Zobrazeno 1 - 10
of 256
pro vyhledávání: '"Feng, Pu"'
A flagellated bacterium navigates fluid environments by rotating its helical flagellar bundle. The wobbling of the bacterial body significantly influences its swimming behavior. To quantify the three underlying motions--precession, nutation, and spin
Externí odkaz:
http://arxiv.org/abs/2409.13350
Autor:
Xue, Yanni, Hao, Haojie, Wang, Jiakai, Sheng, Qiang, Tao, Renshuai, Liang, Yu, Feng, Pu, Liu, Xianglong
While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus drawing increas
Externí odkaz:
http://arxiv.org/abs/2409.05021
Autor:
Feng, Pu, Liang, Junkang, Wang, Size, Yu, Xin, Ji, Xin, Chen, Yiting, Zhang, Kui, Shi, Rongye, Wu, Wenjun
In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking
Externí odkaz:
http://arxiv.org/abs/2407.08164
Incorporating symmetry as an inductive bias into multi-agent reinforcement learning (MARL) has led to improvements in generalization, data efficiency, and physical consistency. While prior research has succeeded in using perfect symmetry prior, the r
Externí odkaz:
http://arxiv.org/abs/2401.00167
In multi-agent reinforcement learning (MARL), ensuring robustness against unpredictable or worst-case actions by allies is crucial for real-world deployment. Existing robust MARL methods either approximate or enumerate all possible threat scenarios a
Externí odkaz:
http://arxiv.org/abs/2310.09833
Multi-agent reinforcement learning (MARL) has achieved promising results in recent years. However, most existing reinforcement learning methods require a large amount of data for model training. In addition, data-efficient reinforcement learning requ
Externí odkaz:
http://arxiv.org/abs/2307.16186
Autor:
Li, Simin, Zhang, Shuing, Chen, Gujun, Wang, Dong, Feng, Pu, Wang, Jiakai, Liu, Aishan, Yi, Xin, Liu, Xianglong
Publikováno v:
CVPR 2023
Physical world adversarial attack is a highly practical and threatening attack, which fools real world deep learning systems by generating conspicuous and maliciously crafted real world artifacts. In physical world attacks, evaluating naturalness is
Externí odkaz:
http://arxiv.org/abs/2305.12863
Autor:
Li, Simin, Guo, Jun, Xiu, Jingqiao, Zheng, Yuwei, Feng, Pu, Yu, Xin, Liu, Aishan, Yang, Yaodong, An, Bo, Wu, Wenjun, Liu, Xianglong
This study probes the vulnerabilities of cooperative multi-agent reinforcement learning (c-MARL) under adversarial attacks, a critical determinant of c-MARL's worst-case performance prior to real-world implementation. Current observation-based attack
Externí odkaz:
http://arxiv.org/abs/2302.03322
Publikováno v:
Arabian Journal of Chemistry, Vol 17, Iss 8, Pp 105843- (2024)
Background: The traditional Chinese medicine Ligusticum chuanxiong Hort. (CHX) has been used in the management of heart disease, particularly myocardial ischemia (MI), but its related active constituents and mechanisms remain to be further explored.
Externí odkaz:
https://doaj.org/article/e4bd9e2b0f784a8bb18cc7ccc3c7b818
Publikováno v:
Frontiers in Cardiovascular Medicine, Vol 11 (2024)
BackgroundElevated lipoprotein (a) level was recognized as an independent risk factor for significant adverse cardiovascular events in acute coronary syndrome (ACS) patients. Despite this recognition, the consensus in the literature regarding the pro
Externí odkaz:
https://doaj.org/article/6cffa9bc917548f989392e3f6c8957cc