Alignment Risks from Capability-Seeking RL Training
从能力寻求强化学习训练中产生的对齐风险
Yujun Zhou, Yue Huang, Han Bao, Kehan Guo, Zhenwen Liang, Pin-Yu Chen, Tian Gao, Werner Geyer, Nuno Moniz, Nitesh V Chawla, Xiangliang Zhang
机构
*
University of California, Berkeley(加州大学伯克利分校)
;
Stanford University(斯坦福大学)
;
University of Washington(华盛顿大学)
;
University of Texas at Austin(德克萨斯大学奥斯汀分校)
;
University of Toronto(多伦多大学)
;
University of Cambridge(剑桥大学)
Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming
机构
*
University of Science and Technology of China(中国科学技术大学)
;
Tsinghua University(清华大学)
;
National University of Singapore(新加坡国立大学)
;
University of California, Berkeley(加州大学伯克利分校)
An interpretable and trustworthy AI framework for large-scale longitudinal structure-pain association studies using data from the Osteoarthritis Initiative (OAI)
一个可解释且可信赖的AI框架,用于利用骨关节炎倡议(OAI)数据进行大规模纵向结构-疼痛关联研究
Jincheng Yu, Haoyang Li, Yiwen Liu, Shen Liu, Rachel Yuanbao Chen, C. Kent Kwoh, Hongxu Ding, Xiaoxiao Sun
机构
*
Statistics & Data Science GIDP, University of Arizona(大学阿瓜斯卡连特斯统计与数据科学GIDP)
;
Department of Epidemiology and Biostatistics, University of Arizona(大学阿瓜斯卡连特斯流行病学与生物统计学系)
;
College of Medicine Tucson, University of Arizona(大学阿瓜斯卡连特斯医学学院)
;
R. Kent Coit College of Pharmacy, University of Arizona(大学阿瓜斯卡连特斯R. Kent Coit药学院)
;
University High School(大学高中)
机构
*
School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院)
;
BrainCog AI Lab, CASIA(CASIA脑认知人工智能实验室)
;
Gaoling School of AI, Renmin University of China(中国人民大学 Gallagher人工智能学院)
;
Beijing-AISI(北京人工智能研究所)
;
Beijing Key Laboratory of Safe AI and Superalignment(北京安全人工智能与超对齐重点实验室)
;
School of Artificial Intelligence, UCAS(中国科学技术大学人工智能学院)
;
Huawei Technologies Co., Ltd.(华为技术有限公司)
CommentsWithdrawn by the authors due to pending intellectual property considerations. The authors have determined that the current version contains material that should not have been publicly disseminated at this stage
$p$-adic Bi-Filtrations for Topological Machine Learning on Genomic Sequences
$p$-adic 双过滤用于基因组序列的拓扑机器学习
Tirtharaj Dash, Gunja Sachdeva
机构
*
Department of CS & IS, BITS Pilani, K K Birla Goa Campus(计算机科学与信息系统系,比斯潘大学,KK Birla Goa校区)
;
Department of Mathematics, BITS Pilani, K K Birla Goa Campus(数学系,比斯潘大学,KK Birla Goa校区)
机构
*
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院)
;
College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)
;
School of Computer Science, Wuhan University(武汉大学计算机学院)
;
School of Computing Technologies, RMIT University(皇家墨尔本理工学院计算技术学院)
A Generative Approach for Semantic Auditing of Electronic Health Records
电子健康记录语义审计的生成式方法
Irena Girshovitz, Atai Ambus, Moni Shahar, Ran Gilad-Bachrach
机构
*
School of Biomedical Engineering, Faculty of Engineering, Tel Aviv University(特拉维夫大学生物医学工程学院,工程学院)
;
AI and Data Science Center of Tel Aviv University (TAD)(特拉维夫大学人工智能与数据科学中心(TAD))
;
Safra Center for Bioinformatics, Tel Aviv University(特拉维夫大学萨弗拉生物信息学中心)