牛哥精选 · 三个月

📋 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

🤖 AI·大模型 arXiv 机器学习 2026-05-29

Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance

提出Stable-GFlowNet，用对比轨迹平衡生成多样对抗样本，提升LLM红队测试的鲁棒性

arXiv:2605.00553v2 Announce Type: replace Abstract: Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is a…

llm红队 gflownet 对比轨迹平衡对抗样本 ai安全

📝 深度技术 arXiv AI 2026-05-19

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

提出f-轨迹平衡损失族，统一了GFlowNets和LLM的on/off-policy训练，梯度对应KL散度，低方差高效。

arXiv:2605.15417v1 Announce Type: cross Abstract: In GFlowNets and variational inference, it has been shown that the mean square error between target …

gflownets 生成模型大语言模型损失函数轨迹平衡

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance

$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data

📅 日期