cs.AI（2025-01-24）

📊 共 13 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (1)

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

#题目一句话要点标签🔗⭐
1 Distributed Multi-Agent Coordination Using Multi-Modal Foundation Models 提出VL-DCOPs框架，利用多模态大模型自动生成约束，解决多智能体协同问题。 large language model foundation model multimodal
2 Rethinking Foundation Models for Medical Image Classification through a Benchmark Study on MedMNIST 通过MedMNIST基准研究，重新评估医学图像分类中的预训练模型 foundation model
3 Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph 提出FastToG，通过知识图谱社区化推理加速大语言模型并提升准确性。 large language model
4 Explaining Categorical Feature Interactions Using Graph Covariance and LLMs 提出基于图协方差和LLM的框架，用于解释分类特征交互并挖掘数据驱动的洞察。 large language model TAMP
5 Top Ten Challenges Towards Agentic Neural Graph Databases 提出自主神经图数据库以解决现有图数据库推理能力不足的问题 large language model foundation model
6 Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs 提出因果图增强的图RAG方法，提升LLM在知识密集型任务中的复杂推理能力 large language model chain-of-thought
7 Exploring the sustainable scaling of AI dilemma: A projective study of corporations' AI environmental impacts 提出评估AI环境影响的方法，揭示生成式AI能耗问题并预测未来趋势 large language model
8 Personalizing Education through an Adaptive LMS with Integrated LLMs 提出自适应学习管理系统以解决个性化教育问题 large language model
9 Extracting Problem Structure with LLMs for Optimized SAT Local Search 利用LLM提取问题结构，优化SAT局部搜索 large language model
10 VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoning VERUS-LM：结合LLM与符号推理的通用框架，提升复杂推理任务性能 large language model
11 Prompt-Based Cost-Effective Evaluation and Operation of ChatGPT as a Computer Programming Teaching Assistant 提出基于Prompt的ChatGPT评估与应用方案，用于计算机编程教学辅助。 large language model
12 A Zero-Shot LLM Framework for Automatic Assignment Grading in Higher Education 提出一种零样本LLM框架，用于高等教育中自动作业评分。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
13 Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation 提出HM4SR模型，通过分层时间感知专家混合网络解决多模态序列推荐中冗余信息干扰和动态兴趣建模问题。 contrastive learning TAMP

⬅️ 返回 cs.AI 首页 · 🏠 返回主页