English
Related papers

Related papers: Accelerating Multi-Scale Deformable Attention Usin…

200 papers

Deep Neural Networks (DNNs) have made significant improvements to reach the desired accuracy to be employed in a wide variety of Machine Learning (ML) applications. Recently the Google Brain's team demonstrated the ability of Capsule…

Machine Learning · Computer Science 2021-01-26 Alberto Marchisio , Andrea Massa , Vojtech Mrazek , Beatrice Bussolino , Maurizio Martina , Muhammad Shafique

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…

Machine Learning · Computer Science 2021-08-12 Yao Zhang , Yunpu Ma , Thomas Seidl , Volker Tresp

The landscape of computational building blocks of efficient image restoration architectures is dominated by a combination of convolutional processing and various attention mechanisms. However, convolutional filters, while efficient, are…

Image and Video Processing · Electrical Eng. & Systems 2025-01-23 Mohammad Shahab Sepehri , Zalan Fabian , Mahdi Soltanolkotabi

Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory-constrained devices. While GPUs offer fast inference, their limited memory compared to CPUs means…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-06 Yujie Zhang , Shivam Aggarwal , Tulika Mitra

Sampling is an important process in many GNN structures in order to train larger datasets with a smaller computational complexity. However, compared to other processes in GNN (such as aggregate, backward propagation), the sampling process…

Machine Learning · Computer Science 2022-09-08 Yuchen Gui , Boyi Wei , Wei Yuan , Xi Jin

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with…

Machine Learning · Computer Science 2025-11-10 Andrew DiGiugno , Ausif Mahmood

With the tremendous success of deep learning, there exists imminent need to deploy deep learning models onto edge devices. To tackle the limited computing and storage resources in edge devices, model compression techniques have been widely…

Machine Learning · Computer Science 2020-10-20 Sung-En Chang , Yanyu Li , Mengshu Sun , Weiwen Jiang , Runbin Shi , Xue Lin , Yanzhi Wang

Various processing-in-memory (PIM) accelerators based on various devices, micro-architectures, and interfaces have been proposed to accelerate deep neural networks (DNNs). How to deploy DNNs onto PIM-based accelerators is the key to explore…

Hardware Architecture · Computer Science 2024-11-15 Xiaotian Sun , Xinyu Wang , Wanqian Li , Yinhe Han , Xiaoming Chen

Neural network training is inherently sequential where the layers finish the forward propagation in succession, followed by the calculation and back-propagation of gradients (based on a loss function) starting from the last layer. The…

Machine Learning · Computer Science 2023-12-01 Vahid Janfaza , Shantanu Mandal , Farabi Mahmud , Abdullah Muzahid

In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model…

Machine Learning · Computer Science 2024-12-02 Xingyu Xie , Pan Zhou , Huan Li , Zhouchen Lin , Shuicheng Yan

Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using…

Hardware Architecture · Computer Science 2024-11-12 Zihang Song , Prabodh Katti , Osvaldo Simeone , Bipin Rajendran

Deep neural network (DNN) latency characterization is a time-consuming process and adds significant cost to Neural Architecture Search (NAS) processes when searching for efficient convolutional neural networks for embedded vision…

Machine Learning · Computer Science 2022-05-26 Saad Abbasi , Alexander Wong , Mohammad Javad Shafiee

The attention mechanism is becoming increasingly popular in Natural Language Processing (NLP) applications, showing superior performance than convolutional and recurrent architectures. However, attention becomes the compution bottleneck…

Hardware Architecture · Computer Science 2024-07-22 Hanrui Wang , Zhekai Zhang , Song Han

Training deep neural networks (DNNs) is a computationally expensive job, which can take weeks or months even with high performance GPUs. As a remedy for this challenge, community has started exploring the use of more efficient data…

Machine Learning · Computer Science 2022-03-15 Seock-Hwan Noh , Jahyun Koo , Seunghyun Lee , Jongse Park , Jaeha Kung

While Graph Neural Networks (GNNs) are popular in the deep learning community, they suffer from several challenges including over-smoothing, over-squashing, and gradient vanishing. Recently, a series of models have attempted to relieve…

Machine Learning · Computer Science 2022-11-18 Junxiang Wang , Hongyi Li , Zheng Chai , Yongchao Wang , Yue Cheng , Liang Zhao

Brain-inspired learning mechanisms, e.g. spike timing dependent plasticity (STDP), enable agile and fast on-the-fly adaptation capability in a spiking neural network. When incorporating emerging nanoscale resistive non-volatile memory (NVM)…

Neural and Evolutionary Computing · Computer Science 2020-02-19 Xinyu Wu , Vishal Saxena

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency…

Computer Vision and Pattern Recognition · Computer Science 2019-03-26 Tao Hu , Honggang Qi , Qingming Huang , Yan Lu

Large language models (LLMs) face significant inference latency due to inefficiencies in GEMM operations, weight access, and KV cache access, especially in real-time scenarios. This highlights the need for a versatile compute-memory…

Hardware Architecture · Computer Science 2025-09-15 Huizheng Wang , Zichuan Wang , Zhiheng Yue , Yousheng Long , Taiquan Wei , Jianxun Yang , Yang Wang , Chao Li , Shaojun Wei , Yang Hu , Shouyi Yin

Mixture-of-Experts (MoE) models scale large language models through conditional computation, but inference becomes memory-bound once expert weights exceed the capacity of GPU memory. In this case, weights must be offloaded to external…

Machine Learning · Computer Science 2025-12-05 Zehao Fan , Zhenyu Liu , Yunzhen Liu , Yayue Hou , Hadjer Benmeziane , Kaoutar El Maghraoui , Liu Liu

Intensive computation is entering data centers with multiple workloads of deep learning. To balance the compute efficiency, performance, and total cost of ownership (TCO), the use of a field-programmable gate array (FPGA) with…

Computer Vision and Pattern Recognition · Computer Science 2019-09-19 Xiaoyu Yu , Yuwei Wang , Jie Miao , Ephrem Wu , Heng Zhang , Yu Meng , Bo Zhang , Biao Min , Dewei Chen , Jianlin Gao