cs.AI（2024-08-06）

📊 共 8 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) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents	OpenOmni：用于构建多模态对话Agent的开源协作工具，支持端到端pipeline基准测试。	large language model multimodal	✅
2	The Use of Large Language Models (LLM) for Cyber Threat Intelligence (CTI) in Cybercrime Forums	利用大型语言模型分析网络犯罪论坛中的网络威胁情报	large language model
3	A Taxonomy of Architecture Options for Foundation Model-based Agents: Analysis and Decision Model	提出面向基础模型Agent的架构分类法与决策模型，提升Agent设计效率。	foundation model
4	Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learning	提出基于进化学习的“捉迷藏”方法，用于LLM指纹识别，模型家族识别准确率达72%。	large language model
5	LLMs as Probabilistic Minimally Adequate Teachers for DFA Learning	提出概率最小充分教师以解决DFA学习中的错误问题	large language model
6	LLM-Empowered Resource Allocation in Wireless Communications Systems	提出基于LLM的无线通信资源分配方案，旨在优化能效或频谱效率	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	🔗	⭐
7	ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval	提出AMPere模型，利用LLM增强的ASR文本进行跨域产品检索。	representation learning multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Compromising Embodied Agents with Contextual Backdoor Attacks	提出Contextual Backdoor Attack，通过上下文投毒攻击具身智能体	manipulation large language model chain-of-thought

⬅️ 返回 cs.AI 首页 · 🏠 返回主页