cs.AI（2025-03-26）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 A Survey of Multimodal Retrieval-Augmented Generation 综述多模态检索增强生成技术，提升LLM在多模态信息处理中的性能 large language model multimodal
2 D4R -- Exploring and Querying Relational Graphs Using Natural Language and Large Language Models -- the Case of Historical Documents D4R：利用自然语言和LLM探索关系图，应用于历史文档查询 large language model
3 FinAudio: A Benchmark for Audio Large Language Models in Financial Applications FinAudio：金融场景下音频大语言模型评测基准 large language model
4 PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving 提出PHYSICS：用于评估大模型在大学物理问题求解能力的综合基准 foundation model
5 CodeTool: Enhancing Programmatic Tool Invocation of LLMs via Process Supervision CodeTool：通过过程监督增强LLM的程序化工具调用能力 large language model
6 Leveraging LLMs, IDEs, and Semantic Embeddings for Automated Move Method Refactoring 提出MM-assist，利用LLM、IDE和语义嵌入自动化Move Method重构，显著提升推荐准确率。 large language model
7 QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions QualiSpeech：提出一种基于自然语言推理和描述的语音质量评估数据集。 large language model ✅
8 Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations 评估LLM代码优化对能源效率的影响：Matlab脚本的案例研究 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🔗⭐
9 Synthesizing world models for bilevel planning 提出TheoryCoder，通过合成世界模型进行双层规划，提升强化学习的样本效率和适应性。 reinforcement learning world model large language model
10 Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation 提出透视转换神经符号世界模型，用于具有社会意识的机器人导航 reinforcement learning world model egocentric
11 Exploiting Temporal State Space Sharing for Video Semantic Segmentation 提出TV3S架构，利用时序状态空间共享提升视频语义分割性能。 Mamba state space model spatiotemporal ✅
12 Graph-Enhanced Model-Free Reinforcement Learning Agents for Efficient Power Grid Topological Control 提出图增强无模型强化学习，用于高效电力网络拓扑控制 reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页