arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

NeurIPS

Conference on Neural Information Processing Systems · 会议 · Machine Learning

2026-06-16 至 2026-06-16 共收录 3
2606.15899 2026-06-16 cs.CR cs.AI cs.HC cs.LG cs.MA 新提交

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

SkillVetBench: 基于LLM评判的多维安全风险评估开源LLM智能体技能

Ismail Hossain, Sai Puppala, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder

机构 * SUPREME Lab, University of Texas at El Paso, Texas, USA(SUPREME实验室,德克萨斯理工大学埃尔帕索分校,德克萨斯州,美国)

AI总结 提出SkillVetBench,利用LLM作为评判器对开源LLM智能体技能进行多维安全风险评估,引入五维技能智能体风险评分(SARS)和CVSS v4.0向量分解,在78个恶意技能上实现零假阴性,22个良性技能上零假阳性。

Comments The main research paper is submitted to NeurIPS 2027, it is in under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.24987 2026-06-16 q-bio.QM cs.LG q-bio.GN

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

scMRDR:一种可扩展且灵活的无配对单细胞多组学数据整合框架

Jianle Sun, Chaoqi Liang, Ran Wei, Peng Zheng, Lei Bai, Wanli Ouyang, Hongliang Yan, Peng Ye

机构 * Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) Carnegie Mellon University(卡内基梅隆大学) The Chinese University of Hong Kong(香港中文大学) Guangzhou Laboratory(广州实验室)

AI总结 scMRDR通过β-VAE架构解耦细胞潜在表示,结合等距正则化、对抗目标和掩码重建损失,实现无配对多组学数据整合,有效提升大规模数据处理能力。

Comments Accepted at NeurIPS 2025 (Spotlight)

Journal ref Advances in Neural Information Processing Systems 38 (2025): 154538-154565

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.07277 2026-06-16 cs.CL cs.AI cs.MA

Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication

说出你的语言:可解释的涌现交流中的空间关系

Olaf Lipinski, Adam J. Sobey, Federico Cerutti, Timothy J. Norman

机构 * University of Southampton(索姆塞特大学) The Alan Turing Institute(艾伦·图灵研究所) University of Brescia(布雷西亚大学)

AI总结 本文研究了智能体如何通过空间关系交流,展示了其能发展出表达观察部分关系的语言,实现90%以上的准确率,并证明该语言可被人类解读。

Comments Accepted at NeurIPS 2024. 18 pages, 3 figures

Journal ref In Advances in Neural Information Processing Systems (Vol. 37, pp. 140113-140137) 2024

详情

展开后加载摘要…

URL PDF HTML 收藏