牛哥精选 · 所有

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

📝 深度技术 arXiv 计算机视觉 2026-06-30

3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems

无需训练即可抗噪的3D结构先验，为体素逆问题提供全新几何约束，值得关注。

arXiv:2603.02149v2 Announce Type: replace Abstract: Volume denoising is a foundational problem in computational imaging, as many 3D imaging inverse pr…

3d视觉逆问题结构先验噪声鲁棒免训练

📝 深度技术 arXiv AI 2026-06-23

Strengthening LLMs for Tabular Prediction with Structural Priors

用结构先验强化大模型处理表格数据预测，一项提升LLM表格推理能力的创新方法。

arXiv:2510.17385v5 Announce Type: replace-cross Abstract: Tabular prediction has long been dominated by gradient-boosted decision trees and specialize…

llms 表格预测结构先验结构化数据算法改进

📝 深度技术 arXiv AI 2026-05-20

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

提出归一化等变性的结构先验，可应用于任意骨干网络的图像去噪，有效提升分布偏移健壮性。

arXiv:2605.08193v2 Announce Type: replace-cross Abstract: Normalization Equivariance (NE) is a structural prior that improves robustness to distributi…

归一化等变性图像去噪分布偏移骨干网络结构先验

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems

Strengthening LLMs for Tabular Prediction with Structural Priors

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

📅 日期