English
Related papers

Related papers: Alternating Updates for Efficient Transformers

200 papers

Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contributions: a residual path that copies the input and the…

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Computation and Language · Computer Science 2021-09-07 Chuhan Wu , Fangzhao Wu , Tao Qi , Yongfeng Huang , Xing Xie

Modern transformer-based deep neural networks present unique technical challenges for effective acceleration in real-world applications. Apart from the vast amount of linear operations needed due to their sizes, modern transformer models…

Hardware Architecture · Computer Science 2024-11-07 Jiajun Wu , Mo Song , Jingmin Zhao , Yizhao Gao , Jia Li , Hayden Kwok-Hay So

The combination of linear transformations and non-linear activation functions forms the foundation of most modern deep neural networks, enabling them to approximate highly complex functions. This paper explores the introduction of quadratic…

Machine Learning · Computer Science 2025-10-07 Qian Chen , Linxin Yang , Akang Wang , Xiaodong Luo , Yin Zhang

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

In data-parallel synchronous training of deep neural networks, different devices (replicas) run the same program with different partitions of the training batch, but weight update computation is repeated on all replicas, because the weights…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-05-05 Yuanzhong Xu , HyoukJoong Lee , Dehao Chen , Hongjun Choi , Blake Hechtman , Shibo Wang

Executing machine learning inference tasks on resource-constrained edge devices requires careful hardware-software co-design optimizations. Recent examples have shown how transformer-based deep neural network models such as ALBERT can be…

Machine Learning · Computer Science 2023-04-14 Zirui Fu , Aleksandre Avaliani , Marco Donato

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Computation and Language · Computer Science 2026-05-27 Kuan-Wei Lu , Ding-Yong Hong , Pangfeng Liu , Jan-Jan Wu

Transformer-based architectures have become the de-facto standard models for a wide range of Natural Language Processing tasks. However, their memory footprint and high latency are prohibitive for efficient deployment and inference on…

Machine Learning · Computer Science 2021-09-28 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Data augmentation with \textbf{Mixup} has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels at once through linear interpolation. However, this one-stage…

Machine Learning · Computer Science 2022-06-07 Xiangjin Xie , Yangning Li , Wang Chen , Kai Ouyang , Li Jiang , Haitao Zheng

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Machine Learning · Computer Science 2017-08-22 Luke Taylor , Geoff Nitschke

Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Ildoo Kim , Younghoon Kim , Sungwoong Kim

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's complexity scales quadratically with sequence length.…

Computation and Language · Computer Science 2021-09-21 Jungo Kasai , Hao Peng , Yizhe Zhang , Dani Yogatama , Gabriel Ilharco , Nikolaos Pappas , Yi Mao , Weizhu Chen , Noah A. Smith

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Machine Learning · Computer Science 2025-09-24 Yuxuan Cai , Xiaozhuan Liang , Xinghua Wang , Jin Ma , Haijin Liang , Jinwen Luo , Xinyu Zuo , Lisheng Duan , Yuyang Yin , Xi Chen

Transformer is a state-of-the-art model in the field of natural language processing (NLP). Current NLP models primarily increase the number of transformers to improve processing performance. However, this technique requires a lot of…

Computation and Language · Computer Science 2023-10-18 Woohyeon Moon , Taeyoung Kim , Bumgeun Park , Dongsoo Har

Though the transformer architectures have shown dominance in many natural language understanding tasks, there are still unsolved issues for the training of transformer models, especially the need for a principled way of warm-up which has…

Computation and Language · Computer Science 2021-06-01 Wei Zhu , Xiaoling Wang , Xipeng Qiu , Yuan Ni , Guotong Xie

Catastrophic forgetting remains a major challenge when adapting large language models (LLMs) to new tasks or domains. Conventional fine-tuning often overwrites existing knowledge, causing performance degradation on original tasks. We…

Computation and Language · Computer Science 2025-01-08 Ayoub Ben Chaliah , Hela Dellagi

Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the…

Artificial Intelligence · Computer Science 2023-06-28 Lukas Hedegaard , Arian Bakhtiarnia , Alexandros Iosifidis

As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models…

Machine Learning · Computer Science 2026-01-06 Hongze Sun , Wuque Cai , Duo Chen , Quan Tang , Shifeng Mao , Jiayi He , Zhenxing Wang , Yan Cui , Dezhong Yao , Daqing Guo
‹ Prev 1 3 4 5 6 7 10 Next ›