cs.AI（2024-08-09）

📊 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Assessment of Cell Nuclei AI Foundation Models in Kidney Pathology	评估细胞核AI基础模型在肾脏病理学中的性能，CellViT表现最佳但仍有差距。	foundation model
2	Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models	针对大语言模型时代XAI的挑战，提出以人为中心的解释性框架	large language model
3	Enhancing Exploratory Learning through Exploratory Search with the Emergence of Large Language Models	结合探索性搜索与大语言模型，提升学生的探索式学习能力	large language model
4	Is ChatGPT a Good Software Librarian? An Exploratory Study on the Use of ChatGPT for Software Library Recommendations	评估ChatGPT作为软件库推荐工具的有效性，揭示其优势与局限	large language model
5	SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions	SHIELD：LLM驱动的模式归纳用于电动汽车电池供应链中断预测分析	large language model
6	AttackER: Towards Enhancing Cyber-Attack Attribution with a Named Entity Recognition Dataset	提出AttackER数据集，用于提升网络攻击溯源中的命名实体识别性能	large language model
7	A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?	综述性研究：大型语言模型时代下的文本到SQL转换技术进展与未来方向	large language model	✅
8	COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis	COAST：通过基于通信代理的数据合成增强LLM的代码调试能力	large language model	✅
9	ConfusedPilot: Confused Deputy Risks in RAG-based LLMs	ConfusedPilot：揭示并缓解RAG-LLM中Confused Deputy风险，保障企业数据安全	large language model
10	h4rm3l: A language for Composable Jailbreak Attack Synthesis	提出h4rm3l语言，用于可组合的越狱攻击合成，提升大语言模型安全性评估。	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	🔗	⭐
11	SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation	SELD-Mamba：利用选择性状态空间模型进行声源定位与检测，并估计声源距离。	Mamba
12	Neural Machine Unranking	提出CoCoL框架，解决神经信息检索中选择性信息移除的难题	teacher-student distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworks	Rag 'n Roll框架评估RAG系统抵抗间接提示注入攻击的脆弱性	manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页