cs.AI（2023-12-02）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Self Generated Wargame AI: Double Layer Agent Task Planning Based on Large Language Model	提出基于大语言模型的双层Agent任务规划，用于智能决策	reinforcement learning large language model
2	Axiomatic Preference Modeling for Longform Question Answering	提出基于公理化偏好建模的长文本问答方法，小模型性能超越GPT-4。	reinforcement learning RLHF large language model	✅
3	Just-in-Time Detection of Silent Security Patches	LLMDA：利用大语言模型及时检测静默安全补丁，防范N-day攻击。	representation learning contrastive learning large language model
4	Adaptive Resource Allocation for Semantic Communication Networks	提出自适应语义资源分配方案，兼容传统无线通信并提升语义通信服务质量。	reinforcement learning deep reinforcement learning DRL

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
5	From Voices to Validity: Leveraging Large Language Models (LLMs) for Textual Analysis of Policy Stakeholder Interviews	利用大型语言模型进行政策利益相关者访谈文本分析，提升效率与信度	large language model
6	Kattis vs. ChatGPT: Assessment and Evaluation of Programming Tasks in the Age of Artificial Intelligence	评估ChatGPT在Kattis编程任务中的表现，揭示其在不同难度编程问题上的能力差异	large language model

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

#	题目	一句话要点	标签	🔗	⭐
7	PROFL: A Privacy-Preserving Federated Learning Method with Stringent Defense Against Poisoning Attacks	PROFL：一种具有严格防御投毒攻击的隐私保护联邦学习方法	OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页