English
Related papers

Related papers: ReGLA: Refining Gated Linear Attention

200 papers

Gated Linear Units (GLU) have shown great potential in enhancing neural network performance. In this paper, I introduce a novel attention mechanism called GLU Attention, which introduces nonlinearity into the values of Attention. My…

Machine Learning · Computer Science 2025-07-08 Zehao Wang

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…

Artificial Intelligence · Computer Science 2026-05-08 Gongli Xi , Ye Tian , Mengyu Yang , Huahui Yi , Liang Lin , Xiaoshuai Hao , Kun Wang , Wendong Wang

Large language models (LLMs) have made transformed changes for human society. One of the key computation in LLMs is the softmax unit. This operation is important in LLMs because it allows the model to generate a distribution over possible…

Machine Learning · Computer Science 2023-04-27 Yichuan Deng , Zhihang Li , Zhao Song

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…

Computation and Language · Computer Science 2025-08-15 Shuhai Zhang , Zeng You , Yaofo Chen , Zhiquan Wen , Qianyue Wang , Zhijie Qiu , Yuanqing Li , Mingkui Tan

The quadratic computational and memory complexities of the Transformer's attention mechanism have limited its scalability for modeling long sequences. In this paper, we propose Luna, a linear unified nested attention mechanism that…

Machine Learning · Computer Science 2021-11-04 Xuezhe Ma , Xiang Kong , Sinong Wang , Chunting Zhou , Jonathan May , Hao Ma , Luke Zettlemoyer

Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how information flows between hidden states). However, the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-27 Zhanzhan Cheng , Yunlu Xu , Mingjian Cheng , Yu Qiao , Shiliang Pu , Yi Niu , Fei Wu

Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we train Large Language Models (LLMs) modularly-combining small, domain-specific…

Machine Learning · Computer Science 2026-02-25 Corinna Cortes , Mehryar Mohri , Yutao Zhong

Random-feature-based attention (RFA) is an efficient approximation of softmax attention with linear runtime and space complexity. However, the approximation gap between RFA and conventional softmax attention is not well studied. Built upon…

Machine Learning · Computer Science 2023-02-10 Lin Zheng , Jianbo Yuan , Chong Wang , Lingpeng Kong

Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…

Computation and Language · Computer Science 2025-09-03 Fabien Furfaro

Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that the hidden state of trained linear attention models often exhibits a low-rank structure,…

Machine Learning · Computer Science 2026-02-13 Philipp Nazari , T. Konstantin Rusch

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Machine Learning · Computer Science 2016-09-20 Alexandre de Brébisson , Pascal Vincent

Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process through circuit…

Computation and Language · Computer Science 2025-06-16 Xu Wang , Yan Hu , Wenyu Du , Reynold Cheng , Benyou Wang , Difan Zou

Since its introduction, softmax attention has become the backbone of modern transformer architectures due to its expressiveness and scalability across a wide range of tasks. However, the main drawback of softmax attention is the quadratic…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Eric C. Larson

This study aims to innovatively explore adaptive applications of large language models (LLM) in urban renewal. It also aims to improve its performance and text generation quality for knowledge question-answering (QA) tasks. Based on the…

Computation and Language · Computer Science 2023-11-28 Xi Wang , Xianyao Ling , Tom Zhang , Xuecao Li , Shaolan Wang , Zhixing Li , Liang Zhang , Peng Gong

Attention is a key part of the transformer architecture. It is a sequence-to-sequence mapping that transforms each sequence element into a weighted sum of values. The weights are typically obtained as the softmax of dot products between…

An essential component of modern recurrent sequence models is the forget gate. While Transformers do not have an explicit recurrent form, we show that a forget gate can be naturally incorporated into Transformers by down-weighting the…

Machine Learning · Computer Science 2025-04-02 Zhixuan Lin , Evgenii Nikishin , Xu Owen He , Aaron Courville

While transformer models exhibit strong in-context learning (ICL) abilities, they often fail to generalize under simple distribution shifts. We analyze these failures and identify Softmax, the scoring function in the attention mechanism, as…

Computation and Language · Computer Science 2026-05-12 Omar Naim , Swarnadeep Bhar , Jérôme Bolte , Nicholas Asher

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Machine Learning · Computer Science 2025-10-03 Yifei Zuo , Yutong Yin , Zhichen Zeng , Ang Li , Banghua Zhu , Zhaoran Wang

Various natural language processing (NLP) tasks necessitate models that are efficient and small based on their ultimate application at the edge or in other resource-constrained environments. While prior research has reduced the size of…

Computation and Language · Computer Science 2023-06-27 Victor Agostinelli , Lizhong Chen

The core component of attention is the scoring function, which transforms the inputs into low-dimensional queries and keys and takes the dot product of each pair. While the low-dimensional projection improves efficiency, it causes…

Machine Learning · Computer Science 2025-09-10 Yilun Kuang , Noah Amsel , Sanae Lotfi , Shikai Qiu , Andres Potapczynski , Andrew Gordon Wilson