cs.AI（2024-02-28）

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging 提出Lemur框架以解决日志解析中的模板识别问题 large language model chain-of-thought ✅
2 From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs 提出Sum2Act以增强LLM在复杂任务中的工具调用能力 large language model
3 Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners 提出基于用户交互数据生成个性化电商横幅的新方法 large language model
4 Large Language Models As Evolution Strategies 提出EvoLLM以解决黑箱优化问题 large language model
5 Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information 提出随机硅采样以模拟人群子群体意见 large language model
6 Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction 提出DRA方法以解决大型语言模型的安全性问题 large language model
7 Do Large Language Models Mirror Cognitive Language Processing? 通过代表相似性分析探讨大语言模型与认知语言处理的关系 large language model
8 Position Paper: Agent AI Towards a Holistic Intelligence 提出Agent Foundation Model以实现更全面的智能行为 foundation model multimodal
9 Data Interpreter: An LLM Agent For Data Science 提出Data Interpreter以解决数据科学中的复杂任务问题 large language model ✅
10 Automated Discovery of Integral with Deep Learning 利用深度学习自动发现积分计算方法 large language model
11 Commonsense Ontology Micropatterns 提出104种本体设计模式以支持MOMo方法的应用 large language model
12 A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems 提出多层次安全分析以解决LLM系统安全问题 large language model ✅
13 Language Models Represent Beliefs of Self and Others 通过解码语言模型内部表征提升理论心智能力 large language model
14 TroubleLLM: Align to Red Team Expert 提出TroubleLLM以生成可控的安全性测试提示 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
15 MedAide: Leveraging Large Language Models for On-Premise Medical Assistance on Edge Devices 提出MedAide以解决边缘设备医疗辅助问题 reinforcement learning RLHF large language model
16 A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist 提出FinAgent以解决金融交易中的多模态数据处理问题 reinforcement learning multimodal
17 The Fusion of Deep Reinforcement Learning and Edge Computing for Real-time Monitoring and Control Optimization in IoT Environments 提出基于深度强化学习与边缘计算的优化控制系统以解决工业物联网实时监控问题 reinforcement learning deep reinforcement learning
18 ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games 提出ELA以解决零和博弈中的离线学习效率问题 reinforcement learning offline reinforcement learning imitation learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards 提出动态感知奖励以提高偏好强化学习的样本效率 quadruped reinforcement learning policy learning ✅

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
20 Auditable Homomorphic-based Decentralized Collaborative AI with Attribute-based Differential Privacy 提出AerisAI以解决联邦学习中的数据隐私问题 OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页