cs.AI（2024-12-17）
📊 共 5 篇论文 | 🔗 3 篇有代码
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | SafeDrive: Knowledge- and Data-Driven Risk-Sensitive Decision-Making for Autonomous Vehicles with Large Language Models | SafeDrive：提出基于知识和数据驱动的风险敏感决策框架，提升自动驾驶在高风险场景下的安全性。 | large language model | ✅ | |
| 2 | SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents | SafeAgentBench：用于具身LLM智能体安全任务规划的基准测试 | large language model | ✅ | |
| 3 | Fooling LLM graders into giving better grades through neural activity guided adversarial prompting | 提出神经活动引导的对抗性提示方法，欺骗LLM评分器以获得更高分数 | large language model | ||
| 4 | Are Your LLMs Capable of Stable Reasoning? | 提出G-Pass@$k$以解决大语言模型推理稳定性问题 | large language model | ||
| 5 | A Survey of Calibration Process for Black-Box LLMs | 对黑盒大语言模型校准过程的综述研究，填补了系统性方法论的空白。 | large language model | ✅ |