cs.AI（2024-07-23）

📊 共 10 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	UniMEL: A Unified Framework for Multimodal Entity Linking with Large Language Models	UniMEL：一个基于大语言模型的多模态实体链接统一框架	large language model multimodal	✅
2	OpenHands: An Open Platform for AI Software Developers as Generalist Agents	OpenHands：一个面向AI软件开发者作为通用智能体的开放平台	generalist agent large language model
3	RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent	RedAgent：提出上下文感知自主语言Agent，用于LLM的红队测试	large language model
4	Prompt Injection Attacks on Large Language Models in Oncology	揭示医学视觉语言模型易受提示注入攻击的安全漏洞	large language model
5	Artificial Agency and Large Language Models	提出基于动态框架的人工智能体阈值概念模型，并探讨LLM实现人工自主性的可行性。	large language model
6	HAPFI: History-Aware Planning based on Fused Information	提出HAPFI：一种融合历史信息的多模态具身指令跟随规划方法	instruction following
7	Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design	提出层级提示方法，提升LLM在复杂芯片设计中HDL代码生成能力	large language model	✅
8	Patched RTC: evaluating LLMs for diverse software development tasks	提出Patched RTC评估LLM在软件开发任务中的一致性和鲁棒性	large language model
9	PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing	PrimeGuard：通过免调优路由实现安全且有用的LLM	instruction following	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models	提出基于分析的越狱攻击（ABJ），利用LLM推理过程漏洞绕过安全机制。	manipulation large language model multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页