cs.AI（2023-12-05）
📊 共 6 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) (4)
支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Training on Synthetic Data Beats Real Data in Multimodal Relation Extraction | 提出MI2RAGE，利用互信息指导的合成数据生成，显著提升多模态关系抽取性能。 | multimodal | ||
| 2 | A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education | 利用GPT-4生成Python编程多选题：一项与人工命题的对比研究 | large language model | ||
| 3 | Beyond Isolation: Multi-Agent Synergy for Improving Knowledge Graph Construction | 提出CooperKGC，利用多智能体协同提升知识图谱构建质量 | large language model | ||
| 4 | Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety | 提出CREST框架，利用神经符号AI提升LLM的可信度，解决一致性、可靠性、可解释性和安全性问题。 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation | 提出创意跳跃思维框架以提升大语言模型的幽默生成能力 | HuMoR large language model multimodal | ✅ |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Large Knowledge Model: Perspectives and Challenges | 提出大型知识模型以解决人类知识管理挑战 | manipulation large language model |