cs.AI（2025-07-13）

📊 共 17 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Bridging Bots: from Perception to Action via Multimodal-LMs and Knowledge Graphs 提出一种神经符号框架，结合多模态LLM和知识图谱，提升机器人平台互操作性。 multimodal
2 KEN: Knowledge Augmentation and Emotion Guidance Network for Multimodal Fake News Detection 提出知识增强与情感引导网络KEN，用于提升多模态假新闻检测的准确性。 multimodal
3 A Serverless Architecture for Real-Time Stock Analysis using Large Language Models: An Iterative Development and Debugging Case Study 提出一种基于无服务器架构和LLM的实时股票分析系统，降低AI金融工具开发门槛。 large language model
4 Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey 综述：面向大语言推理模型中简洁自适应思维的研究进展 large language model chain-of-thought
5 LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents 提出LaSM，通过层级缩放机制防御GUI智能体上的弹出窗口攻击 large language model multimodal
6 Prompting for Performance: Exploring LLMs for Configuring Software 探索LLM在软件配置中的应用，利用Prompt提升性能 large language model
7 TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit TinyTroupe：一个基于LLM的多智能体角色模拟工具包，用于逼真的人类行为模拟。 large language model ✅
8 Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations 提出一种基于LLM解释的神经符号推理方法，保证逻辑的可靠性和完备性 large language model
9 eSapiens: A Platform for Secure and Auditable Retrieval-Augmented Generation eSapiens：一个安全可审计的检索增强生成平台，赋能企业AI应用。 large language model
10 A Mixture of Linear Corrections Generates Secure Code 提出混合线性校正方法，提升LLM代码生成安全性与功能性 large language model
11 Evaluating LLMs on Sequential API Call Through Automated Test Generation 提出StateGen框架，自动生成API序列调用测试用例，评估LLM工具使用能力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
12 From Reasoning to Super-Intelligence: A Search-Theoretic Perspective 提出Diligent Learner，通过搜索理论解决LLM复杂推理学习难题。 reinforcement learning large language model chain-of-thought
13 A Disentangled Representation Learning Framework for Low-altitude Network Coverage Prediction 提出一种解耦表征学习框架，用于低空网络覆盖预测。 representation learning MAE
14 GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective 提出基于生成式AI的多智能体强化学习框架，实现分布式智能涌现 reinforcement learning
15 OrQstrator: An AI-Powered Framework for Advanced Quantum Circuit Optimization OrQstrator：一个用于高级量子电路优化的AI驱动框架 reinforcement learning deep reinforcement learning DRL

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning CTP：基于离线模型强化学习的高效高质量轨迹优化方法 trajectory optimization reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
17 SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations 提出Chain-of-Abstractions框架以增强AI生成互动模拟的规范与调试能力 affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页