English
Related papers

Related papers: Improving Transformers with Dynamically Composable…

200 papers

To overcome the quadratic cost of self-attention, recent works have proposed various sparse attention modules, most of which fall under one of two groups: 1) sparse attention under a hand-crafted patterns and 2) full attention followed by a…

Machine Learning · Computer Science 2022-10-28 Sungjun Cho , Seonwoo Min , Jinwoo Kim , Moontae Lee , Honglak Lee , Seunghoon Hong

Vision Transformers has demonstrated competitive performance on computer vision tasks benefiting from their ability to capture long-range dependencies with multi-head self-attention modules and multi-layer perceptron. However, calculating…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xiangyu Chen , Qinghao Hu , Kaidong Li , Cuncong Zhong , Guanghui Wang

We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks. While the existing literature predominantly focuses on the convergence of transformers with…

Machine Learning · Computer Science 2024-02-01 Yingqian Cui , Jie Ren , Pengfei He , Jiliang Tang , Yue Xing

With the development of the self-attention mechanism, the Transformer model has demonstrated its outstanding performance in the computer vision domain. However, the massive computation brought from the full attention mechanism became a…

Computer Vision and Pattern Recognition · Computer Science 2021-12-13 Hai Lan , Xihao Wang , Xian Wei

Complex-valued signals encode both amplitude and phase, yet most deep models treat attention as real-valued correlation, overlooking interference effects. We introduce the Holographic Transformer, a physics-inspired architecture that…

Signal Processing · Electrical Eng. & Systems 2025-10-31 Enhao Huang , Zhiyu Zhang , Tianxiang Xu , Chunshu Xia , Kaichun Hu , Yuchen Yang , Tongtong Pan , Dong Dong , Zhan Qin

The attention mechanism is a pivotal element within the transformer architecture, making a substantial contribution to its exceptional performance. Within this attention mechanism, Softmax is an imperative component that enables the model…

Hardware Architecture · Computer Science 2024-09-05 Tianhua Xia , Sai Qian Zhang

While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a…

Computation and Language · Computer Science 2020-07-28 Yang Fan , Shufang Xie , Yingce Xia , Lijun Wu , Tao Qin , Xiang-Yang Li , Tie-Yan Liu

Linear attentions have shown potential for improving Transformer efficiency, reducing attention's quadratic complexity to linear in sequence length. This holds exciting promise for (1) training linear Transformers from scratch, (2)…

Machine Learning · Computer Science 2024-02-08 Michael Zhang , Kush Bhatia , Hermann Kumbong , Christopher Ré

The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention mechanisms used by…

Machine Learning · Computer Science 2020-01-01 Thomas Dowdell , Hongyu Zhang

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…

Machine Learning · Computer Science 2025-12-09 Minshen Zhang , Xiang Hu , Jianguo Li , Wei Wu , Kewei Tu

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Machine Learning · Computer Science 2021-05-21 Jean-Baptiste Cordonnier , Andreas Loukas , Martin Jaggi

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this…

Computation and Language · Computer Science 2022-04-08 Zuzana Jelčicová , Marian Verhelst

With the introduction of Transformers, different attention-based models have been proposed for image segmentation with promising results. Although self-attention allows capturing of long-range dependencies, it suffers from a quadratic…

Image and Video Processing · Electrical Eng. & Systems 2023-10-10 Ken C. L. Wong , Hongzhi Wang , Tanveer Syeda-Mahmood

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Artificial Intelligence · Computer Science 2025-11-18 Jingze Shi , Yifan Wu , Yiran Peng , Bingheng Wu , Liangdong Wang , Guang Liu , Yuyu Luo

Multi-Head Attention (MHA) is a critical computational kernel in transformer-based AI models. Emerging scalable tile-based accelerator architectures integrate increasing numbers of tightly-packed processing elements (PEs) with tensor units.…

Hardware Architecture · Computer Science 2025-05-27 Chi Zhang , Luca Colagrande , Renzo Andri , Thomas Benz , Gamze Islamoglu , Alessandro Nadalini , Francesco Conti , Yawei Li , Luca Benini

In this paper, we propose a simple and effective technique to allow for efficient self-supervised learning with bi-directional Transformers. Our approach is motivated by recent studies demonstrating that self-attention patterns in trained…

Computation and Language · Computer Science 2020-10-07 Ameet Deshpande , Karthik Narasimhan

Despite many recent works on Mixture of Experts (MoEs) for resource-efficient Transformer language models, existing methods mostly focus on MoEs for feedforward layers. Previous attempts at extending MoE to the self-attention layer fail to…

Machine Learning · Computer Science 2024-10-02 Róbert Csordás , Piotr Piękos , Kazuki Irie , Jürgen Schmidhuber

Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA,…

Computation and Language · Computer Science 2025-10-06 Tao Ji , Bin Guo , Yuanbin Wu , Qipeng Guo , Lixing Shen , Zhan Chen , Xipeng Qiu , Qi Zhang , Tao Gui

Transformers and large language models (LLMs) have revolutionized machine learning, with attention mechanisms at the core of their success. As the landscape of attention variants expands, so too do the challenges of optimizing their…

Computation and Language · Computer Science 2025-02-24 Feiyang Chen , Yu Cheng , Lei Wang , Yuqing Xia , Ziming Miao , Lingxiao Ma , Fan Yang , Jilong Xue , Zhi Yang , Mao Yang , Haibo Chen

Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studies on speech…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-24 Vinay Kothapally , John H. L. Hansen