English
Related papers

Related papers: Mega: Moving Average Equipped Gated Attention

200 papers

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

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Machine Learning · Computer Science 2025-09-05 Yihe Dong , Lorenzo Noci , Mikhail Khodak , Mufan Li

MEGA is a recent transformer-based architecture, which utilizes a linear recurrent operator whose parallel computation, based on the FFT, scales as $O(LlogL)$, with $L$ being the sequence length. We build upon their approach by replacing…

Machine Learning · Computer Science 2023-12-12 Aleksandar Terzic , Michael Hersche , Geethan Karunaratne , Luca Benini , Abu Sebastian , Abbas Rahimi

Attention architectures are widely used; they recently gained renewed popularity with Transformers yielding a streak of state of the art results. Yet, the geometrical implications of softmax-attention remain largely unexplored. In this work…

Machine Learning · Computer Science 2020-05-20 Oliver Richter , Roger Wattenhofer

Transformer has achieved remarkable success in language, image, and speech processing. Recently, various efficient attention architectures have been proposed to improve transformer's efficiency while largely preserving its efficacy,…

Machine Learning · Computer Science 2025-01-14 Jun Zhang , Shuyang Jiang , Jiangtao Feng , Lin Zheng , Lingpeng Kong

In this paper, we propose generalized attention mechanism (GAM) by first suggesting a new interpretation for self-attention mechanism of Vaswani et al. . Following the interpretation, we provide description for different variants of…

Computation and Language · Computer Science 2022-08-23 R. V. R. Pandya

Recent advances in diffusion-based controllable visual generation have led to remarkable improvements in image quality. However, these powerful models are typically deployed on cloud servers due to their large computational demands, raising…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Yuhe Liu , Zhenxiong Tan , Yujia Hu , Songhua Liu , Xinchao Wang

Anticipating future actions in videos is challenging, as the observed frames provide only evidence of past activities, requiring the inference of latent intentions to predict upcoming actions. Existing transformer-based approaches, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Tsung-Ming Tai , Sofia Casarin , Andrea Pilzer , Werner Nutt , Oswald Lanz

We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs. Unlike the traditional multi-head attention mechanism, which equally consumes all attention heads, GaAN uses a convolutional sub-network to…

Machine Learning · Computer Science 2018-03-21 Jiani Zhang , Xingjian Shi , Junyuan Xie , Hao Ma , Irwin King , Dit-Yan Yeung

Reducing the key-value (KV) cache size is a crucial step toward enabling efficient inference in large language models (LLMs), especially under latency and memory constraints. While Multi-Head Attention (MHA) offers strong representational…

Computation and Language · Computer Science 2025-09-23 Zhengge Cai , Haowen Hou

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

Computation and Language · Computer Science 2017-07-04 Denny Britz , Melody Y. Guan , Minh-Thang Luong

The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality but suffers from large Key-Value (KV) cache memory…

Artificial Intelligence · Computer Science 2025-12-25 Esmail Gumaan

Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding token-wise sparsity and internal linear representations. To address this gap, we introduce the…

Machine Learning · Statistics 2025-02-27 Pierre Marion , Raphaël Berthier , Gérard Biau , Claire Boyer

Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…

Machine Learning · Computer Science 2024-03-05 Sadegh Mahdavi , Renjie Liao , Christos Thrampoulidis

We propose a novel framework, Continuous_Time Attention, which infuses partial differential equations (PDEs) into the Transformer's attention mechanism to address the challenges of extremely long input sequences. Instead of relying solely…

Machine Learning · Computer Science 2025-12-30 Yukun Zhang , Xueqing Zhou

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

Many studies have been conducted to improve the efficiency of Transformer from quadric to linear. Among them, the low-rank-based methods aim to learn the projection matrices to compress the sequence length. However, the projection matrices…

Machine Learning · Computer Science 2022-11-30 Bosheng Qin , Juncheng Li , Siliang Tang , Yueting Zhuang

In Sequential Recommendation Systems (SRSs), Transformer models have demonstrated remarkable performance but face computational and memory cost challenges, especially when modeling long-term user behavior sequences. Due to its quadratic…

Information Retrieval · Computer Science 2026-03-25 Juntao Hu , Wei Zhou , Haini Cai , Xiao Du , Huayi Shen , Junhao Wen

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

Artificial Intelligence · Computer Science 2025-12-25 Yawei Liu

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

Computation and Language · Computer Science 2018-05-08 Biao Zhang , Deyi Xiong , Jinsong Su