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 机器学习 2026-06-18

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

用LLM智能体自动挖掘强化学习后训练的最优策略，无需人工调参。

arXiv:2606.18388v1 Announce Type: new Abstract: RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity p…

llmzero 强化学习自适应训练策略 llm代理后训练

📝 深度技术 arXiv AI 2026-05-29

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

逐层表示分析新方法，精准识别RL后训练阶段的数据污染，提升模型安全与可靠性。

arXiv:2605.29888v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (L…

lara 逐层表示分析数据污染检测 rl后训练语言模型安全

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

LLMZero: Discovering Adaptive Training Strategies for RL Post-Training via LLM Agents

LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training

📅 日期