English
Related papers

Related papers: Alternating Updates for Efficient Transformers

200 papers

Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance. Previous works focus on designing effective architectures suited for tracking,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-18 Jie Zhao , Johan Edstedt , Michael Felsberg , Dong Wang , Huchuan Lu

Transformers suffer from the computational overhead of their quadratic dependence on the length of sequences processed. We present three methods, all adding an intermediate step between training and inference/generation, which extend the…

Machine Learning · Computer Science 2024-08-21 R. I. Cukier

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Machine Learning · Computer Science 2024-11-06 Hanrui Yan , Dan Shao

Reconfigurable data center networks (DCNs) enhance traditional architectures with optical circuit switches (OCSs), enabling dynamic reconfiguration of inter-pod links, i.e., the logical topology. Optimizing this topology is crucial for…

Networking and Internet Architecture · Computer Science 2025-12-22 Yingming Mao , Qiaozhu Zhai , Ximeng Liu , Xinchi Han , Fafan li , Shizhen Zhao , Yuzhou Zhou , Zhen Yao , Xia Zhu

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…

Machine Learning · Computer Science 2023-11-13 Yuhao Chen , Yuxuan Yan , Qianqian Yang , Yuanchao Shu , Shibo He , Zhiguo Shi , Jiming Chen

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention…

Computation and Language · Computer Science 2023-08-30 Hao Liu , Pieter Abbeel

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Computation and Language · Computer Science 2024-02-07 Aydar Bulatov , Yuri Kuratov , Yermek Kapushev , Mikhail S. Burtsev

In contrast to RNNs, which compress their history into a single hidden state, Transformers can attend to all past tokens directly. However, standard Transformers rely solely on the hidden state from the previous layer to represent the…

Machine Learning · Computer Science 2025-05-29 Gleb Gerasimov , Yaroslav Aksenov , Nikita Balagansky , Viacheslav Sinii , Daniil Gavrilov

Recent advances in the field of artificial intelligence have been made possible by deep neural networks. In applications where data are scarce, transfer learning and data augmentation techniques are commonly used to improve the…

Computer Vision and Pattern Recognition · Computer Science 2020-02-13 Mohammad Saeed Abrishami , Amir Erfan Eshratifar , David Eigen , Yanzhi Wang , Shahin Nazarian , Massoud Pedram

Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn can render optimizations like offloading and pre-fetching…

Machine Learning · Computer Science 2026-04-23 Zeyu Shen , Peter Henderson

Successful training of convolutional neural networks is often associated with sufficiently deep architectures composed of high amounts of features. These networks typically rely on a variety of regularization and pruning techniques to…

Computer Vision and Pattern Recognition · Computer Science 2017-10-23 Martin Mundt , Tobias Weis , Kishore Konda , Visvanathan Ramesh

Despite the rapid growth in model architecture, the scarcity of large parallel corpora remains the main bottleneck in Neural Machine Translation. Data augmentation is a technique that enhances the performance of data-hungry models by…

Computation and Language · Computer Science 2023-11-14 Seokjin Oh , Su Ah Lee , Woohwan Jung

Traditional analytical reflectance models, while compact and interpretable, lack the capacity to accurately represent physical measurements. Recent neural models, which closely fit input data, are less generalizable and often more expensive…

Graphics · Computer Science 2026-04-28 Xuanzhe Shen , Xiaohe Ma , Kun Zhou , Hongzhi Wu

This work introduces alternating latent topologies (ALTO) for high-fidelity reconstruction of implicit 3D surfaces from noisy point clouds. Previous work identifies that the spatial arrangement of latent encodings is important to recover…

Computer Vision and Pattern Recognition · Computer Science 2022-12-09 Zhen Wang , Shijie Zhou , Jeong Joon Park , Despoina Paschalidou , Suya You , Gordon Wetzstein , Leonidas Guibas , Achuta Kadambi

Improving information flow in deep networks helps to ease the training difficulties and utilize parameters more efficiently. Here we propose a new convolutional neural network architecture with alternately updated clique (CliqueNet). In…

Computer Vision and Pattern Recognition · Computer Science 2018-04-04 Yibo Yang , Zhisheng Zhong , Tiancheng Shen , Zhouchen Lin

This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes…

Computer Vision and Pattern Recognition · Computer Science 2024-12-04 Said Togru , Youssef Sameh Mostafa , Karim Lotfy

This paper introduces Deep Incremental Boosting, a new technique derived from AdaBoost, specifically adapted to work with Deep Learning methods, that reduces the required training time and improves generalisation. We draw inspiration from…

Machine Learning · Statistics 2017-08-15 Alan Mosca , George D Magoulas

Latency and energy consumption are key metrics in the performance of deep neural network (DNN) accelerators. A significant factor contributing to latency and energy is data transfers. One method to reduce transfers or data is reusing data…

Hardware Architecture · Computer Science 2024-10-15 Michael Gilbert , Yannan Nellie Wu , Joel S. Emer , Vivienne Sze

The transformer architecture has become the foundation of modern Large Language Models (LLMs), yet its theoretical properties are still not well understood. As with classic neural networks, a common approach to improve these models is to…

Artificial Intelligence · Computer Science 2025-09-26 Álvaro Rodríguez Abella , João Pedro Silvestre , Paulo Tabuada

For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for…

Machine Learning · Computer Science 2024-01-12 Deepika Bablani , Jeffrey L. Mckinstry , Steven K. Esser , Rathinakumar Appuswamy , Dharmendra S. Modha