机构
*
School of Software Technology, Zhejiang University(浙江大学软件学院)
;
Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
;
Ningbo Global Innovation Center, Zhejiang University(浙江大学宁波全球创新中心)
;
Washington University in St. Louis(圣路易斯华盛顿大学)
;
University of Science and Technology of China(中国科学技术大学)
;
College of Computer Science and Technology, Zhejiang Normal University(浙江师范大学计算机科学与技术学院)
;
China Electronics Technology Design and Research Institute(中国电子技术设计与研究院)
CommentsThis is an extended version of the paper "Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits," accepted to NeurIPS 2025
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
SafeVLA: 通过约束学习实现视觉-语言-动作模型的安全对齐
Borong Zhang, Yuhao Zhang, Jiaming Ji, Yingshan Lei, Yishuai Cai, Josef Dai, Yuanpei Chen, Yaodong Yang
机构
*
Institute for Artificial Intelligence, Peking University(人工智能研究院,北京大学)
;
PKU-PsiBot Joint Lab(北京大学PsiBot联合实验室)
;
State Key Laboratory of General Artificial Intelligence, Peking University(通用人工智能国家重点实验室,北京大学)
;
Zhongguancun Academy(中关村学院)
机构
*
Faculty of Information Technology, Monash University(墨尔本大学信息科技学院)
;
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)(教育部计算能力网络与信息安全重点实验室,山东计算机科学中心,齐鲁大学(山东科学院))
;
Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science(山东省计算能力互联网与服务计算重点实验室,山东省计算机科学基础研究中心)
;
School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院)