English
Related papers

Related papers: Two Heads Are Better than One: Simulating Large Tr…

200 papers

Long sequence neural memory remains a challenging problem. RNNs and their variants suffer from vanishing gradients, and Transformers suffer from quadratic scaling. Furthermore, compressing long sequences into a finite fixed representation…

Machine Learning · Computer Science 2026-02-03 Liyu Zerihun , Alexandr Plashchinsky

Transformers have achieved great success in a wide variety of natural language processing (NLP) tasks due to the attention mechanism, which assigns an importance score for every word relative to other words in a sequence. However, these…

Machine Learning · Computer Science 2023-03-15 Shrihari Sridharan , Jacob R. Stevens , Kaushik Roy , Anand Raghunathan

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

Transformers have become a standard neural network architecture for many NLP problems, motivating theoretical analysis of their power in terms of formal languages. Recent work has shown that transformers with hard attention are quite…

Computation and Language · Computer Science 2022-04-12 William Merrill , Ashish Sabharwal , Noah A. Smith

Sequence-to-sequence models have achieved impressive results on various tasks. However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output…

Machine Learning · Computer Science 2016-08-08 Navdeep Jaitly , David Sussillo , Quoc V. Le , Oriol Vinyals , Ilya Sutskever , Samy Bengio

This article describes our experiments in neural machine translation using the recent Tensor2Tensor framework and the Transformer sequence-to-sequence model (Vaswani et al., 2017). We examine some of the critical parameters that affect the…

Computation and Language · Computer Science 2018-05-03 Martin Popel , Ondřej Bojar

Time-series data in real-world settings typically exhibit long-range dependencies and are observed at non-uniform intervals. In these settings, traditional sequence-based recurrent models struggle. To overcome this, researchers often…

Machine Learning · Statistics 2025-01-14 Fernando Moreno-Pino , Álvaro Arroyo , Harrison Waldon , Xiaowen Dong , Álvaro Cartea

Since hardware resources are limited, the objective of training deep learning models is typically to maximize accuracy subject to the time and memory constraints of training and inference. We study the impact of model size in this setting,…

Computation and Language · Computer Science 2020-06-24 Zhuohan Li , Eric Wallace , Sheng Shen , Kevin Lin , Kurt Keutzer , Dan Klein , Joseph E. Gonzalez

The transformer is the most critical algorithm innovation of the Nature Language Processing (NLP) field in recent years. Unlike the Recurrent Neural Network (RNN) models, Transformers can process on dimensions of sequence lengths in…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-02-23 Jiarui Fang , Yang Yu , Chengduo Zhao , Jie Zhou

We study the capabilities of the transformer architecture with varying depth. Specifically, we designed a novel set of sequence learning tasks to systematically evaluate and comprehend how the depth of transformer affects its ability to…

Machine Learning · Computer Science 2024-04-03 Xingwu Chen , Difan Zou

Transformer-based large language models have achieved remarkable performance across various natural language processing tasks. However, they often struggle with seemingly easy tasks like arithmetic despite their vast capabilities. This…

Computation and Language · Computer Science 2024-07-23 Luyu Qiu , Jianing Li , Chi Su , Chen Jason Zhang , Lei Chen

Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so…

Machine Learning · Computer Science 2025-03-14 Joni-Kristian Kämäräinen

Transformer-based sequence-to-sequence architectures, while achieving state-of-the-art results on a large number of NLP tasks, can still suffer from overfitting during training. In practice, this is usually countered either by applying…

Computation and Language · Computer Science 2022-01-04 Dušan Variš , Ondřej Bojar

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

With the recent developments in the field of Natural Language Processing, there has been a rise in the use of different architectures for Neural Machine Translation. Transformer architectures are used to achieve state-of-the-art accuracy,…

Computation and Language · Computer Science 2021-11-30 Aditya Mandke , Onkar Litake , Dipali Kadam

Transformer models gain popularity because of their superior inference accuracy and inference throughput. However, the transformer is computation-intensive, causing a long inference time. The existing works on transformer inference…

Performance · Computer Science 2023-04-19 Yuan Feng , Hyeran Jeon , Filip Blagojevic , Cyril Guyot , Qing Li , Dong Li

Pseudo-random number generators (PRNGs) are high-nonlinear processes, and they are key blocks in optimization of Large language models. Transformers excel at processing complex nonlinear relationships. Thus it is reasonable to generate…

Machine Learning · Computer Science 2025-08-05 Ran Li , Lingshu Zeng

Transformer models have been widely adopted in various domains over the last years, and especially large language models have advanced the field of AI significantly. Due to their size, the capability of these networks has increased…

Machine Learning · Computer Science 2023-11-10 Yelysei Bondarenko , Markus Nagel , Tijmen Blankevoort

Training large transformer models is one of the most important computational challenges of modern AI. In this paper, we show how to significantly accelerate training of large transformer models by reducing activation recomputation.…

Machine Learning · Computer Science 2022-05-12 Vijay Korthikanti , Jared Casper , Sangkug Lym , Lawrence McAfee , Michael Andersch , Mohammad Shoeybi , Bryan Catanzaro

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami