Zobrazeno 1 - 10
of 5 858
pro vyhledávání: '"Wang,Weidong"'
Mixed-precision quantization offers superior performance to fixed-precision quantization. It has been widely used in signal processing, communication systems, and machine learning. In mixed-precision quantization, bit allocation is essential. Hence,
Externí odkaz:
http://arxiv.org/abs/2412.03101
Autor:
Liao, Wangdan, Wang, Weidong
Spiking Neural Networks (SNNs) offer a biologically inspired alternative to conventional artificial neural networks, with potential advantages in power efficiency due to their event-driven computation. Despite their promise, SNNs have yet to achieve
Externí odkaz:
http://arxiv.org/abs/2411.17439
Autor:
Hu, Junhao, Huang, Wenrui, Wang, Haoyi, Wang, Weidong, Hu, Tiancheng, Zhang, Qin, Feng, Hao, Chen, Xusheng, Shan, Yizhou, Xie, Tao
Large Language Models (LLMs) are critical for a wide range of applications, but serving them efficiently becomes increasingly challenging as inputs become more complex. Context caching improves serving performance by exploiting inter-request dependen
Externí odkaz:
http://arxiv.org/abs/2410.15332
Autor:
Wang, Weidong, Zhu, Haoran
In advancing parallel programming, particularly with OpenMP, the shift towards NLP-based methods marks a significant innovation beyond traditional S2S tools like Autopar and Cetus. These NLP approaches train on extensive datasets of examples to effic
Externí odkaz:
http://arxiv.org/abs/2405.03215
Autor:
Hong, Zesheng, Yue, Yubiao, Chen, Yubin, Cong, Lele, Lin, Huanjie, Luo, Yuanmei, Wang, Mini Han, Wang, Weidong, Xu, Jialong, Yang, Xiaoqi, Chen, Hechang, Li, Zhenzhang, Xie, Sihong
Computer-aided diagnostics has benefited from the development of deep learning-based computer vision techniques in these years. Traditional supervised deep learning methods assume that the test sample is drawn from the identical distribution as the t
Externí odkaz:
http://arxiv.org/abs/2404.18279
Autor:
Liao, Wangdan, Wang, Weidong
Brain-computer interfaces (BCIs) harness electroencephalographic signals for direct neural control of devices, offering a significant benefit for individuals with motor impairments. Traditional machine learning methods for EEG-based motor imagery (MI
Externí odkaz:
http://arxiv.org/abs/2404.14869
Channel state information (CSI) is important to reap the full benefits of millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems. The traditional channel estimation methods using pilot frames (PF) lead to excessive overhead. T
Externí odkaz:
http://arxiv.org/abs/2401.01794
Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural network on sm
Externí odkaz:
http://arxiv.org/abs/2311.08179
Deep learning has been widely used in radio frequency (RF) fingerprinting. Despite its excellent performance, most existing methods only consider a closed-set assumption, which cannot effectively tackle signals emitted from those unknown devices that
Externí odkaz:
http://arxiv.org/abs/2306.13895
As a revolutionary generative paradigm of deep learning, generative adversarial networks (GANs) have been widely applied in various fields to synthesize realistic data. However, it is challenging for conventional GANs to synthesize raw signal data, e
Externí odkaz:
http://arxiv.org/abs/2306.13893