牛哥精选 · 所有

📋 全部 ☁️ 云服务 🤖 AI 平台 🔗 API 中转 🔐 安全/认证 💳 支付 📧 通讯 📊 数据分析 🖼 媒体处理 🌐 域名/DNS

📝 深度技术 arXiv AI 2026-08-15

What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting

用消融实验揭开LLM自我反思的机制，看不确定性路由如何影响冲突预测准确率。

arXiv:2608.12322v1 Announce Type: cross Abstract: Self-reflection is widely assumed to improve LLM reasoning, yet which component drives the gain rema…

llm 自我反思不确定性路由武装冲突预测消融研究

📝 深度技术 arXiv AI 2026-07-21

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

提出 Mediator 框架，通过减少参数冲突和不确定性路由，实现内存高效的 LLM 合并。

arXiv:2502.04411v3 Announce Type: replace-cross Abstract: Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a st…

llm合并参数冲突不确定性路由内存效率模型压缩

🔓 开源项目 Hacker News LLM 2026-07-21

Deterministic LLM router with a cryptographic audit trail – TEIA

确定性LLM路由+加密审计，确保可追溯且防篡改的决策记录

Article URL: https://github.com/felippebarcelos/teia-omega-awakening Comments URL: https://news.ycombinator.com/item?id=48978938 Points: 2 # Comments:…

llm路由加密审计语义熵确定性路由 apache2.0

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting

Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing

Deterministic LLM router with a cryptographic audit trail – TEIA

📅 日期