Zobrazeno 1 - 10
of 1 010
pro vyhledávání: '"Zhang, ShuDong"'
Glitch tokens in Large Language Models (LLMs) can trigger unpredictable behaviors, threatening model reliability and safety. Existing detection methods rely on predefined patterns, limiting their adaptability across diverse LLM architectures. We prop
Externí odkaz:
http://arxiv.org/abs/2410.15052
Solar photothermal conversion is one of the most straightforward methods to utilize solar energy. In this manuscript, a novel double-layer structure constructed of graphene enhanced thermoplastic polyurethanes (G-TPU) and neat thermoplastic polyureth
Externí odkaz:
http://arxiv.org/abs/2410.06470
Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of which are de
Externí odkaz:
http://arxiv.org/abs/2405.19360
Autor:
Zhang, Miao1,2 (AUTHOR) mia.zhang@northeastern.edu, Zhang, Shudong3 (AUTHOR), Wang, Lin3 (AUTHOR), Zhang, Zhe3 (AUTHOR), Hu, Qin3 (AUTHOR) huqin@bidc.org.cn, Liu, Dongyang1 (AUTHOR) huqin@bidc.org.cn
Publikováno v:
Pharmaceutics. Oct2024, Vol. 16 Issue 10, p1324. 20p.
Autor:
Zhang, Shudong.
Publikováno v:
Restricted access.
Thesis (M.A.)--University of Missouri-Columbia, 2008.
The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general
The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general
Externí odkaz:
http://hdl.handle.net/10355/6080
In this paper, we investigate on improving the adversarial robustness obtained in adversarial training (AT) via reducing the difficulty of optimization. To better study this problem, we build a novel Bregman divergence perspective for AT, in which AT
Externí odkaz:
http://arxiv.org/abs/2208.12511
Adversarial training (AT) has proven to be one of the most effective ways to defend Deep Neural Networks (DNNs) against adversarial attacks. However, the phenomenon of robust overfitting, i.e., the robustness will drop sharply at a certain stage, alw
Externí odkaz:
http://arxiv.org/abs/2205.11744
Gold nanospheres (Au NSs) and gold nanorods (Au NRs) are traditional noble metal plasmonic nanomaterials. Particularly, Au NRs with tunable longitudinal plasmon resonance from visible to the near infrared (NIR) range were suitable for high efficient
Externí odkaz:
http://arxiv.org/abs/2204.03976
Autor:
Cui, Jian, Li, Meng, Wu, Yang, Shen, Qinge, Yan, Wei, Zhang, Shudong, Chen, Min, Zhou, Jingjing
Publikováno v:
In Journal of Affective Disorders 15 November 2024 365:1-8
Autor:
Zhang, Shudong, van Spronsen, Bas, Fonck, Myrthe, van Logtestijn, Richard S.P., Soudzilovskaia, Nadia A., Trimbos, Krijn, Cornelissen, Johannes H.C.
Publikováno v:
In Forest Ecology and Management 1 November 2024 571