cs.AI（2024-09-13）

📊 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) (8 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 ATFLRec: A Multimodal Recommender System with Audio-Text Fusion and Low-Rank Adaptation via Instruction-Tuned Large Language Model ATFLRec：利用指令调优LLM和低秩适应的多模态推荐系统 large language model multimodal
2 Affective Computing Has Changed: The Foundation Model Disruption 基础模型颠覆情感计算：利用合成多模态数据分析其情感能力 foundation model multimodal
3 Propaganda is all you need 揭示大型语言模型政治倾向：对齐过程中的意识形态偏见分析 large language model
4 Agents in Software Engineering: Survey, Landscape, and Vision 首个LLM Agent在软件工程领域应用的综述，提出包含感知、记忆和行动的关键模块框架。 large language model ✅
5 AI-LieDar: Examine the Trade-off Between Utility and Truthfulness in LLM Agents AI-LieDar框架：研究LLM智能体在效用与真实性之间的权衡 large language model
6 A RAG Approach for Generating Competency Questions in Ontology Engineering 提出基于RAG的框架，利用领域知识增强LLM在本体工程中生成能力问题。 large language model
7 Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task 在人机协作中引入基于LLM的ToM智能体，探索互惠心智理论对团队表现的影响 large language model
8 B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests B4：利用可信测试，实现对代码生成中多个候选解的最优评估与选择 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
9 CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks CPL：关键计划步骤学习提升LLM在推理任务中的泛化能力 reinforcement learning DPO direct preference optimization
10 The unknotting number, hard unknot diagrams, and reinforcement learning 利用强化学习求解解纽数，发现难解纽结图并确定纽结不变量 reinforcement learning

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

#题目一句话要点标签🔗⭐
11 Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation 提出基于LLM的多模态融合方法，用于自然对话中参与度预测 dyadic interaction large language model multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
12 Deep reinforcement learning for tracking a moving target in jellyfish-like swimming 提出基于深度强化学习的控制方法，实现水母状游泳者对移动目标的有效追踪。 locomotion reinforcement learning deep reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
13 Incorporation of Verifier Functionality in the Software for Operations and Network Attack Results Review and the Autonomous Penetration Testing System SONARR集成验证器功能，提升网络攻击结果审查和自主渗透测试系统的数据一致性 penetration

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging 提出SRE-CNN，利用时空旋转等变性提升心脏电影MR成像质量 spatiotemporal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 Using The Concept Hierarchy for Household Action Recognition 提出概念层级方法，用于家庭环境中人类行为的识别与建模。 affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页