cs.AI（2024-02-05）

📊 共 18 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Graph-enhanced Large Language Models in Asynchronous Plan Reasoning 提出图增强大语言模型以解决异步计划推理问题 large language model ✅
2 Adversarial Text Purification: A Large Language Model Approach for Defense 提出对抗性文本净化方法以增强文本分类器的防御能力 large language model
3 A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications 系统性调查提示工程在大语言模型中的应用与技术 large language model
4 Neural networks for abstraction and reasoning: Towards broad generalization in machines 提出新方法以解决抽象与推理问题 large language model
5 Governance of Generative Artificial Intelligence for Companies 提出生成性人工智能治理框架以应对企业挑战 large language model
6 Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models 提出对话重构攻击以揭示GPT模型的隐私泄露风险 large language model
7 Understanding the planning of LLM agents: A survey 提出系统性视角以提升LLM代理的规划能力 large language model
8 C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models 提出C-RAG框架以解决检索增强语言模型的生成风险问题 large language model
9 User Centric Evaluation of Code Generation Tools 提出用户中心评估方法以优化代码生成工具的可用性 large language model
10 List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation 提出Reranking-Truncation联合模型以解决信息检索中的错误累积问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
11 DeAL: Decoding-time Alignment for Large Language Models 提出DeAL框架以解决大语言模型对齐问题 reinforcement learning RLHF large language model
12 Large Language Model Distilling Medication Recommendation Model 提出LEADER模型以解决药物推荐中的语义理解问题 distillation large language model
13 Abstracted Trajectory Visualization for Explainability in Reinforcement Learning 提出抽象轨迹可视化以解决非RL专家理解RL模型的问题 reinforcement learning
14 Curriculum reinforcement learning for quantum architecture search under hardware errors 提出课程强化学习算法以解决量子架构搜索中的噪声问题 reinforcement learning
15 Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning 通过元强化学习学习抽象视觉运动映射以提升技能学习效率 reinforcement learning
16 Dual Knowledge Distillation for Efficient Sound Event Detection 提出双重知识蒸馏以解决高效声音事件检测问题 distillation

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
17 Point and Instruct: Enabling Precise Image Editing by Unifying Direct Manipulation and Text Instructions 提出Point and Instruct以解决图像编辑中的精确操作问题 manipulation
18 Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks 提出Beyond Text方法以改善机器人导航中的决策能力 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页