cs.AI（2025-03-12）

📊 共 15 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) (11) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models 综述长链思考（Long CoT）在推理大语言模型中的应用，并提出未来研究方向。 large language model chain-of-thought
2 LLM-Guided Indoor Navigation with Multimodal Map Understanding 利用LLM和多模态地图理解实现室内导航 large language model multimodal
3 Enhancing High-Quality Code Generation in Large Language Models with Comparative Prefix-Tuning 提出比较前缀调优方法，提升大语言模型生成代码的质量，同时保持功能正确性。 large language model
4 Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks 提出JCB：一种高效的黑盒LLM越狱方法，利用跨行为攻击提升攻击效率。 large language model zero-shot transfer
5 Media and responsible AI governance: a game-theoretic and LLM analysis 利用博弈论和LLM分析媒体在负责任AI治理中的作用 large language model
6 CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection CASTLE：用于CWE检测的静态代码分析器和LLM基准测试数据集 large language model
7 CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning CyberLLMInstruct：揭示网络安全LLM微调中安全与性能的权衡 large language model
8 A Global Dataset Mapping the AI Innovation from Academic Research to Industrial Patents 构建DeepInnovationAI数据集，用于分析AI学术研究到工业专利的创新转移模式 large language model
9 In-Context Defense in Computer Agents: An Empirical Study 提出上下文防御方法，提升计算机Agent抵抗环境欺骗攻击的能力 chain-of-thought
10 KNighter: Transforming Static Analysis with LLM-Synthesized Checkers KNighter：利用LLM合成静态分析器，革新静态分析技术 large language model
11 Leveraging Knowledge Graphs and LLMs for Context-Aware Messaging 利用知识图谱和LLM实现上下文感知的个性化消息传递 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
12 LREF: A Novel LLM-based Relevance Framework for E-commerce 提出LREF框架以提升电商搜索相关性问题 DPO direct preference optimization large language model
13 ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning 提出ReMA：利用多智能体强化学习提升LLM的元认知能力 reinforcement learning large language model ✅
14 RESTRAIN: Reinforcement Learning-Based Secure Framework for Trigger-Action IoT Environment 提出RESTRAIN，基于强化学习的物联网触发-动作环境安全框架，防御远程注入攻击。 reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 Online Language Splatting 提出Online Language Splatting，实现3DGS-SLAM系统中近实时开放词汇语言映射。 3D gaussian splatting 3DGS gaussian splatting

⬅️ 返回 cs.AI 首页 · 🏠 返回主页