cs.AI（2025-09-16）

📊 共 6 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱四：生成式动作 (Generative Motion) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Models	TICL：文本嵌入KNN用于语音上下文学习，解锁大型多模态模型的语音识别能力	foundation model multimodal
2	The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration	揭示多智能体协作中组合隐私泄露风险，并提出ToM和CoDef防御机制。	large language model chain-of-thought
3	Optimizing Agricultural Research: A RAG-Based Approach to Mycorrhizal Fungi Information	提出基于RAG的农业研究系统，提升菌根真菌信息检索与利用效率。	large language model
4	Towards mitigating information leakage when evaluating safety monitors	提出评估安全监控器信息泄露的框架，并设计策略缓解泄露以提升评估可靠性	large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
5	From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing	评估LLM在渗透测试中的功能特性，提升攻击效率与可靠性	penetration large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
6	RepIt: Steering Language Models with Concept-Specific Refusal Vectors	RepIt：利用概念特定拒绝向量引导语言模型，实现精准干预。	manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页