Can LLM Safety Be Ensured by Constraining Parameter Regions?
通过约束参数区域能否确保大语言模型的安全性?
Zongmin Li, Jian Su, Farah Benamara, Aixin Sun
机构
*
Nanyang Technological University(南洋理工大学)
;
Institute for Infocomm Research (I 2 R)(信息通信研究所)
;
IRIT, Université de Toulouse, CNRS, Toulouse INP(图卢兹大学IRIT研究所、法国国家科学研究中心)
;
IPAL, CNRS-NUS-A*STAR(IPAL、法国国家科学研究中心-南洋理工大学-A*STAR)
Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities
物理信息神经网络的进化优化:Evo-PINN的前沿与机遇
Jian Cheng Wong, Abhishek Gupta, Chin Chun Ooi, Pao-Hsiung Chiu, Jiao Liu, Yew-Soon Ong
机构
*
Agency for Science, Technology and Research (A*STAR)(科技研究局)
;
Indian Institute of Technology (IIT) Goa(印度理工学院 Goa分校)
;
Nanyang Technological University(南洋理工大学)
Evolutionary Optimization of Physics-Informed Neural Networks: Advancing Generalizability by the Baldwin Effect
物理信息神经网络的进化优化:通过巴尔德效应提升通用性
Jian Cheng Wong, Chin Chun Ooi, Abhishek Gupta, Pao-Hsiung Chiu, Joshua Shao Zheng Low, My Ha Dao, Yew-Soon Ong
机构
*
Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore(高性能计算研究所,科技研究局,新加坡)
;
School of Mechanical Sciences, Indian Institute of Technology Goa, India(机械科学学院,印度理工学院 Goa)
;
College of Computing and Data Science, Nanyang Technological University, Singapore(计算与数据科学学院,南洋理工大学)
;
Technology Centre for Offshore and Marine, Singapore(海上与海洋技术中心,新加坡)
;
Agency for Science, Technology and Research, Singapore(科技研究局,新加坡)
AI总结
本文提出通过巴尔德效应框架优化PINNs,提升其在多物理任务中的通用性和预测精度。
CommentsAccepted for publication in IEEE Transactions on Evolutionary Computation
Journal refIEEE Transactions on Evolutionary Computation, 2026