Zobrazeno 1 - 10
of 6 085
pro vyhledávání: '"XIAO, Xi"'
Autor:
Huang, Linhao, Jiang, Xue, Wang, Zhiqiang, Mo, Wentao, Xiao, Xi, Han, Bo, Yin, Yongjie, Zheng, Feng
Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models--a common and practical real world scenario--r
Externí odkaz:
http://arxiv.org/abs/2501.01042
Autor:
Xing, Sizhe, Sun, Aolong, Wang, Chengxi, Wang, Yizhi, Dong, Boyu, Hu, Junhui, Deng, Xuyu, Yan, An, Liu, Yingjun, Hu, Fangchen, Li, Zhongya, Huang, Ouhan, Zhao, Junhao, Zhou, Yingjun, Li, Ziwei, Shi, Jianyang, Xiao, Xi, Penty, Richard, Cheng, Qixiang, Chi, Nan, Zhang, Junwen
The rapid advancement of generative artificial intelligence (AI) in recent years has profoundly reshaped modern lifestyles, necessitating a revolutionary architecture to support the growing demands for computational power. Cloud computing has become
Externí odkaz:
http://arxiv.org/abs/2412.12126
Black-box context-free grammar inference presents a significant challenge in many practical settings due to limited access to example programs. The state-of-the-art methods, Arvada and Treevada, employ heuristic approaches to generalize grammar rules
Externí odkaz:
http://arxiv.org/abs/2408.16706
Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a
Externí odkaz:
http://arxiv.org/abs/2408.12099
Autor:
Du, Yongqiang, Li, Bing-Hong, Hua, Xin, Cao, Xiao-Yu, Zhao, Zhengeng, Xie, Feng, Zhang, Zhenrong, Yin, Hua-Lei, Xiao, Xi, Wei, Kejin
The development of quantum networks is paramount towards practical and secure communications. Quantum digital signatures (QDS) offer an information-theoretically secure solution for ensuring data integrity, authenticity, and non-repudiation, rapidly
Externí odkaz:
http://arxiv.org/abs/2407.07513
Autor:
Xiao, Xi, Wang, Wentao, Xie, Jiacheng, Zhu, Lijing, Chen, Gaofei, Li, Zhengji, Wang, Tianyang, Xu, Min
Drug target binding affinity (DTA) is a key criterion for drug screening. Existing experimental methods are time-consuming and rely on limited structural and domain information. While learning-based methods can model sequence and structural informati
Externí odkaz:
http://arxiv.org/abs/2406.17697
Randomized Smoothing (RS) is currently a scalable certified defense method providing robustness certification against adversarial examples. Although significant progress has been achieved in providing defenses against $\ell_p$ adversaries, the intera
Externí odkaz:
http://arxiv.org/abs/2406.02309
Autor:
Chen, Zhicheng, Xiao, Xi, Xu, Ke, Zhang, Zhong, Rong, Yu, Li, Qing, Gan, Guojun, Xu, Zhiqiang, Zhao, Peilin
Multivariate time series prediction is widely used in daily life, which poses significant challenges due to the complex correlations that exist at multi-grained levels. Unfortunately, the majority of current time series prediction models fail to simu
Externí odkaz:
http://arxiv.org/abs/2405.19661
Autor:
Li, Zhengji, Xiao, Xi, Xie, Jiacheng, Fan, Yuxiao, Wang, Wentao, Chen, Gang, Zhang, Liqiang, Wang, Tianyang
With the development of modern society, traffic volume continues to increase in most countries worldwide, leading to an increase in the rate of pavement damage Therefore, the real-time and highly accurate pavement damage detection and maintenance hav
Externí odkaz:
http://arxiv.org/abs/2405.17905
Autor:
Lin, Zhutian, Pan, Junwei, Yu, Haibin, Xiao, Xi, Wang, Ximei, Feng, Zhixiang, Wen, Shifeng, Huang, Shudong, Liu, Dapeng, Xiao, Lei
Multi-domain learning (MDL) has become a prominent topic in enhancing the quality of personalized services. It's critical to learn commonalities between domains and preserve the distinct characteristics of each domain. However, this leads to a challe
Externí odkaz:
http://arxiv.org/abs/2405.12706