cs.AI（2025-01-13）

📊 共 15 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) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Bridging Smart Meter Gaps: A Benchmark of Statistical, Machine Learning and Time Series Foundation Models for Data Imputation 评估统计、机器学习和时间序列大模型在智能电表数据缺失值填充中的性能 large language model foundation model
2 Lifelong Learning of Large Language Model based Agents: A Roadmap 提出终身学习框架以增强大语言模型代理的适应能力 large language model multimodal ✅
3 Large Language Models for Interpretable Mental Health Diagnosis 提出结合LLM与约束逻辑编程的心理健康诊断决策支持系统 large language model
4 PowerGraph-LLM: Novel Power Grid Graph Embedding and Optimization with Large Language Models 提出PowerGraph-LLM框架，利用大语言模型解决电力系统最优潮流问题。 large language model
5 A Proposed Large Language Model-Based Smart Search for Archive System 提出基于大语言模型的智能搜索框架，提升数字档案馆信息检索精度与相关性 large language model
6 Unveiling the Potential of Text in High-Dimensional Time Series Forecasting 提出融合文本信息的高维时间序列预测框架，提升预测精度。 large language model multimodal
7 Understanding and Benchmarking Artificial Intelligence: OpenAI's o3 Is Not AGI 批判性分析OpenAI o3：并非通用人工智能，并提出更全面的智能评估基准 large language model
8 Value Compass Benchmarks: A Platform for Fundamental and Validated Evaluation of LLMs Values Value Compass Benchmarks：构建全面、有效、多元的大语言模型价值观评估平台 large language model
9 PoAct: Policy and Action Dual-Control Agent for Generalized Applications 提出PoAct：一种策略与行动双重控制的Agent框架，用于通用任务 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🔗⭐
10 From Screens to Scenes: A Survey of Embodied AI in Healthcare 综述具身智能在医疗健康领域的应用，分析挑战并展望未来 world model embodied AI large language model
11 Online inductive learning from answer sets for efficient reinforcement learning exploration 提出基于应答集归纳学习的在线强化学习探索方法，提升训练效率和可解释性 reinforcement learning reward shaping
12 How GPT learns layer by layer 通过分析OthelloGPT，揭示GPT模型逐层学习棋盘状态和游戏策略的机制 world model representation learning large language model ✅
13 CureGraph: Contrastive Multi-Modal Graph Representation Learning for Urban Living Circle Health Profiling and Prediction CureGraph：用于城市生活圈健康画像与预测的对比多模态图表示学习 representation learning ✅
14 Graph Contrastive Learning on Multi-label Classification for Recommendations 提出MCGCL模型，利用图对比学习增强多标签推荐系统的性能。 contrastive learning

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

#题目一句话要点标签🔗⭐
15 Initial Findings on Sensor based Open Vocabulary Activity Recognition via Text Embedding Inversion 提出基于文本嵌入反演的开放词汇活动识别框架OV-HAR，无需大型语言模型。 open-vocabulary open vocabulary large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页