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 AI 2026-06-17

SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation

提出SkillMoV混合视图路由架构，用原型条件门控统一多视角能力估计，创新融合视图选择与专家路由

arXiv:2606.17615v1 Announce Type: cross Abstract: Estimating human proficiency from video is a key challenge for automated skill assessment, with appl…

skillmov mixture-of 原型门控多视图技能评估混合专家模型

🤖 AI·大模型 arXiv AI 2026-06-05

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

跨层共享路由实现稀疏注意力，一次索引大幅降低计算开销，为长序列模型提供高效新范式。

arXiv:2606.06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially…

稀疏注意力跨层共享路由机制注意力优化效率提升

📝 深度技术 arXiv AI 2026-05-23

Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs

新型图增强LLM框架Ex-GraphRAG，通过可解释证据路由解决GNN编码器节点贡献纠缠问题。

arXiv:2605.21994v1 Announce Type: cross Abstract: GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via messag…

graphrag 可解释性图增强大模型证据路由 gnn

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs

📅 日期