cs.AI（2024-07-16）
📊 共 5 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1)
支柱一：机器人控制 (Robot Control) (1)
支柱二：RL算法与架构 (RL & Architecture) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models | 提出基于裁剪输入的连续嵌入攻击方法，提升大语言模型越狱成功率。 | large language model | ||
| 2 | Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models | 提出RACE基准，用于多维度评估大型语言模型生成的代码质量 | large language model | ||
| 3 | The Oscars of AI Theater: A Survey on Role-Playing with Language Models | 语言模型角色扮演综述：从Persona到Character驱动的模拟 | large language model | ✅ |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | BadRobot: Jailbreaking Embodied LLMs in the Physical World | BadRobot：针对具身LLM的物理世界越狱攻击 | manipulation embodied AI large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Multi-Step Reasoning with Large Language Models, a Survey | 综述：大型语言模型的多步推理能力研究进展与未来方向 | reinforcement learning large language model chain-of-thought |