cs.AI（2025-01-06）

📊 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) (7) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Analyzing Finetuning Representation Shift for Multimodal LLMs Steering	提出一种免训练的多模态LLM行为可解释性与控制框架，用于分析和引导模型。	multimodal
2	Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?	质疑GNN在微服务故障诊断中的有效性，提出拓扑无关的DiagMLP基线模型。	multimodal
3	KG-CF: Knowledge Graph Completion with Context Filtering under the Guidance of Large Language Models	提出KG-CF框架以解决知识图谱补全中的上下文过滤问题	large language model
4	Artificial Intelligence in Creative Industries: Advances Prior to 2025	分析AI在创意产业的最新进展，重点关注生成式AI和LLM带来的创新与效率提升	large language model multimodal
5	Political Events using RAG with LLMs	提出基于RAG的政治事件抽取系统，利用LLM从新闻文章中提取政治事件信息。	large language model
6	CodeVision: Detecting LLM-Generated Code Using 2D Token Probability Maps and Vision Models	CodeVision：利用2D Token概率图和视觉模型检测LLM生成的代码	large language model
7	RTLSquad: Multi-Agent Based Interpretable RTL Design	提出RTLSquad，基于多智能体系统实现可解释的RTL代码设计与优化	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
8	CALM: Curiosity-Driven Auditing for Large Language Models	CALM：基于好奇心驱动的黑盒大语言模型审计方法	reinforcement learning large language model	✅
9	Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies	结合模型检验与共激活图分析，提升深度强化学习策略的安全性和可解释性	reinforcement learning deep reinforcement learning
10	GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT	提出基于Mamba增强UNet的全局-局部特征与对比学习框架GLFC，用于CBCT生成高质量合成CT	Mamba	✅
11	Turn-based Multi-Agent Reinforcement Learning Model Checking	提出一种基于模型检验的轮流制多智能体强化学习验证方法	reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches	综述大型语言模型在通用人工智能中的应用，探讨基础原则与方法	physically plausible vision-language-action VLA

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

#	题目	一句话要点	标签	🔗	⭐
13	CONTINUUM: Detecting APT Attacks through Spatial-Temporal Graph Neural Networks	提出基于时空图神经网络的CONTINUUM模型，用于检测高级持续性威胁攻击。	OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页