Zobrazeno 1 - 10
of 336
pro vyhledávání: '"Li, Hongjia"'
Existing wisdom demonstrates the significance of syntactic knowledge for the improvement of neural machine translation models. However, most previous works merely focus on leveraging the source syntax in the well-known encoder-decoder framework. In s
Externí odkaz:
http://arxiv.org/abs/2305.17698
Publikováno v:
Cybersecurity, Vol 7, Iss 1, Pp 1-21 (2024)
Abstract Unprotected gradient exchange in federated learning (FL) systems may lead to gradient leakage-related attacks. CKKS is a promising approximate homomorphic encryption scheme to protect gradients, owing to its unique capability of performing o
Externí odkaz:
https://doaj.org/article/841dd36c89f843ce9556212527a0d9af
Autor:
Huang, Shaoyi, Liu, Ning, Liang, Yueying, Peng, Hongwu, Li, Hongjia, Xu, Dongkuan, Xie, Mimi, Ding, Caiwen
With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy. Existing BERT pruning methods
Externí odkaz:
http://arxiv.org/abs/2206.10461
Publikováno v:
In Structure 5 September 2024 32(9):1507-1518
Publikováno v:
In Journal of Energy Storage 1 September 2024 97 Part A
Publikováno v:
In Environmental Technology & Innovation August 2024 35
Autor:
Xu, Chengyin, Chai, Zenghao, Xu, Zhengzhuo, Li, Hongjia, Zuo, Qiruyi, Yang, Lingyu, Yuan, Chun
Deep hashing has shown promising performance in large-scale image retrieval. However, latent codes extracted by Deep Neural Networks (DNNs) will inevitably lose semantic information during the binarization process, which damages the retrieval accurac
Externí odkaz:
http://arxiv.org/abs/2112.02225
Autor:
Wu Quanyang, Huang Yao, Wang Sicong, Qi Linlin, Zhang Zewei, Hou Donghui, Li Hongjia, Zhao Shijun
Publikováno v:
Cancer Medicine, Vol 13, Iss 7, Pp n/a-n/a (2024)
Abstract Background The exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies
Externí odkaz:
https://doaj.org/article/8daf31bb3600441791d6550eb674b938
Autor:
Yang, Junjie, Li, Hongjia, Gao, Teng, Zhang, Changsheng, Xia, Yuanhua, Li, Jian, Huang, Chaoqiang, Zhong, Shengyi, Sun, Guangai
Publikováno v:
In Journal of Alloys and Compounds 15 March 2024 977
Publikováno v:
In Ultramicroscopy January 2024 255