Zobrazeno 1 - 10
of 494
pro vyhledávání: '"Wang, Yinong"'
Autor:
Chakraborty, Rwiddhi, Wang, Yinong, Gao, Jialu, Zheng, Runkai, Zhang, Cheng, De la Torre, Fernando
The widespread success of deep learning models today is owed to the curation of extensive datasets significant in size and complexity. However, such models frequently pick up inherent biases in the data during the training process, leading to unrelia
Externí odkaz:
http://arxiv.org/abs/2409.18055
We propose residual denoising diffusion models (RDDM), a novel dual diffusion process that decouples the traditional single denoising diffusion process into residual diffusion and noise diffusion. This dual diffusion framework expands the denoising-b
Externí odkaz:
http://arxiv.org/abs/2308.13712
Publikováno v:
Teshugang, Vol 45, Iss 4, Pp 47-54 (2024)
The effect of different electron beam refining parameters on the type, quantity and size distribution of inclusions during melt solidification was studied. The content of O and N in FGH4096 alloy and the type, quantity and size distribution of in
Externí odkaz:
https://doaj.org/article/945f0d2cf99644bf9ec518680577a7fc
Autor:
Chang, Kai, Tan, Yi, Bai, Rusheng, Dong, Gengyi, Li, Pengting, Liu, Yufeng, Yuan, Hua, Wang, Yinong
Publikováno v:
In Separation and Purification Technology 24 December 2024 351
Publikováno v:
In Separation and Purification Technology 3 December 2024 349
Autor:
Cui, Xiaoling, Zhu, Junlong, Wang, Jie, Song, Linhu, Wang, Yinong, Zhang, Junwei, Zhou, Junfei, Li, Xin, Zhao, Dongni, Li, Shiyou
Publikováno v:
In Materials Today Energy July 2024 43
Autor:
Wang, Yinong, Xiao, Zhiguang, Feng, Xiao, Shi, Shuyan, Liu, Dongdong, Li, Rui, Jiang, Feng, Liu, Jinzhang
Publikováno v:
In Sensors and Actuators: B. Chemical 15 April 2024 405
Autor:
You, Xiaogang, Dong, Gengyi, Zhang, Qifei, Zhang, Huixing, Cao, Tieshan, Zhou, Haijing, Yiliti, Yijiala, Cui, Hongyang, Li, Yi, Liu, Dongfu, Hu, Yebing, Li, Pengting, Wang, Yinong
Publikováno v:
In Materials Characterization April 2024 210
Autor:
Selby, Kira A., Wang, Yinong, Wang, Ruizhe, Passban, Peyman, Rashid, Ahmad, Rezagholizadeh, Mehdi, Poupart, Pascal
Despite recent monumental advances in the field, many Natural Language Processing (NLP) models still struggle to perform adequately on noisy domains. We propose a novel probabilistic embedding-level method to improve the robustness of NLP models. Our
Externí odkaz:
http://arxiv.org/abs/2104.08420
Autor:
Zhang, Ningshuang, Wang, Mengya, Quan, Yin, Li, Xiaohua, Hu, Xinyi, Yan, JingXuan, Wang, Yinong, Sun, Mengzhen, Li, Shiyou
Publikováno v:
In Journal of Industrial and Engineering Chemistry June 2024