cs.AI（2023-11-01）

📊 共 15 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) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake? 提出WTaG基准以解决个性化任务指导问题 foundation model multimodal
2 Advances in Embodied Navigation Using Large Language Models: A Survey 综述大型语言模型在具身导航中的应用与挑战 large language model ✅
3 Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Bias 评估大型语言模型在捕捉全球变暖公众意见中的算法忠实度与偏见 large language model
4 Improving Interpersonal Communication by Simulating Audiences with Language Models 提出EGS框架以提升人际沟通效果 large language model chain-of-thought
5 SAGE: Smart home Agent with Grounded Execution 提出SAGE以解决智能家居助手的执行与知识局限问题 large language model
6 SALLM: Security Assessment of Generated Code 提出SALLM框架以评估生成代码的安全性 large language model
7 Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving 将语言模型作为层次化策略以提升复杂问题求解能力 large language model ✅
8 On the Opportunities of Green Computing: A Survey 提出绿色计算框架以应对人工智能的环境影响 large language model
9 ChatCoder: Chat-based Refine Requirement Improves LLMs' Code Generation 提出ChatCoder以解决人类需求模糊导致的代码生成问题 large language model
10 Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems 提出Magmaw以解决多模态无线通信系统的对抗攻击问题 multimodal
11 Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities 提出主观性建模方法以解决多元社区的有毒评论识别问题 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🔗⭐
12 On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval 提出任务个性化的多模态少样本学习以解决视觉丰富文档实体检索问题 contrastive learning multimodal
13 A Multi-Agent Reinforcement Learning Framework for Public Health Decision Analysis 提出多智能体强化学习框架以优化公共卫生决策 reinforcement learning
14 Emergence of Collective Open-Ended Exploration from Decentralized Meta-Reinforcement Learning 提出去中心化元强化学习以实现集体开放式探索 reinforcement learning
15 QFree: A Universal Value Function Factorization for Multi-Agent Reinforcement Learning 提出QFree以解决多智能体强化学习中的价值函数分解问题 reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页