English
Related papers

Related papers: GLU Attention Improve Transformer

200 papers

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Machine Learning · Computer Science 2025-05-28 Ted Zadouri , Hubert Strauss , Tri Dao

Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize the model from few samples, GNN usually…

Machine Learning · Computer Science 2020-10-05 Hao Cheng , Joey Tianyi Zhou , Wee Peng Tay , Bihan Wen

In this article, we introduce a novel deep learning hybrid model that integrates attention Transformer and Gated Recurrent Unit (GRU) architectures to improve the accuracy of cryptocurrency price predictions. By combining the Transformer's…

Machine Learning · Computer Science 2025-05-01 Esam Mahdi , C. Martin-Barreiro , X. Cabezas

Recently recurrent neural networks (RNN) has been very successful in handling sequence data. However, understanding RNN and finding the best practices for RNN is a difficult task, partly because there are many competing and complex hidden…

Neural and Evolutionary Computing · Computer Science 2016-04-01 Guo-Bing Zhou , Jianxin Wu , Chen-Lin Zhang , Zhi-Hua Zhou

Activation functions are fundamental elements of deep learning architectures as they significantly influence training dynamics. ReLU, while widely used, is prone to the dying neuron problem, which has been mitigated by variants such as…

Machine Learning · Computer Science 2025-05-22 Indrashis Das , Mahmoud Safari , Steven Adriaensen , Frank Hutter

The design choices in the Transformer attention mechanism, including weak inductive bias and quadratic computational complexity, have limited its application for modeling long sequences. In this paper, we introduce Mega, a simple,…

Machine Learning · Computer Science 2023-01-31 Xuezhe Ma , Chunting Zhou , Xiang Kong , Junxian He , Liangke Gui , Graham Neubig , Jonathan May , Luke Zettlemoyer

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…

Transformer attention architectures, similar to those developed for natural language processing, have recently proved efficient also in vision, either in conjunction with or as a replacement for convolutional layers. Typically, visual…

Computer Vision and Pattern Recognition · Computer Science 2021-07-01 Rufin VanRullen , Andrea Alamia

With the increasing demand for practical applications of Large Language Models (LLMs), many attention-efficient models have been developed to balance performance and computational cost. However, the adversarial robustness of these models…

Computation and Language · Computer Science 2024-09-17 Xiaojing Fan , Chunliang Tao

Transformers have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and…

Machine Learning · Computer Science 2021-06-03 Hanxiao Liu , Zihang Dai , David R. So , Quoc V. Le

We propose the Gaussian Error Linear Unit (GELU), a high-performing neural network activation function. The GELU activation function is $x\Phi(x)$, where $\Phi(x)$ the standard Gaussian cumulative distribution function. The GELU…

Machine Learning · Computer Science 2023-06-07 Dan Hendrycks , Kevin Gimpel

The LLaMA-Adapter has recently emerged as an efficient fine-tuning technique for LLaMA models, leveraging zero-initialized attention to stabilize training and enhance performance. However, despite its empirical success, the theoretical…

Machine Learning · Computer Science 2025-06-19 Nghiem T. Diep , Huy Nguyen , Chau Nguyen , Minh Le , Duy M. H. Nguyen , Daniel Sonntag , Mathias Niepert , Nhat Ho

Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, standing on the multi-headed dot product attention by attending to all the global contexts at different locations. Through a…

Computation and Language · Computer Science 2020-11-25 Yekun Chai , Shuo Jin , Xinwen Hou

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

Attention mechanism is a significant part of Transformer models. It helps extract features from embedded vectors by adding global information and its expressivity has been proved to be powerful. Nevertheless, the quadratic complexity…

Machine Learning · Computer Science 2025-11-11 Hanwen Liu , Yixuan Ma , Shi Jin , Yuguang Wang

Motivated by the factorization inherent in the original fast multipole method and the improved fast Gauss transform we introduce a factorable form of attention that operates efficiently in high dimensions. This approach reduces the…

Machine Learning · Computer Science 2024-02-13 Armin Gerami , Monte Hoover , Pranav S. Dulepet , Ramani Duraiswami

ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of…

Machine Learning · Computer Science 2019-06-13 Jonathan Fiat , Eran Malach , Shai Shalev-Shwartz

Due to the depth degradation effect in residual connections, many efficient Vision Transformers models that rely on stacking layers for information exchange often fail to form sufficient information mixing, leading to unnatural visual…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Dai Shi

We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and…

Computer Vision and Pattern Recognition · Computer Science 2018-07-25 Pau Rodríguez , Josep M. Gonfaus , Guillem Cucurull , F. Xavier Roca , Jordi Gonzàlez

Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Suwichaya Suwanwimolkul , Satoshi Komorita