cs.AI（2025-08-20）

📊 共 21 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) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 Automated Optimization Modeling through Expert-Guided Large Language Model Reasoning 提出ORThought框架以自动化优化建模过程 large language model chain-of-thought
2 Building and Measuring Trust between Large Language Models 提出信任构建与测量方法以解决LLMs间信任关系问题 large language model
3 PerFairX: Is There a Balance Between Fairness and Personality in Large Language Model Recommendations? 提出PerFairX以解决大语言模型推荐中的公平性与个性化问题 large language model
4 NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding 提出NoteIt系统以解决教学视频笔记生成不足的问题 multimodal ✅
5 MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs 提出MoEcho以解决Mixture-of-Experts模型中的用户隐私问题 large language model multimodal
6 Open-Universe Assistance Games 提出开放宇宙辅助游戏框架以解决人类目标推断问题 embodied AI
7 Emergent Crowds Dynamics from Language-Driven Multi-Agent Interactions 提出语言驱动的多智能体交互方法以解决人群动态模拟问题 large language model
8 ECHO: Frequency-aware Hierarchical Encoding for Variable-length Signals 提出ECHO模型以解决变长信号建模问题 foundation model ✅
9 aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists 提出aiXiv以解决AI生成研究内容发布难题 large language model
10 S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner 提出S3LoRA以解决LLM适应过程中的安全性问题 large language model
11 Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design 将知识学习框架嵌入多智能体系统以提升教育内容设计质量 large language model
12 Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs 提出结构化思维-行动序列以提升LLM的视角理解能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers 提出MCP-Universe以解决现有LLM基准评估不足问题 world model large language model
14 Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions 提出Mamba2模型以解决稀疏区域的声源分离问题 Mamba state space model
15 Enhanced Predictive Modeling for Hazardous Near-Earth Object Detection: A Comparative Analysis of Advanced Resampling Strategies and Machine Learning Algorithms in Planetary Risk Assessment 提出增强预测建模方法以提高近地危险小行星检测精度 predictive model
16 Goals and the Structure of Experience 提出目标导向状态表征以解决智能体行为建模问题 reinforcement learning world model

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

#题目一句话要点标签🔗⭐
17 From Basic Affordances to Symbolic Thought: A Computational Phylogenesis of Biological Intelligence 提出动态绑定与层次整合以实现符号思维 affordance

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Learning in Repeated Multi-Objective Stackelberg Games with Payoff Manipulation 提出基于期望效用的操控策略以解决多目标Stackelberg博弈中的收益操控问题 manipulation

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

#题目一句话要点标签🔗⭐
19 LeanGeo: Formalizing Competitional Geometry problems in Lean 提出LeanGeo以解决几何问题形式化与验证挑战 IMoS large language model ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
20 The Agent Behavior: Model, Governance and Challenges in the AI Digital Age 提出网络行为生命周期模型以解决AI代理行为治理问题 penetration

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
21 A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References 提出SI-SDR以解决带噪语音分离中的评估问题 WHAM

⬅️ 返回 cs.AI 首页 · 🏠 返回主页