📄 arXiv 论文速递

💡 量子图上的非局部微分方程数值求解是数学物理中的难点，该框架将物理信息神经网络扩展至此，为复杂网络结构上的科学计算提供了新工具，具有重要理论价值。

We propose QGPINNs, a physics-informed neural network framework developed in PyTorch for the numerical solution of nonlocal differential equations on quantum graphs. The framework …

Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce that saving. Routi…

💡 合成数据增强在真实数据稀缺时很关键，但直接混用会产生偏差。该研究提出大小-权重前沿方法，平衡偏差与方差，提升统计推断可靠性，对数据稀缺领域影响深远。

Synthetic data can improve statistical inference when real data are scarce, but naively treating synthetic samples as real data can introduce bias and lead to unreliable inference.…

We study the mixing time of weighted Dikin walks for sampling from exponential distributions on polytopes and truncated positive-semidefinite (PSD) cones. Our first result gives a …

💡 该论文揭示了各向异性高斯数据下核岭回归的精确渐近行为，为高维非均匀数据建模提供了理论指导，有助于理解核方法的极限性能并优化设计。

We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent $α\geq 0$ for polynomial inner-product kernels. We …

Neural-network optimization in 2025-2026 is no longer well described as a succession of new Adam variants. The design space has expanded from coordinates to matrices and layers, fr…

Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spatiotemporal-composability calculus,…

As a precursor to high-dimensional biomedical data modeling, reliable feature selection can reduce computational expense, improve modeling performance, and yield simpler, more inte…

💡 将视频生成模型用于几何估计是新兴方向，该工作利用生成先验解决传统方法在复杂场景中的几何推断难题，为3D视觉与生成模型的交叉应用开辟了新路径。

Recent generative approaches to geometry estimation adapt pretrained image diffusion models and treat the task as image-conditioned generation. Leveraging off-the-shelf image diffu…

💡 模型合并是低成本构建多任务模型的关键技术，但合并后性能常退化。该研究提出解码器感知的表示调优方法，显著提升合并质量，对LLM高效部署有重要实践意义。

Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are known to suffer from representa…

A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wrong beyond it. We characterize what a certified model can know,…

Recent advances in generative AI allow users to create 3D models from text or images. However, these models prioritize visual plausibility over geometric accuracy, often generating…