cs.AI（2024-07-25）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models 揭示LLM函数调用安全漏洞：提出“越狱函数”攻击方法 large language model ✅
2 Financial Statement Analysis with Large Language Models 利用大型语言模型进行财务报表分析，预测公司未来收益走向 large language model
3 TwIPS: A Large Language Model Powered Texting Application to Simplify Conversational Nuances for Autistic Users TwIPS：基于大语言模型的文本应用，旨在简化自闭症用户在对话中的细微差别理解与表达。 large language model
4 Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment Babel：一种可扩展的多模态预训练模型，用于解决多模态传感中的数据稀疏问题。 large language model foundation model
5 Untrained neural networks can demonstrate memorization-independent abstract reasoning 提出一种无需训练的神经网络，用于解决与记忆无关的抽象推理问题 large language model
6 Combining Cognitive and Generative AI for Self-explanation in Interactive AI Agents 结合认知AI与生成AI，为交互式AI Agent提供自解释能力 chain-of-thought
7 MindGPT: Advancing Human-AI Interaction with Non-Invasive fNIRS-Based Imagined Speech Decoding MindGPT：首个基于非侵入式fNIRS脑成像的想象语音解码与LLM交互系统 large language model
8 Revolutionizing Undergraduate Learning: CourseGPT and Its Generative AI Advancements CourseGPT：利用生成式AI革新本科教学，提升学生学习体验 large language model
9 Very Large-Scale Multi-Agent Simulation in AgentScope AgentScope：面向超大规模多智能体模拟的actor分布式平台 large language model ✅
10 Enhancing Agent Learning through World Dynamics Modeling 提出DiVE框架，通过建模世界动态增强LLM在交互决策中的Agent学习能力 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🔗⭐
11 Shapley Value-based Contrastive Alignment for Multimodal Information Extraction 提出基于Shapley值的对比对齐方法以解决多模态信息提取问题 contrastive learning multimodal
12 Personalized and Context-aware Route Planning for Edge-assisted Vehicles 提出基于图神经网络和深度强化学习的个性化车辆路径规划方法 reinforcement learning deep reinforcement learning DRL
13 Differentiable Quantum Architecture Search in Asynchronous Quantum Reinforcement Learning 提出可微量子架构搜索DiffQAS，用于异步量子强化学习，降低QRL模型设计门槛。 reinforcement learning

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

#题目一句话要点标签🔗⭐
14 ReCorD: Reasoning and Correcting Diffusion for HOI Generation 提出ReCorD，通过推理和校正扩散模型提升HOI图像生成质量 human-object interaction HOI ✅

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

#题目一句话要点标签🔗⭐
15 MindSpeech: Continuous Imagined Speech Decoding using High-Density fNIRS and Prompt Tuning for Advanced Human-AI Interaction MindSpeech：利用高密度fNIRS和Prompt Tuning实现连续想象语音解码，促进人机交互 open-vocabulary open vocabulary large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
16 Multi-Resolution Histopathology Patch Graphs for Ovarian Cancer Subtyping 提出多分辨率组织病理切片图模型，用于卵巢癌亚型分类，性能达到新高。 spatial relationship foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页