针对跨域计数中密度组成变化导致模型退化问题，提出条件特征对齐方法，避免全局域不变性带来的负面影响
arXiv:2506.17137v3 Announce Type: replace Abstract: Object counting models often degrade under cross-domain deployment because density composition var…
提出一种提升输入凸神经网络训练效率的新方法，适用于密度估计与标准化流。
arXiv:2605.24274v1 Announce Type: new Abstract: Input-convex neural networks (ICNNs) are widely used for log-concave density estimation, convex-potent…
提出ConjNorm方法，实现可计算的密度估计，高效解决分布外检测难题
arXiv:2402.17888v5 Announce Type: replace-cross Abstract: Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable ma…
针对RAG系统数据泄露，提出隐私政策执行（PPE）框架，用双密度估计器与嵌入融合检测非规则属性聚类。
arXiv:2605.17034v1 Announce Type: new Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribut…
新方法BMTI通过无箱多维积分实现非参数密度估计，数据高效且鲁棒。
arXiv:2407.08094v3 Announce Type: replace-cross Abstract: We introduce the Binless Multidimensional Thermodynamic Integration (BMTI) method for nonpar…