arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

Journal of Machine Learning Research · 期刊 · Machine Learning

2025-12-30 至 2025-12-30 共收录 2
2412.18387 2025-12-30 cs.AI cs.LG

Scaling Capability in Token Space: An Analysis of Large Vision Language Model

令牌空间中的扩展能力:对大视觉语言模型的分析

Tenghui Li, Guoxu Zhou, Xuyang Zhao, Qibin Zhao

机构 * School of Automation, Guangdong University of Technology(广东工业大学自动化学院) Key Laboratory of Intelligent Detection and the Internet of Things in Manufacturing, Ministry of Education(教育部智能制造智能检测与物联网重点实验室) Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration(广东省智能系统与优化集成重点实验室) Medical Science Data-driven Mathematics Team, RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences(RIKEN跨学科理论与数学科学中心医学科学数据驱动数学团队) Medical Data Mathematical Reasoning Special Team, RIKEN Center for Integrative Medical Sciences(RIKEN整合医学科学中心医学数据数学推理特别团队) Department of Artificial Intelligence Medicine, Chiba University(千叶大学人工智能医学系) Tensor Learning Team, RIKEN Center for Advanced Intelligence Project(RIKEN高级人工智能项目中心张量学习团队)

AI总结 本研究通过理论分析和实证验证,揭示了视觉语言模型在视觉令牌数量上的扩展规律,发现不同数量的视觉令牌对应不同的扩展模式,并提出了扩展指数与视觉令牌表示相关结构的关系。

Journal ref Journal of Machine Learning Research, volume 26, number 253, page 1--61, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.09064 2025-12-30 stat.ML cs.CR cs.LG

Minimax Optimal Two-Sample Testing under Local Differential Privacy

在局部差分隐私下两样本检验的最优化

Jongmin Mun, Seungwoo Kwak, Ilmun Kim

AI总结 本文在局部差分隐私下提出两样本检验方法,通过隐私排列检验和自适应检验实现最小分离率,平衡隐私与统计效用。

Comments 66 pages, 6 figures, 1 table; added a graphical illustration of central and local differential privacy in Section 1, referenced the Python package, fixed typos, and changed the citation style

Journal ref Journal of Machine Learning Research 26(252):1-79, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏