer Science 2022-09-27 Sheng-Chun Kao , Suvinay Subramanian , Gaurav Agrawal , Amir Yazdanbakhsh , Tushar Krishna

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Machine Learning · Computer Science 2025-11-10 Jatin Prakash , Aahlad Puli , Rajesh Ranganath

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine Learning · Computer Science 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

Vision Transformer (ViT) has prevailed in computer vision tasks due to its strong long-range dependency modelling ability. \textcolor{blue}{However, its large model size and weak local feature modeling ability hinder its application in real…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Yi Zhang , Lingxiao Wei , Bowei Zhang , Ziwei Liu , Kai Yi , Shu Hu

Transformer-based pre-trained models, such as BERT, have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications. However, deploying these models can be prohibitively costly, as the…

Computation and Language · Computer Science 2022-03-18 Jing Zhao , Yifan Wang , Junwei Bao , Youzheng Wu , Xiaodong He

The strong performance of vision transformers on image classification and other vision tasks is often attributed to the design of their multi-head attention layers. However, the extent to which attention is responsible for this strong…

Computer Vision and Pattern Recognition · Computer Science 2021-05-07 Luke Melas-Kyriazi

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental…

Machine Learning · Computer Science 2022-04-15 Liangqiong Qu , Yuyin Zhou , Paul Pu Liang , Yingda Xia , Feifei Wang , Ehsan Adeli , Li Fei-Fei , Daniel Rubin

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

Recent advances have demonstrated the powerful capability of transformer architecture in image restoration. However, our analysis indicates that existing transformerbased methods can not establish both exact global and local dependencies…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Zhijun Tu , Kunpeng Du , Hanting Chen , Hailing Wang , Wei Li , Jie Hu , Yunhe Wang

We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding a new branch to selected attention layers that computes an…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Vivek Trivedy , Amani Almalki , Longin Jan Latecki

Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most of recent works thus are dedicated to designing more…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Daquan Zhou , Yujun Shi , Bingyi Kang , Weihao Yu , Zihang Jiang , Yuan Li , Xiaojie Jin , Qibin Hou , Jiashi Feng

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Zihang Dai , Hanxiao Liu , Quoc V. Le , Mingxing Tan

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Xinyu Liu , Houwen Peng , Ningxin Zheng , Yuqing Yang , Han Hu , Yixuan Yuan

Transformers have recently demonstrated strong performance in computer vision, with Vision Transformers (ViTs) leveraging self-attention to capture both low-level and high-level image features. However, standard ViTs remain computationally…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Ali El Bellaj , Mohammed-Amine Cheddadi , Rhassan Berber

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

Hardware Architecture · Computer Science 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which scales linearly…

Machine Learning · Computer Science 2024-10-10 Joseph Eisner

Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Chongjian Ge , Xiaohan Ding , Zhan Tong , Li Yuan , Jiangliu Wang , Yibing Song , Ping Luo

Transformer is leading a trend in the field of image processing. Despite the great success that existing lightweight image processing transformers have achieved, they are tailored to FLOPs or parameters reduction, rather than practical…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Junbo Qiao , Wei Li , Haizhen Xie , Hanting Chen , Yunshuai Zhou , Zhijun Tu , Jie Hu , Shaohui Lin

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré