English
Related papers

Related papers: One Wide Feedforward is All You Need

200 papers

An increasing number of emerging applications in data science and engineering are based on multidimensional and structurally rich data. The irregularities, however, of high-dimensional data often compromise the effectiveness of standard…

The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…

Machine Learning · Computer Science 2023-05-09 Riccardo Ughi , Eugenio Lomurno , Matteo Matteucci

Compression has been a critical lens to understand the success of Transformers. In the past, we have typically taken the target distribution as a criterion to evaluate a model's compression performance. Nevertheless,it often remains…

Machine Learning · Computer Science 2025-04-29 Ruifeng Ren , Yong Liu

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment…

Computation and Language · Computer Science 2021-09-14 Javier Ferrando , Marta R. Costa-jussà

Attention-based Transformers have demonstrated strong adaptability across a wide range of tasks and have become the backbone of modern Large Language Models (LLMs). However, their underlying mechanisms remain open for further exploration.…

Machine Learning · Computer Science 2026-01-13 Ruifeng Ren , Sheng Ouyang , Huayi Tang , Yong Liu

There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains largely unexamined despite its critical role. During…

Computation and Language · Computer Science 2020-10-07 Yilin Yang , Longyue Wang , Shuming Shi , Prasad Tadepalli , Stefan Lee , Zhaopeng Tu

We argue that Transformers are essentially graph-to-graph models, with sequences just being a special case. Attention weights are functionally equivalent to graph edges. Our Graph-to-Graph Transformer architecture makes this ability…

Computation and Language · Computer Science 2023-10-30 James Henderson , Alireza Mohammadshahi , Andrei C. Coman , Lesly Miculicich

We break the linear link between the layer size and its inference cost by introducing the fast feedforward (FFF) architecture, a log-time alternative to feedforward networks. We demonstrate that FFFs are up to 220x faster than feedforward…

Machine Learning · Computer Science 2023-09-19 Peter Belcak , Roger Wattenhofer

Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, and support for…

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto

Transformer-based models have recently become dominant in Long-term Time Series Forecasting (LTSF), yet the variations in their architecture, such as encoder-only, encoder-decoder, and decoder-only designs, raise a crucial question: What…

Machine Learning · Computer Science 2025-07-18 Lefei Shen , Mouxiang Chen , Han Fu , Xiaoxue Ren , Xiaoyun Joy Wang , Jianling Sun , Zhuo Li , Chenghao Liu

Designing hardware accelerators for deep neural networks (DNNs) has been much desired. Nonetheless, most of these existing accelerators are built for either convolutional neural networks (CNNs) or recurrent neural networks (RNNs). Recently,…

Signal Processing · Electrical Eng. & Systems 2020-09-21 Siyuan Lu , Meiqi Wang , Shuang Liang , Jun Lin , Zhongfeng Wang

We present an explicit construction for feedforward neural network (FNN), which provides a piecewise constant approximation for multivariate functions. The proposed FNN has two hidden layers, where the weights and thresholds are explicitly…

Numerical Analysis · Mathematics 2018-08-23 Kailiang Wu , Dongbin Xiu

Human perceive the 3D world through 2D observations from limited viewpoints. While recent feed-forward generalizable 3D reconstruction models excel at recovering 3D structures from sparse images, their representations are often confined to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Mochu Xiang , Zhelun Shen , Xuesong Li , Jiahui Ren , Jing Zhang , Chen Zhao , Shanshan Liu , Haocheng Feng , Jingdong Wang , Yuchao Dai

Self-attention is the central computational primitive of Vision Transformers, yet we lack a principled understanding of what information attention mechanisms exchange between tokens. Attention maps describe where weight mass concentrates;…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Fenil R. Doshi , Thomas Fel , Talia Konkle , George Alvarez

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Sound · Computer Science 2020-10-08 Anshuman Tripathi , Jaeyoung Kim , Qian Zhang , Han Lu , Hasim Sak

We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series…

Computation and Language · Computer Science 2021-09-15 Mozhdeh Gheini , Xiang Ren , Jonathan May

Transformers with linearised attention (''linear Transformers'') have demonstrated the practical scalability and effectiveness of outer product-based Fast Weight Programmers (FWPs) from the '90s. However, the original FWP formulation is…

Machine Learning · Computer Science 2021-10-28 Kazuki Irie , Imanol Schlag , Róbert Csordás , Jürgen Schmidhuber

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Hila Chefer , Shir Gur , Lior Wolf