cs.AI(2025-09-10)

📊 共 10 篇论文

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (7) 支柱二:RL算法与架构 (RL & Architecture) (2) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗
1 SPADE: A Large Language Model Framework for Soil Moisture Pattern Recognition and Anomaly Detection in Precision Agriculture SPADE:利用大语言模型进行精准农业中的土壤湿度模式识别与异常检测 large language model instruction following
2 PianoVAM: A Multimodal Piano Performance Dataset PianoVAM:一个包含视频、音频、MIDI等多模态钢琴演奏数据集 multimodal
3 GAUSS: Benchmarking Structured Mathematical Skills for Large Language Models GAUSS:构建结构化数学能力基准,评估大语言模型的数学技能 large language model
4 Gala: Global LLM Agents for Text-to-Model Translation Gala:利用全局LLM Agent将自然语言描述转化为优化模型 large language model chain-of-thought
5 Agents of Discovery 利用大型语言模型构建智能体团队,解决粒子物理数据分析中的异常检测问题 large language model
6 Scaling Truth: The Confidence Paradox in AI Fact-Checking 揭示AI事实核查中的置信度悖论:小模型高置信度但低准确率 large language model
7 Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations 构建弹性LLM Agent:安全“计划-执行”模式的实现指南 large language model

🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗
8 Robust Belief-State Policy Learning for Quantum Network Routing Under Decoherence and Time-Varying Conditions 提出基于GNN的鲁棒信念状态策略学习方法,用于解决量子网络路由中的退相干问题。 policy learning
9 Narrative-Guided Reinforcement Learning: A Platform for Studying Language Model Influence on Decision Making 提出一个结合强化学习与语言模型的平台,研究叙事框架对AI决策的影响 reinforcement learning

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
10 HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants 提出HumanAgencyBench,用于评估AI助手中对人类自主性的支持程度。 manipulation RLHF large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页