cs.AI（2025-01-12）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification 提出一种融合分类学和LLM的多模态分层分类框架，提升分类一致性。 large language model multimodal
2 An efficient approach to represent enterprise web application structure using Large Language Model in the service of Intelligent Quality Engineering 提出一种基于大语言模型的企业Web应用结构表示方法，用于智能质量工程。 large language model
3 Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions 构建用户需求分类体系，探讨LLM、知识图谱和搜索引擎的协同效应 large language model
4 LLMs Model Non-WEIRD Populations: Experiments with Synthetic Cultural Agents 利用大型语言模型构建合成文化代理，模拟非西方人群经济行为 large language model
5 A Study on Educational Data Analysis and Personalized Feedback Report Generation Based on Tags and ChatGPT 提出基于标签和ChatGPT的教育数据分析与个性化反馈报告生成方法 large language model
6 AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds AIOpsLab：用于评估自主云中AI Agent的整体框架 large language model
7 Fine-tuning ChatGPT for Automatic Scoring of Written Scientific Explanations in Chinese 微调ChatGPT用于中文科学解释写作的自动评分 large language model
8 Generative AI in Education: From Foundational Insights to the Socratic Playground for Learning 提出基于生成式AI的Socratic Playground，实现大规模个性化学习 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
9 Risk-Averse Finetuning of Large Language Models 提出基于条件风险价值的风险规避微调方法，降低大语言模型生成有害内容风险 reinforcement learning RLHF large language model
10 An Empirical Study of Deep Reinforcement Learning in Continuing Tasks 针对持续性任务，本文深入研究了深度强化学习算法的性能，并验证了奖励中心化方法的有效性。 reinforcement learning deep reinforcement learning
11 DVM: Towards Controllable LLM Agents in Social Deduction Games DVM：面向社交推理游戏的可控LLM智能体框架 reinforcement learning large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 Generative Artificial Intelligence-Supported Pentesting: A Comparison between Claude Opus, GPT-4, and Copilot 评估通用GenAI在渗透测试中的应用：Claude Opus、GPT-4与Copilot对比 penetration

⬅️ 返回 cs.AI 首页 · 🏠 返回主页