Zobrazeno 1 - 10
of 750
pro vyhledávání: '"He, Yongjun"'
Autor:
Lu, Yao, Bian, Song, Chen, Lequn, He, Yongjun, Hui, Yulong, Lentz, Matthew, Li, Beibin, Liu, Fei, Li, Jialin, Liu, Qi, Liu, Rui, Liu, Xiaoxuan, Ma, Lin, Rong, Kexin, Wang, Jianguo, Wu, Yingjun, Wu, Yongji, Zhang, Huanchen, Zhang, Minjia, Zhang, Qizhen, Zhou, Tianyi, Zhuo, Danyang
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures. Recent large models such as ChatGPT, while revolutionary in their capabilities, face challenges like escalating costs and demand fo
Externí odkaz:
http://arxiv.org/abs/2401.12230
Autor:
Guan, Yadong, Han, Jiqing, Song, Hongwei, Song, Wenjie, Zheng, Guibin, Zheng, Tieran, He, Yongjun
Overlapping sound events are ubiquitous in real-world environments, but existing end-to-end sound event detection (SED) methods still struggle to detect them effectively. A critical reason is that these methods represent overlapping events using shar
Externí odkaz:
http://arxiv.org/abs/2401.05850
Classical machine learning models, such as linear models and tree-based models, are widely used in industry. These models are sensitive to data distribution, thus feature preprocessing, which transforms features from one distribution to another, is a
Externí odkaz:
http://arxiv.org/abs/2310.02540
Autor:
Huang, Qiang, Jiang, Jiawei, Rao, Xi Susie, Zhang, Ce, Han, Zhichao, Zhang, Zitao, Wang, Xin, He, Yongjun, Xu, Quanqing, Zhao, Yang, Hu, Chuang, Shang, Shuo, Du, Bo
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed. Despite the success of these TGNNs, the previous TGNN evaluations reveal several limitations regarding
Externí odkaz:
http://arxiv.org/abs/2308.16385
Autor:
Wang, Jue, Yuan, Binhang, Rimanic, Luka, He, Yongjun, Dao, Tri, Chen, Beidi, Re, Christopher, Zhang, Ce
Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks. Despite recent intensive studies of gradient compression for data parallel-style training, com
Externí odkaz:
http://arxiv.org/abs/2206.01299
Autor:
Yuan, Binhang, He, Yongjun, Davis, Jared Quincy, Zhang, Tianyi, Dao, Tri, Chen, Beidi, Liang, Percy, Re, Christopher, Zhang, Ce
Training foundation models, such as GPT-3 and PaLM, can be extremely expensive, often involving tens of thousands of GPUs running continuously for months. These models are typically trained in specialized clusters featuring fast, homogeneous intercon
Externí odkaz:
http://arxiv.org/abs/2206.01288
Autor:
Lian, Xiangru, Yuan, Binhang, Zhu, Xuefeng, Wang, Yulong, He, Yongjun, Wu, Honghuan, Sun, Lei, Lyu, Haodong, Liu, Chengjun, Dong, Xing, Liao, Yiqiao, Luo, Mingnan, Zhang, Congfei, Xie, Jingru, Li, Haonan, Chen, Lei, Huang, Renjie, Lin, Jianying, Shu, Chengchun, Qiu, Xuezhong, Liu, Zhishan, Kong, Dongying, Yuan, Lei, Yu, Hai, Yang, Sen, Zhang, Ce, Liu, Ji
Deep learning based models have dominated the current landscape of production recommender systems. Furthermore, recent years have witnessed an exponential growth of the model scale--from Google's 2016 model with 1 billion parameters to the latest Fac
Externí odkaz:
http://arxiv.org/abs/2111.05897
Publikováno v:
In Computerized Medical Imaging and Graphics October 2024 117
Publikováno v:
In Information Sciences October 2024 681
Autor:
Zhang, Xiaohui, Zhen, Da, Yi, Faling, Zhang, Tianyi, Li, Xuemei, Wang, Yuhe, Li, Xuguang, Sheng, Yemeng, Liu, Xiaoli, Jin, Tianbo, He, Yongjun
Publikováno v:
In Journal of Surgical Research April 2024 296:18-28