Zobrazeno 1 - 10
of 33 246
pro vyhledávání: '"Juanjuan An"'
Autor:
Li, Xurui, Yao, Juanjuan
The advent of Large Language Models (LLMs) has ushered in a new era of artificial intelligence, with the potential to transform various sectors through automation and insightful analysis. The Mixture of Experts (MoE) architecture has been proposed as
Externí odkaz:
http://arxiv.org/abs/2410.10896
Autor:
Shi, Bingxian, Geng, Yanyan, Wang, Hengning, Yang, Jianhui, Shang, Chenglin, Wang, Manyu, Mi, Shuo, Huang, Jiale, Pan, Feihao, Gui, Xuejuan, Wang, Jinchen, Liu, Juanjuan, Xu, Daye, Zhang, Hongxia, Qin, Jianfei, Wang, Hongliang, Hao, Lijie, Tian, Mingliang, Cheng, Zhihai, Zheng, Guolin, Cheng, Peng
Publikováno v:
J.Am.Chem.Soc.2024,146,21546-21554
Two-dimensional (2D) magnets have attracted significant attentions in recent years due to their importance in the research on both fundamental physics and spintronic applications. Here, we report the discovery of a new ternary compound FePd2Te2. It f
Externí odkaz:
http://arxiv.org/abs/2409.04800
Current out-of-distribution (OOD) detection methods typically assume balanced in-distribution (ID) data, while most real-world data follow a long-tailed distribution. Previous approaches to long-tailed OOD detection often involve balancing the ID dat
Externí odkaz:
http://arxiv.org/abs/2408.06742
Despite the significant advances that deep neural networks (DNNs) have achieved in various visual tasks, they still exhibit vulnerability to adversarial examples, leading to serious security concerns. Recent adversarial training techniques have utili
Externí odkaz:
http://arxiv.org/abs/2408.06079
Autor:
Yu, Yi, Yu, Jingru, Wang, Xuhong, Li, Juanjuan, Lin, Yilun, He, Conghui, Yang, Yanqing, Qiao, Yu, Li, Li, Wang, Fei-Yue
Data has been increasingly recognized as a critical factor in the future economy. However, constructing an efficient data trading market faces challenges such as privacy breaches, data monopolies, and misuse. Despite numerous studies proposing algori
Externí odkaz:
http://arxiv.org/abs/2407.11466
Second harmonic generation (SHG) extensively employs periodically poled nonlinear crystals through forward quasi-phase-matching to achieve efficient frequency conversion. As poling periods approach sub-micrometers, backward quasi-phase-matching has a
Externí odkaz:
http://arxiv.org/abs/2407.09464
Ensuring the robustness of computer vision models against adversarial attacks is a significant and long-lasting objective. Motivated by adversarial attacks, researchers have devoted considerable efforts to enhancing model robustness by adversarial tr
Externí odkaz:
http://arxiv.org/abs/2407.04016
By considering a single lossy three-dimensional cavity mode and using a quasinormal mode expansion for the photonic medium, we show that the frequency-dependence of the coupling between the cavity and its reservoir is dependent on both the cavity con
Externí odkaz:
http://arxiv.org/abs/2407.01855
The vulnerability of Deep Neural Networks to adversarial perturbations presents significant security concerns, as the imperceptible perturbations can contaminate the feature space and lead to incorrect predictions. Recent studies have attempted to ca
Externí odkaz:
http://arxiv.org/abs/2406.11576
This paper aims to enhance the transferability of adversarial samples in targeted attacks, where attack success rates remain comparatively low. To achieve this objective, we propose two distinct techniques for improving the targeted transferability f
Externí odkaz:
http://arxiv.org/abs/2405.06340