cs.AI（2024-06-21）

📊 共 16 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2)

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

#题目一句话要点标签🔗⭐
1 Enhancing Large Language Model Performance with Gradient-Based Parameter Selection 提出基于梯度的参数选择方法GMT，提升大语言模型微调性能。 large language model
2 GIEBench: Towards Holistic Evaluation of Group Identity-based Empathy for Large Language Models GIEBench：构建群体身份共情能力评测基准，提升大语言模型对不同群体的理解 large language model ✅
3 Investigating the impact of 2D gesture representation on co-speech gesture generation 研究2D/3D手势表示对语音驱动手势生成模型性能的影响 multimodal
4 LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking 提出LLM2TEA以解决跨领域设计优化问题 large language model
5 Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference Logicbreaks框架：研究基于规则推理的大语言模型如何被恶意prompt攻击 large language model
6 I don't trust you (anymore)! -- The effect of students' LLM use on Lecturer-Student-Trust in Higher Education 研究LLM使用对师生信任的影响，强调透明度以促进团队合作 large language model
7 Inferring Pluggable Types with Machine Learning 提出基于机器学习的类型推断方法，自动为Java代码添加类型限定符。 large language model
8 Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code Stacks BICS：评估LLM在大型Python代码中查找语法错误的能力 large language model
9 Évaluation des capacités de réponse de larges modèles de langage (LLM) pour des questions d'historiens 评估大型语言模型在回答历史学家提问方面的能力，揭示其在法语环境下的不足。 large language model
10 A GPT-based Code Review System for Programming Language Learning 提出基于GPT的代码评审系统，用于个性化编程语言学习反馈。 large language model
11 Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback Pistis-RAG：利用人类反馈增强检索增强生成，提升内容排序和生成质量 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🔗⭐
12 RouteFinder: Towards Foundation Models for Vehicle Routing Problems RouteFinder：面向车辆路径问题的通用基础模型框架 reinforcement learning foundation model ✅
13 KnobTree: Intelligent Database Parameter Configuration via Explainable Reinforcement Learning KnobTree：基于可解释强化学习的智能数据库参数配置 reinforcement learning deep reinforcement learning DRL
14 V-RECS, a Low-Cost LLM4VIS Recommender with Explanations, Captioning and Suggestions V-RECS：低成本LLM4VIS推荐系统，具备解释、描述和建议功能 teacher-student chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 Do Large Language Models Exhibit Cognitive Dissonance? Studying the Difference Between Revealed Beliefs and Stated Answers 提出Revealed Belief框架，揭示大语言模型在不确定性推理中存在的认知失调现象 manipulation large language model
16 Fair, Manipulation-Robust, and Transparent Sortition 提出Goldilocks目标函数，实现公平、抗操纵和透明的政治代表随机抽选。 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页