cs.AI（2025-08-12）

📊 共 38 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring 提出DUAL-Health以解决动态环境下健康监测中的不确定性问题 large language model multimodal
2 Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation 提出E-Agent以优化多模态检索增强生成的规划能力 large language model multimodal
3 Multimodal Appearance based Gaze-Controlled Virtual Keyboard with Synchronous Asynchronous Interaction for Low-Resource Settings 提出多模态外观基础的注视控制虚拟键盘以解决低资源环境下的沟通问题 multimodal
4 Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning 研究大型语言模型与人类抽象推理的神经认知对齐 large language model
5 EditMF: Drawing an Invisible Fingerprint for Your Large Language Models 提出EditMF以解决大语言模型的隐私保护问题 large language model
6 Prompt-and-Check: Using Large Language Models to Evaluate Communication Protocol Compliance in Simulation-Based Training 提出Prompt-and-Check以评估模拟训练中的沟通协议合规性 large language model
7 AgriGPT: a Large Language Model Ecosystem for Agriculture 提出AgriGPT以解决农业领域大语言模型应用不足问题 large language model
8 OpenCUA: Open Foundations for Computer-Use Agents 提出OpenCUA框架以推动计算机使用代理的研究与应用 foundation model chain-of-thought
9 Silicon Minds versus Human Hearts: The Wisdom of Crowds Beats the Wisdom of AI in Emotion Recognition 研究表明众智在情感识别中优于人工智能 large language model multimodal
10 SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling 提出SMA以解决RAG系统中的成员泄露审计问题 large language model multimodal
11 Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMs 提出上下文完整性验证以解决大语言模型安全问题 large language model
12 BrowseMaster: Towards Scalable Web Browsing via Tool-Augmented Programmatic Agent Pair 提出BrowseMaster以解决大规模网络浏览中的信息检索与推理平衡问题 large language model
13 Can We Trust AI to Govern AI? Benchmarking LLM Performance on Privacy and AI Governance Exams 评估大型语言模型在隐私与AI治理中的表现 large language model
14 Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs 提出激活引导技术以缓解大型语言模型中的偏见问题 large language model
15 Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory 提出内在记忆代理以解决多智能体系统的记忆一致性问题 large language model
16 NEFMind: Parameter-Efficient Fine-Tuning of Open-Source LLMs for Telecom APIs Automation 提出NEFMind以解决电信API自动化中的复杂性问题 large language model
17 Prospect Theory Fails for LLMs: Revealing Instability of Decision-Making under Epistemic Uncertainty 提出新的评估框架以揭示LLMs在不确定性下的决策不稳定性 large language model ✅
18 Livia: An Emotion-Aware AR Companion Powered by Modular AI Agents and Progressive Memory Compression 提出Livia以解决孤独与社交隔离问题 multimodal
19 Safe Semantics, Unsafe Interpretations: Tackling Implicit Reasoning Safety in Large Vision-Language Models 提出隐式推理安全性以解决大型视觉语言模型的安全问题 multimodal
20 A Dual-Axis Taxonomy of Knowledge Editing for LLMs: From Mechanisms to Functions 提出双轴分类法以优化大语言模型的知识编辑 large language model
21 Simulating Generative Social Agents via Theory-Informed Workflow Design 提出基于理论的框架以设计生成社交代理 large language model
22 A Survey of Optimization Modeling Meets LLMs: Progress and Future Directions 通过大语言模型自动化优化建模以解决决策问题 large language model
23 Securing Educational LLMs: A Generalised Taxonomy of Attacks on LLMs and DREAD Risk Assessment 提出教育领域LLM安全攻击分类与DREAD风险评估方法 large language model
24 QoE-Aware Service Provision for Mobile AR Rendering: An Agent-Driven Approach 提出基于代理的通信服务以提升移动增强现实的用户体验 large language model
25 OmniLLP: Enhancing LLM-based Log Level Prediction with Context-Aware Retrieval 提出OmniLLP以提升基于LLM的日志级别预测准确性 large language model
26 Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System 提出MAESTRO框架以解决网络监控中的Agentic AI安全问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
27 Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning 提出DQInit以解决深度强化学习中的价值函数初始化问题 reinforcement learning deep reinforcement learning DRL
28 Aryabhata: An exam-focused language model for JEE Math 提出Aryabhata以优化印度JEE数学考试的语言模型 reinforcement learning curriculum learning large language model ✅
29 Deep Reinforcement Learning for Optimal Asset Allocation Using DDPG with TiDE 提出基于DDPG与TiDE的深度强化学习方法以优化资产配置 reinforcement learning deep reinforcement learning
30 STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision 提出STELAR-VISION以解决多模态推理中的拓扑依赖问题 reinforcement learning multimodal chain-of-thought
31 Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning 提出MSARL框架以降低工具使用中的认知负担 reinforcement learning imitation learning
32 Attacks and Defenses Against LLM Fingerprinting 提出基于强化学习的LLM指纹攻击与防御方法 reinforcement learning large language model
33 E3-Rewrite: Learning to Rewrite SQL for Executability, Equivalence,and Efficiency 提出E3-Rewrite以解决SQL重写的执行性、等价性和效率问题 reinforcement learning large language model
34 Compass-Thinker-7B Technical Report 提出Compass-Thinker-7B以降低大规模模型的RL实验成本 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
35 Large Language Models for Power System Security: A Novel Multi-Modal Approach for Anomaly Detection in Energy Management Systems 提出多模态方法以解决能源管理系统中的异常检测问题 manipulation large language model multimodal
36 Special-Character Adversarial Attacks on Open-Source Language Model 研究特殊字符对开源语言模型的对抗攻击以提升安全性 manipulation large language model
37 Collective dynamics of strategic classification 基于进化博弈理论提出用户适应与算法重训练的动态模型 manipulation

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

#题目一句话要点标签🔗⭐
38 Designing Memory-Augmented AR Agents for Spatiotemporal Reasoning in Personalized Task Assistance 提出记忆增强的AR代理以解决个性化任务辅助中的时空推理问题 spatiotemporal large language model foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页