cs.AI（2024-09-12）

📊 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks 提出WirelessAgent，利用大语言模型解决复杂无线网络管理问题。 large language model multimodal
2 OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering OmniQuery：通过上下文增强多模态记忆，实现个性化问答 large language model multimodal
3 Early Joint Learning of Emotion Information Makes MultiModal Model Understand You Better 提出基于早期联合学习的多模态情感识别模型，提升噪声和数据不足场景性能 large language model multimodal
4 LLM Honeypot: Leveraging Large Language Models as Advanced Interactive Honeypot Systems 利用大型语言模型构建高级交互式蜜罐系统，提升网络安全防御能力 large language model
5 The Impact of Large Language Models on Open-source Innovation: Evidence from GitHub Copilot 研究GitHub Copilot对开源创新影响：加速迭代创新，但能力创新提升相对较小 large language model
6 DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? DSBench：构建更贴近现实的数据科学基准，评估数据科学智能体的能力。 large language model multimodal
7 Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale 提出Windows Agent Arena，用于大规模评估多模态操作系统Agent large language model ✅
8 ScriptSmith: A Unified LLM Framework for Enhancing IT Operations via Automated Bash Script Generation, Assessment, and Refinement ScriptSmith：统一的LLM框架，通过自动化Bash脚本生成、评估和优化增强IT运维。 large language model
9 TravelAgent: An AI Assistant for Personalized Travel Planning TravelAgent：一个用于个性化旅行规划的AI助手，解决动态场景下的理性、全面和个性化难题。 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🔗⭐
10 A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning 提出时空隐蔽后门攻击，提升合作多智能体深度强化学习的安全性 reinforcement learning deep reinforcement learning spatiotemporal
11 Towards Opinion Shaping: A Deep Reinforcement Learning Approach in Bot-User Interactions 提出基于深度强化学习的社交网络舆论引导方法，通过用户-机器人交互影响舆论。 reinforcement learning deep reinforcement learning DRL
12 Design Optimization of Nuclear Fusion Reactor through Deep Reinforcement Learning 提出基于深度强化学习的核聚变反应堆设计优化方法，降低建造成本。 reinforcement learning deep reinforcement learning DRL
13 Tidal MerzA: Combining affective modelling and autonomous code generation through Reinforcement Learning Tidal-MerzA：结合情感建模与自主代码生成的强化学习音乐共创系统 reinforcement learning
14 Fitted Q-Iteration via Max-Plus-Linear Approximation 提出基于Max-Plus线性近似的Fitted Q-Iteration算法，用于离线强化学习。 reinforcement learning offline reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
15 Autonomous Vehicle Controllers From End-to-End Differentiable Simulation 提出基于可微仿真和解析策略梯度的自动驾驶车辆控制器训练方法 differentiable simulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页