cs.AI（2025-08-01）

📊 共 8 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (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	Accurate and Consistent Graph Model Generation from Text with Large Language Models	提出基于LLM的抽象-具体化框架，提升文本生成图模型的准确性和一致性	large language model
2	Blueprint First, Model Second: A Framework for Deterministic LLM Workflow	提出Source Code Agent框架，解决LLM Agent在结构化环境中的不确定性问题	large language model
3	Mind the Gap: The Divergence Between Human and LLM-Generated Tasks	揭示人类与LLM生成任务的差异：心理驱动与具身性的缺失	large language model
4	Academic Vibe Coding: Opportunities for Accelerating Research in an Era of Resource Constraint	提出Vibe Coding，利用大语言模型加速资源受限的学术研究	large language model

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

#	题目	一句话要点	标签	🔗	⭐
5	Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts	提出一种QoS感知的LLM路由框架，利用DRL优化边缘计算场景下多专家LLM服务。	reinforcement learning deep reinforcement learning DRL
6	Large AI Model-Enabled Secure Communications in Low-Altitude Wireless Networks: Concepts, Perspectives and Case Study	提出基于大模型的低空无线网络安全通信优化框架，提升强化学习性能。	reinforcement learning large language model

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

#	题目	一句话要点	标签	🔗	⭐
7	Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF	提出一种资源高效的多无人机3D场景重建框架	NeRF scene reconstruction scene understanding

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance	提出REACT框架以解决自动驾驶实时碰撞避免问题	trajectory optimization multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页