cs.AI(2024-08-13)

📊 共 13 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) (7 🔗1) 支柱二:RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗
1 Can Large Language Models Reason? A Characterization via 3-SAT 通过3-SAT问题刻画大语言模型的推理能力,揭示其不具备真正的推理能力。 large language model
2 Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models Casper:一种用于保护Web LLM用户隐私的Prompt清洗技术 large language model
3 Causal Agent based on Large Language Model 提出基于大语言模型的因果Agent,解决LLM在因果推理上的难题 large language model
4 Evaluating Research Quality with Large Language Models: An Analysis of ChatGPT's Effectiveness with Different Settings and Inputs 利用大型语言模型评估研究质量:分析ChatGPT在不同设置和输入下的有效性 large language model
5 Large language models can consistently generate high-quality content for election disinformation operations 研究表明大型语言模型能持续生成高质量内容,用于操纵选举的不实信息传播。 large language model
6 Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents DEI框架:集成软件工程Agent的多元智能,显著提升问题解决能力 large language model
7 What should I wear to a party in a Greek taverna? Evaluation for Conversational Agents in the Fashion Domain 构建多语言时尚对话数据集,评估LLM在电商场景下作为对话助手的性能 large language model

🔬 支柱二:RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗
8 Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement Learning 提出基于模仿学习与强化学习的个性化动态难度调整方法 reinforcement learning imitation learning
9 Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents Agent Q:结合蒙特卡洛树搜索与偏好优化的自主AI Agent推理与学习框架 behavior cloning DPO direct preference optimization
10 Introduction to Reinforcement Learning 强化学习入门综述:概述核心概念、方法与学习资源 reinforcement learning
11 LLMs can Schedule 利用大型语言模型解决Job Shop调度问题,性能媲美传统神经方法 reinforcement learning large language model
12 Multi-Agent Continuous Control with Generative Flow Networks 提出MACFN,通过生成流网络实现多智能体连续控制中的协同探索。 reinforcement learning flow matching

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
13 EditScribe: Non-Visual Image Editing with Natural Language Verification Loops EditScribe:利用自然语言验证循环实现非可视图像编辑 manipulation multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页