cs.AI（2026-09-10）

📊 共 29 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) (17) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (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) (17 篇)

#题目一句话要点标签🔗⭐
1 ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI 提出ORCH以优化多智能体系统的组织与协调 embodied AI large language model
2 SIRF: A Spec-Internalized Risk Foundation Model for Industrial Content Risk Control 提出SIRF模型以解决工业内容风险控制问题 foundation model chain-of-thought
3 Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents 提出Mr.LHDR基准以评估长时段多模态深度研究代理的能力 multimodal
4 When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting 提出信息论指标基准以评估文本在多模态时间序列预测中的贡献 multimodal
5 Sci-MMR: Benchmarking Multi-Step Evidence-Grounded Scientific Reasoning in Multimodal Agents 提出Sci-MMR以解决多步骤证据基础科学推理问题 multimodal
6 Evaluating Scaffolding-Oriented Multi-Agent Large Language Model System for Clinical Interview Training 提出多代理大语言模型系统以提升临床访谈训练效果 large language model
7 A Mathematical Theory of Pragmatic Information 提出实用信息理论以统一通信、控制与决策问题 embodied AI
8 Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models 提出对话式XAI助手以解决能源消费模型解释问题 large language model
9 COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization 提出COBRA-Skills以解决技能优化中的高成本问题 large language model
10 Characterizing Job Power Elasticity for Power-Flexible AI Training 提出作业功率弹性指标以优化AI训练的电力使用 large language model
11 ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps 提出ActMap以解决大语言模型的不确定性量化问题 large language model
12 Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning 提出稳定性意识的测试时适应方法以提升LLM推理能力 large language model
13 AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data Analysis 提出AI足球分析师以解决数据分析中的人机协作问题 large language model
14 (Whose defaults?) Is artificial intelligence reorienting archaeological methods? 评估大型语言模型对考古方法多样性的影响 large language model
15 SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics 提出SemVerBench以评估LLM对版本约束解析语义的理解 large language model
16 Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation 提出Benchmark Radar以解决AI基准评估检索问题 large language model
17 Demystifying the Privacy-Utility Trade-off in LLM Interactions 提出意图驱动的本地保护框架以优化隐私与效用的权衡 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
18 RAMamba-Net: A Reliability-Aware and Mamba-Based Multimodal Fusion Network for Auditory Attention Detection 提出RAMamba-Net以解决听觉注意力检测中的多模态融合问题 Mamba multimodal
19 MindTopo: Can Foundation Models Reason in Topological Space? 提出MindTopo基准以评估基础模型在拓扑空间中的推理能力 reinforcement learning foundation model
20 Exploring Diffusion Transformers for Cross-Modal Augmentation in Multimodal Brain State Decoding 提出CoMA-DiT以解决多模态脑状态解码中的数据增强问题 representation learning multimodal
21 RetroThinker: Enabling Retrospective Thinking in Speech LLMs 提出RetroThinker以解决语音LLM推理延迟问题 DPO direct preference optimization large language model
22 X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation 提出X-AuT框架以优化语音大语言模型的音频编码器压缩 distillation large language model ✅
23 Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models 提出基于模型的强化学习优化模块化生产系统 reinforcement learning
24 DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat 提出DRG-MAPPO以解决空战中的复杂战术协调问题 reinforcement learning
25 Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning 提出信念转变分支以优化树结构强化学习中的决策过程 reinforcement learning
26 KuaiRP Series Role-playing Models Technical Report 提出KuaiRP系列角色扮演模型以解决知识注入与能力保持的矛盾 reinforcement learning distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
27 DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks 提出DeFiFusion以解决去中心化金融中的价格操纵攻击检测问题 manipulation

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

#题目一句话要点标签🔗⭐
28 Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification 提出Magenta以解决数学推理与形式验证之间的鸿沟问题 IMoS large language model

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

#题目一句话要点标签🔗⭐
29 Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless 提出轻量级LiDAR锥体检测框架以解决FSD车辆感知问题 IMU-based motion

⬅️ 返回 cs.AI 首页 · 🏠 返回主页