cs.AI(2024-06-26)
📊 共 14 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱九:具身大模型 (Embodied Foundation Models) (8 🔗1)
支柱一:机器人控制 (Robot Control) (3 🔗1)
支柱二:RL算法与架构 (RL & Architecture) (3)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (8 篇)
🔬 支柱一:机器人控制 (Robot Control) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | GenRL: Multimodal-foundation world models for generalization in embodied agents | GenRL:用于具身智能体泛化的多模态基础世界模型 | locomotion manipulation reinforcement learning | ✅ | |
| 10 | "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models | 揭示RAG模型漏洞:通过恶意知识注入操纵模型行为 | manipulation large language model | ||
| 11 | PlaMo: Plan and Move in Rich 3D Physical Environments | PlaMo:在复杂3D物理环境中规划和移动人形机器人 | humanoid locomotion |
🔬 支柱二:RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations | 批判性评估RLxF对齐方法:揭示其在伦理和安全方面的局限性与矛盾 | reinforcement learning RLHF large language model | ||
| 13 | Dating ancient manuscripts using radiocarbon and AI-based writing style analysis | Enoch:结合放射性碳定年与AI书法分析,用于古代手稿的精准断代 | MAE multimodal | ||
| 14 | Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning | 提出1-to-K对比学习,提升跨语言跨模态检索一致性 | contrastive learning |