机构
*
School of Artificial Intelligence and Robotics, Xiamen University Malaysia(厦门大学马来西亚分校人工智能与机器人学院)
;
S.M.A.R.T. NEXUS Centre of Excellence, Xiamen University Malaysia(厦门大学马来西亚分校S.M.A.R.T. NEXUS卓越研究中心)
Fortifying Time Series: DTW-Certified Robust Anomaly Detection
强化时间序列:DTW认证的鲁棒异常检测
Shijie Liu, Tansu Alpcan, Christopher Leckie, Sarah Erfani
机构
*
Department of Electrical and Electronic Engineering(电气与电子工程系)
;
University of Melbourne(墨尔本大学)
;
School of Computing and Information Systems(计算与信息系统学院)
Bayesian Conformal Prediction as a Decision Risk Problem
贝叶斯符合预测作为决策风险问题
Fanyi Wu, Veronika Lohmanova, Samuel Kaski, Michele Caprio
机构
*
Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系)
;
UKRI AI Centre for Doctoral Training in Decision Making for Complex Systems(UKRI人工智能博士培训中心(复杂系统决策))
;
Department of Computer Science, Aalto University(艾洛大学计算机科学系)
;
ELLIS Institute, Finland(芬兰ELLIS研究所)
Mechanistic Interpretability with Sparse Autoencoder Neural Operators
基于稀疏自编码器的神经算子机制可解释性
Bahareh Tolooshams, Ailsa Shen, Anima Anandkumar
机构
*
University of Alberta(阿尔伯塔大学)
;
Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所(Amii))
;
California Institute of Technology (Caltech)(加州理工学院(Caltech))
CommentsTolooshams and Shen has equal contribution. Preprint. Earlier version was presented as Oral and Extended Abstract at the Workshop on Unifying Representations in Neural Models (UniReps 2025) at NeurIPS