CommentsWe have further refined the benchmark construction and experimental presentation to improve clarity and consistency. The revised version includes updated task design, food-resource data, and evaluation details to better align the benchmark with the intended food resource referral setting. These changes provide a more precise presentation of the experimental findings
机构
*
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(北京大学智能科学与技术学院通用人工智能国家重点实验室)
;
Delta Intelligence(三角洲智能公司)
;
PKU-Wuhan Institute for Artificial Intelligence(北京大学武汉人工智能研究院)
;
Hubei Humanoid Robot Innovation Center Co., Ltd.(湖北人形机器人创新中心有限公司)
;
China Academy of Information and Communications Technology(中国信息通信研究院)
机构
*
National Yang Ming Chiao Tung University(国立阳明交通大学)
;
Institute of Computer Science and Engineering(工程与计算机科学学院)
;
College of Artificial Intelligence(人工智能学院)
CommentsThis version includes a revised manuscript presentation and formatting, expanded methodological and experimental details, enhanced reproducibility documentation, and improved benchmark framing and evaluation descriptions
JailWAM: Jailbreaking World Action Models in Robot Control
JailWAM: 在机器人控制中对World Action Models进行劫持
Hanqing Liu, Songping Wang, Jiahuan Long, Jiacheng Hou, Jialiang Sun, Chao Li, Yang Yang, Wei Peng, Xu Liu, Tingsong Jiang, Yao Mu, Wen Yao
机构
*
MoE key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University(上海交通大学人工智能研究院教育部重点实验室)
;
PR Lab, Nanjing University(南京大学PR实验室)
;
Defense Innovation Institute, Chinese Academy of Military Science(军事科学院国防创新研究院)