cs.AI（2024-10-07）

📊 共 20 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) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents	提出UGround，用于GUI智能体的通用视觉定位，提升人机交互能力。	large language model multimodal visual grounding
2	Temporal Relational Reasoning of Large Language Models for Detecting Stock Portfolio Crashes	提出时间关系推理(TRR)框架，利用大语言模型检测股票投资组合崩盘风险。	large language model
3	Synthesizing Interpretable Control Policies through Large Language Model Guided Search	提出基于大语言模型引导搜索的控制策略生成方法，实现可解释的动态系统控制。	large language model	✅
4	ChatVis: Automating Scientific Visualization with a Large Language Model	ChatVis：利用大语言模型自动生成科学可视化脚本	large language model	✅
5	Leverage Knowledge Graph and Large Language Model for Law Article Recommendation: A Case Study of Chinese Criminal Law	提出融合知识图谱与大语言模型的法律条文推荐方法，提升法院效率。	large language model
6	Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Models	提出智能计算社会建模(ICSM)方法，利用大语言模型探索政治科学中的方法创新	large language model
7	Can LLMs plan paths with extra hints from solvers?	利用求解器提示增强LLM在机器人路径规划中的能力	large language model
8	ImProver: Agent-Based Automated Proof Optimization	ImProver：基于Agent的自动化定理证明优化方法，提升证明质量。	large language model
9	Intuitions of Compromise: Utilitarianism vs. Contractualism	对比功利主义与契约主义，揭示社会决策中人类偏好与大语言模型的错位	large language model
10	Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents	提出GraphAgent-Reasoner，利用多智能体协作实现可扩展且精确的图推理。	large language model
11	The Role of Governments in Increasing Interconnected Post-Deployment Monitoring of AI	提出政府主导的AI后部署互联监控框架，提升AI风险管理能力	chain-of-thought
12	SoK: Towards Security and Safety of Edge AI	Edge AI安全与安全综述：识别威胁、总结对策并呼吁更多研究	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	🔗	⭐
13	SPikE-SSM: A Sparse, Precise, and Efficient Spiking State Space Model for Long Sequences Learning	提出SPikE-SSM：一种稀疏、精确、高效的脉冲状态空间模型，用于长序列学习。	SSM state space model
14	Training Interactive Agent in Large FPS Game Map with Rule-enhanced Reinforcement Learning	提出基于规则增强强化学习的PMCA智能体，用于大型FPS游戏地图中的交互	reinforcement learning deep reinforcement learning DRL
15	Masked Autoencoder with Swin Transformer Network for Mitigating Electrode Shift in HD-EMG-based Gesture Recognition	提出基于Swin Transformer的掩码自编码器（MAST）框架，以缓解HD-EMG手势识别中的电极漂移问题。	masked autoencoder
16	AlphaRouter: Quantum Circuit Routing with Reinforcement Learning and Tree Search	AlphaRouter：提出基于强化学习和树搜索的量子电路路由方法	reinforcement learning
17	Towards using Reinforcement Learning for Scaling and Data Replication in Cloud Systems	探索强化学习在云系统中数据复制与伸缩的应用	reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
18	AI-Enhanced Ethical Hacking: A Linux-Focused Experiment	利用AI增强的伦理黑客技术：一项基于Linux的实验研究	penetration

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Investigating Role of Big Five Personality Traits in Audio-Visual Rapport Estimation	利用大五人格特质提升音视频人际融洽度估计性能	dyadic interaction

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	Image Watermarks are Removable Using Controllable Regeneration from Clean Noise	提出可控再生方法，有效去除图像水印并保持图像质量与一致性	manipulation	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页