cs.AI（2024-06-28）

📊 共 17 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 When Search Engine Services meet Large Language Models: Visions and Challenges 探索LLM与搜索引擎结合：提升信息检索与内容理解的新范式 large language model
2 Efficacy of Various Large Language Models in Generating Smart Contracts 评估大型语言模型在生成安全高效Solidity智能合约中的有效性，并探索新型prompt策略。 large language model
3 Fine-tuning of Geospatial Foundation Models for Aboveground Biomass Estimation 微调地理空间基础模型用于地上生物量估计，在节约计算资源的同时达到与U-Net相当的性能。 foundation model
4 Uncertainty Quantification in Large Language Models Through Convex Hull Analysis 提出基于凸包分析的大语言模型不确定性量化方法，提升高风险应用可靠性。 large language model
5 Leveraging Large Language Models for enhanced personalised user experience in Smart Homes 利用大语言模型提升智能家居的个性化用户体验 large language model
6 Multimodal Learning and Cognitive Processes in Radiology: MedGaze for Chest X-ray Scanpath Prediction MedGaze：提出一种多模态学习方法，用于预测胸部X光片扫描路径，提升放射诊断AI系统。 multimodal
7 Multimodal Data Integration for Precision Oncology: Challenges and Future Directions 综述多模态数据融合在精准肿瘤学中的应用，分析挑战并展望未来方向 multimodal
8 MetaDesigner: Advancing Artistic Typography Through AI-Driven, User-Centric, and Multilingual WordArt Synthesis MetaDesigner：通过AI驱动、用户中心和多语言WordArt合成推进艺术排版 large language model multimodal
9 One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts 提出混合专家提示（MoP）方法，通过自动化构建专家提示组合来提升LLM在复杂任务上的性能。 large language model
10 BMW Agents -- A Framework For Task Automation Through Multi-Agent Collaboration BMW Agents：多智能体协作框架，用于任务自动化 large language model
11 ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents 提出ShortcutsBench以评估API代理在复杂任务中的表现 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
12 Tradeoffs When Considering Deep Reinforcement Learning for Contingency Management in Advanced Air Mobility 针对先进空中交通的应急管理，探索深度强化学习的权衡方案 reinforcement learning deep reinforcement learning DRL
13 Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs 提出LLM4PG框架，利用大语言模型提升强化学习在复杂约束游戏任务中的轨迹评估与策略优化。 reinforcement learning large language model
14 External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling 提出基于外部模型的强化学习智能体，提升环境采样效率 reinforcement learning
15 Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning 提出基于强化学习的动态Active Directory网络防御优化方法 reinforcement learning
16 Fuzzy Logic Guided Reward Function Variation: An Oracle for Testing Reinforcement Learning Programs 提出基于模糊逻辑的奖励函数变异方法，解决强化学习程序测试中的Oracle问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Function+Data Flow: A Framework to Specify Machine Learning Pipelines for Digital Twinning 提出Function+Data Flow领域特定语言，简化数字孪生AI流水线设计。 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页