cs.AI（2024-10-11）

📊 共 29 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models 利用大模型评审团分析行业博客，洞察软件工程与基础模型的交叉应用。 large language model foundation model ✅
2 Multimodal Audio-based Disease Prediction with Transformer-based Hierarchical Fusion Network 提出Transformer分层融合网络，用于多模态音频疾病预测，实现更全面的特征利用。 multimodal
3 Can a large language model be a gaslighter? 提出DeepCoG框架，研究并缓解大语言模型中的“煤气灯效应”攻击。 large language model
4 Natural Language Counterfactual Explanations for Graphs Using Large Language Models 利用大语言模型为图结构数据生成自然语言反事实解释 large language model
5 Synthetic Students: A Comparative Study of Bug Distribution Between Large Language Models and Computing Students 研究LLM生成代码缺陷分布，指导可信的合成学生数据生成 large language model
6 PEAR: A Robust and Flexible Automation Framework for Ptychography Enabled by Multiple Large Language Model Agents PEAR：基于多LLM Agent的稳健、灵活的叠层衍射成像自动化框架 large language model
7 The structure of the token space for large language models 通过分析Token空间结构，揭示大语言模型行为与局限性 large language model
8 ViT3D Alignment of LLaMA3: 3D Medical Image Report Generation ViT3D对齐LLaMA3用于3D医学影像报告生成 large language model multimodal
9 Baichuan-Omni Technical Report 开源7B多模态大语言模型Baichuan-Omni，支持图文音视频并发处理与交互 large language model multimodal
10 One Step at a Time: Combining LLMs and Static Analysis to Generate Next-Step Hints for Programming Tasks 结合LLM与静态分析，为编程学习者生成下一步提示 large language model chain-of-thought
11 Using off-the-shelf LLMs to query enterprise data by progressively revealing ontologies 提出一种渐进式暴露本体的方法，利用现成LLM查询企业数据，克服了长文本prompt限制。 large language model
12 P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains P-FOLIO：利用人工编写的推理链评估并提升LLM的逻辑推理能力 large language model
13 DAWN: Designing Distributed Agents in a Worldwide Network DAWN：设计全球分布式Agent网络，促进LLM智能体协作 large language model
14 Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective 提出UAG框架，解决KG-LLM推理中不确定性量化问题，提升可靠性。 large language model
15 Emergent social conventions and collective bias in LLM populations 研究表明LLM群体可自发形成社会惯例，并可能产生集体偏见 large language model
16 Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning 探索认知参与技术设计空间，利用AI生成代码提升学习效果 large language model
17 Utilizing ChatGPT in a Data Structures and Algorithms Course: A Teaching Assistant's Perspective 利用ChatGPT辅助教学：提升数据结构与算法课程效果 large language model
18 F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents 提出伪代理攻击F2A，利用LLM对安全检测代理的盲信进行提示注入 large language model
19 RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process 提出RePD框架，通过检索式提示分解防御大语言模型的越狱攻击 large language model
20 Federated Vision-Language-Recommendation with Personalized Fusion 提出FedVLR框架，通过个性化融合实现联邦视觉-语言-推荐系统。 multimodal
21 Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks AutoEval：自主评估LLM真值维护与推理能力的新基准 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
22 GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation GIVE：一种知识图谱启发的LLM结构化推理方法，通过真实验证外推提升性能 reinforcement learning large language model chain-of-thought
23 CryoFM: A Flow-based Foundation Model for Cryo-EM Densities CryoFM：基于流模型的冷冻电镜密度图生成式基础模型 flow matching foundation model
24 Words as Beacons: Guiding RL Agents with High-Level Language Prompts 提出基于LLM引导的强化学习框架，解决稀疏奖励环境下的探索难题。 reinforcement learning teacher-student large language model
25 Transforming In-Vehicle Network Intrusion Detection: VAE-based Knowledge Distillation Meets Explainable AI 提出基于VAE知识蒸馏和可解释AI的KD-XVAE，用于车载网络入侵检测。 distillation
26 Public Transport Network Design for Equality of Accessibility via Message Passing Neural Networks and Reinforcement Learning 提出基于MPNN和强化学习的公共交通网络设计方法，提升可达性公平性 reinforcement learning
27 OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents OpenCity：一个可扩展的平台，用大规模LLM智能体模拟城市活动 predictive model large language model
28 Multi-Agent Actor-Critics in Autonomous Cyber Defense 提出基于多智能体Actor-Critic的自主网络防御方法，提升网络安全策略的智能化水平。 reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
29 PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning 提出PoisonBench，评估大语言模型在偏好学习中对数据投毒的脆弱性。 manipulation preference learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页