MALT: Lightweight Curvature-Aware Muon via Diagonal Preconditioning
MALT:通过对角预条件化实现的轻量曲率感知Muon
Tongle Wu, Huanyu Dong, Ying Sun, Ziye Ma
机构
*
School of Electrical Engineering and Computer Science, The Pennsylvania State University(宾夕法尼亚州立大学电气工程与计算机科学学院)
;
Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)
Towards Trustworthy Hypergraph Neural Networks under Label Noise
面向标签噪声下可信赖的超图神经网络
Mengyao Zhou, Zhiheng Zhou, Xiao Han, Guiying Yan
机构
*
Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)
;
University of Chinese Academy of Sciences(中国科学院大学)
;
School of Mathematics and Statistics, Shandong University(山东大学数学与统计学院)
;
School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院)
CommentsA revised version of this paper has been accepted for presentation at UKCI 2026 (https://ukci2026.coventry.ac.uk/home/) and will be published by Springer
State2State: Environment-Derived Mid-Training for LLM Agents
State2State:面向大语言模型智能体的环境衍生式中间训练
Xuanyu Lei, Yiqi Zhu, Chenliang Li, Kaiming Liu, Peng Li, Ming Yan, Jieping Ye, Ya-Qin Zhang, Yang Liu
机构
*
Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院)
;
Institute for AI, Tsinghua University(清华大学人工智能研究院)
;
Institute of Intelligent Computing, Alibaba Group(阿里巴巴集团智能计算研究院)
Personalized Federated Sparse Adaptation of Time-Series Foundation Models
时间序列基础模型的个性化联邦稀疏适配
Priyanka Nihalchandani, Naman Srivastava, Varun Ojha, Pandarasamy Arjunan
机构
*
Robert Bosch Centre for Cyber-Physical Systems, Indian Institute of Science(罗伯特·博世网络物理系统中心,印度科学学院)
;
School of Computing, Newcastle University(纽卡斯尔大学计算学院)