cs.AI（2025-09-18）

📊 共 16 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) (13 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Exploring How Audio Effects Alter Emotion with Foundation Models	利用预训练模型探索音频效果对情感的影响	foundation model multimodal
2	Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling	研究LLM在过程建模中知识驱动的幻觉现象，揭示其固有知识与证据冲突时的可靠性问题。	large language model
3	Towards Human-like Multimodal Conversational Agent by Generating Engaging Speech	提出基于多模态LLM的对话Agent，通过生成更具表现力的语音提升人机交互体验。	multimodal	✅
4	Automating Modelica Module Generation Using Large Language Models: A Case Study on Building Control Description Language	利用大语言模型自动化生成Modelica模块，提升建筑控制描述语言开发效率。	large language model
5	SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair	SecureFixAgent：一种混合LLM Agent，用于自动化Python静态漏洞修复。	large language model
6	Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems	提出哨兵代理以增强多智能体系统的安全性与可信性	large language model
7	OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning	OnlineMate：基于LLM的多智能体同伴系统，用于在线学习中的认知支持	large language model
8	Digging Into the Internal: Causality-Based Analysis of LLM Function Calling	基于因果分析的大语言模型函数调用机制研究，显著提升LLM安全性。	large language model
9	Spatial Audio Motion Understanding and Reasoning	提出空间音频运动理解与推理框架，解决动态声源场景理解难题	large language model
10	Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory	应用Schoenfeld情景理论分析大型推理模型，揭示其思维过程。	chain-of-thought
11	AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production	AgentCompass：面向生产环境中Agent工作流的可靠评估框架	large language model
12	LLM Jailbreak Detection for (Almost) Free!	提出近乎零成本的FJD方法，用于检测大语言模型的越狱攻击。	large language model
13	DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction	DeKeyNLU：通过任务分解和关键词提取增强自然语言到SQL的生成	chain-of-thought

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
14	Generalizable Geometric Image Caption Synthesis	提出RLVR方法以解决几何图像描述生成问题	reinforcement learning large language model multimodal
15	Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning	提出HAD-MFC框架，用于大规模多智能体强化学习中脆弱智能体的识别。	reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation	提出Mesh-infused Neural Acoustic Field (MiNAF)，利用显式几何信息提升高保真RIR生成效果	PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页