cs.AI（2024-10-26）

📊 共 13 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) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	A Novel Multimodal System to Predict Agitation in People with Dementia Within Clinical Settings: A Proof of Concept	提出一种多模态系统，用于预测痴呆症患者在临床环境中的躁动行为	multimodal
2	Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play	提出基于角色扮演的风险评估方法，量化大语言模型伦理倾向与偏见	large language model
3	Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models	针对LLM不确定性估计难题，提出全面分析框架以提升可靠性	large language model
4	Estuary: A Framework For Building Multimodal Low-Latency Real-Time Socially Interactive Agents	Estuary：用于构建低延迟实时社交互动代理的多模态框架	multimodal
5	LLMs Can Evolve Continually on Modality for X-Modal Reasoning	提出PathWeave框架，实现多模态大语言模型在模态上的持续演进，解决新增模态时的计算负担问题。	large language model multimodal	✅
6	Enhancing Lie Detection Accuracy: A Comparative Study of Classic ML, CNN, and GCN Models using Audio-Visual Features	利用听觉-视觉特征，对比经典ML、CNN和GCN模型，提升谎言检测准确率	multimodal
7	AI-Driven Cyber Threat Intelligence Automation	提出基于GPT-4o和One-shot微调的AI驱动网络威胁情报自动化方案	large language model
8	SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement	提出SWE-Search以解决软件代理在动态环境中的适应性问题	large language model
9	Mask-based Membership Inference Attacks for Retrieval-Augmented Generation	提出基于掩码的成员推理攻击框架，用于检测RAG系统中知识库的数据泄露风险。	large language model
10	MAD-Sherlock: Multi-Agent Debate for Visual Misinformation Detection	MAD-Sherlock：用于视觉错误信息检测的多智能体辩论系统	multimodal
11	Optimizing Keyphrase Ranking for Relevance and Diversity Using Submodular Function Optimization (SFO)	提出基于子模函数优化的关键短语排序方法，提升相关性和多样性	large language model
12	Agentic Feedback Loop Modeling Improves Recommendation and User Simulation	提出Agentic反馈环建模，提升推荐系统和用户模拟效果	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
13	MatExpert: Decomposing Materials Discovery by Mimicking Human Experts	MatExpert：模仿人类专家，解构材料发现流程以加速新材料设计	contrastive learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页