Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Chen, Zhirui"'
Autor:
Chen, Zhirui, Tan, Vincent Y. F.
We consider offline reinforcement learning (RL) with preference feedback in which the implicit reward is a linear function of an unknown parameter. Given an offline dataset, our objective consists in ascertaining the optimal action for each state, wi
Externí odkaz:
http://arxiv.org/abs/2406.12205
Autor:
Sun, Qiushi, Chen, Zhirui, Xu, Fangzhi, Cheng, Kanzhi, Ma, Chang, Yin, Zhangyue, Wang, Jianing, Han, Chengcheng, Zhu, Renyu, Yuan, Shuai, Guo, Qipeng, Qiu, Xipeng, Yin, Pengcheng, Li, Xiaoli, Yuan, Fei, Kong, Lingpeng, Li, Xiang, Wu, Zhiyong
Neural Code Intelligence -- leveraging deep learning to understand, generate, and optimize code -- holds immense potential for transformative impacts on the whole society. Bridging the gap between Natural Language and Programming Language, this domai
Externí odkaz:
http://arxiv.org/abs/2403.14734
Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality. Current approaches often rely on the model's tok
Externí odkaz:
http://arxiv.org/abs/2402.15300
Trustworthy machine learning is of primary importance to the practical deployment of deep learning models. While state-of-the-art models achieve astonishingly good performance in terms of accuracy, recent literature reveals that their predictive conf
Externí odkaz:
http://arxiv.org/abs/2302.02628
Publikováno v:
IEEE Transactions on Information Theory, 2023
We study best arm identification in a federated multi-armed bandit setting with a central server and multiple clients, when each client has access to a {\em subset} of arms and each arm yields independent Gaussian observations. The goal is to identif
Externí odkaz:
http://arxiv.org/abs/2210.07780
Autor:
Yahya, Jawad Haj, Volos, Haris, Bartolini, Davide B., Antoniou, Georgia, Kim, Jeremie S., Wang, Zhe, Kalaitzidis, Kleovoulos, Rollet, Tom, Chen, Zhirui, Geng, Ye, Mutlu, Onur, Sazeides, Yiannakis
User-facing applications running in modern datacenters exhibit irregular request patterns and are implemented using a multitude of services with tight latency requirements. These characteristics render ineffective existing energy conserving technique
Externí odkaz:
http://arxiv.org/abs/2203.02550
Autor:
Zheng, Yue1,2 (AUTHOR) zhengyue@gdmu.edu.cn, Chen, Zhirui1,2 (AUTHOR) czrpork@gdmu.edu.cn, Yang, Jinya1,2 (AUTHOR) yangjinya@gdmu.edu.cn, Zheng, Jing3 (AUTHOR) jzheng@wisc.edu, Shui, Xiaorong4 (AUTHOR) shuixiaor@gdmu.edu.cn, Yan, Yiguang1,5 (AUTHOR) huangshian@gdmu.edu.cn, Huang, Shian5 (AUTHOR) liangzheng@gdmu.edu.cn, Liang, Zheng5 (AUTHOR), Lei, Wei1,2,6 (AUTHOR) leiwei@gdmu.edu.cn, He, Yuan1,2 (AUTHOR) leiwei@gdmu.edu.cn
Publikováno v:
Biomolecules (2218-273X). Jul2024, Vol. 14 Issue 7, p753. 16p.
Autor:
Chen, Zhirui, Cong, Zhen
Publikováno v:
In International Journal of Disaster Risk Reduction 15 April 2024 105
Publikováno v:
In Computers & Industrial Engineering March 2024 189
Autor:
Li, Xinke, Chen, Zhirui, Zhao, Yue, Tong, Zekun, Zhao, Yabang, Lim, Andrew, Zhou, Joey Tianyi
3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues of 3D deep models. Although most of them consider adversarial attacks, w
Externí odkaz:
http://arxiv.org/abs/2103.16074