Zobrazeno 1 - 10
of 5 577
pro vyhledávání: '"MA, Qian"'
Autor:
Ma, Qian, Mao, Haitao, Liu, Jingzhe, Zhang, Zhehua, Feng, Chunlin, Song, Yu, Shao, Yihan, Ma, Yao
Self-supervised learning~(SSL) is essential to obtain foundation models in NLP and CV domains via effectively leveraging knowledge in large-scale unlabeled data. The reason for its success is that a suitable SSL design can help the model to follow th
Externí odkaz:
http://arxiv.org/abs/2408.11243
High-performance photonic switches are essential for large-scale optical routing for AI large models and Internet of things. Realizing nonvolatility can further reduce power consumption and expand application scenarios. We propose a nonvolatile 2*2 s
Externí odkaz:
http://arxiv.org/abs/2407.00070
Among various promising candidate technologies for the sixth-generation (6G) wireless communications, recent advances in microwave metasurfaces have sparked a new research area of reconfigurable intelligent surfaces (RISs). By controllably reprogramm
Externí odkaz:
http://arxiv.org/abs/2403.16062
Autor:
Ma, Qian, Chi, Hongliang, Zhang, Hengrui, Liu, Kay, Zhang, Zhiwei, Cheng, Lu, Wang, Suhang, Yu, Philip S., Ma, Yao
The rise of self-supervised learning, which operates without the need for labeled data, has garnered significant interest within the graph learning community. This enthusiasm has led to the development of numerous Graph Contrastive Learning (GCL) tec
Externí odkaz:
http://arxiv.org/abs/2402.15680
Autor:
Li, Xinyu, You, Jian Wei, Gu, Ze, Ma, Qian, Chen, Long, Zhang, Jingyuan, Jin, Shi, Cui, Tie Jun
Reconfigurable intelligent surfaces (RISs) have flexible and exceptional performance in manipulating electromagnetic waves and customizing wireless channels. These capabilities enable them to provide a plethora of valuable activity-related informatio
Externí odkaz:
http://arxiv.org/abs/2311.07873
To investigate the effectiveness of the model explanation in detecting adversarial examples, we reproduce the results of two papers, Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples and Is AmI (Attacks Meet Interpreta
Externí odkaz:
http://arxiv.org/abs/2310.08808
Autor:
Ma, Qian, Zhang, Zijian, Zhao, Xiangyu, Li, Haoliang, Zhao, Hongwei, Wang, Yiqi, Liu, Zitao, Wang, Wanyu
With the acceleration of urbanization, traffic forecasting has become an essential role in smart city construction. In the context of spatio-temporal prediction, the key lies in how to model the dependencies of sensors. However, existing works basica
Externí odkaz:
http://arxiv.org/abs/2309.11284
Autor:
Zhang, Zijian, Zhao, Xiangyu, Liu, Qidong, Zhang, Chunxu, Ma, Qian, Wang, Wanyu, Zhao, Hongwei, Wang, Yiqi, Liu, Zitao
In the era of information explosion, spatio-temporal data mining serves as a critical part of urban management. Considering the various fields demanding attention, e.g., traffic state, human activity, and social event, predicting multiple spatio-temp
Externí odkaz:
http://arxiv.org/abs/2309.09500
Publikováno v:
Shipin Kexue, Vol 45, Iss 17, Pp 316-325 (2024)
Phenolic compounds are a class of important plant secondary metabolites, which are regarded as prime constituents of nutraceuticals and functional foods due to their various bioactivities. Lycium barbarum L., an excellent tonic used for both medicina
Externí odkaz:
https://doaj.org/article/137cccbf66524b3a936ecb86af8609ca
Publikováno v:
Zhejiang dianli, Vol 43, Iss 9, Pp 19-28 (2024)
In the context of dual carbon goals， this paper proposes a multi-energy pricing and dispatch optimization strategy for integrated electricity-heat energy systems in an industrial park， based on the Stackelberg game to address low-carbon schedulin
Externí odkaz:
https://doaj.org/article/d1163a39b9ff4749af4d67ca78196942