cs.AI（2025-04-13）

📊 共 14 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generation 提出Draw with Thought框架，利用多模态推理生成可编辑的科学图表。 large language model multimodal chain-of-thought
2 Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations 通过领域微调大语言模型实现计算流体动力学模拟的自动化配置 large language model chain-of-thought ✅
3 InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signals InfoMAE：通过高效跨模态对齐提升多模态时间序列感知性能 multimodal
4 MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions MigGPT：利用大语言模型自动迁移不同Linux内核版本的外部补丁 large language model
5 Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs 提出GasEraser，通过重分配注意力权重缓解LMMs中的否定诱导欺骗问题 multimodal
6 Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025 利用LLM反馈提升评审质量：ICLR 2025大规模随机对照研究 large language model ✅
7 Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws 通过压缩理解LLM行为：数据生成、知识获取与缩放规律 large language model
8 Migrating Code At Scale With LLMs At Google 利用LLM在Google规模化迁移代码，提升开发效率 large language model
9 AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations AgentDynEx：通过引导机制增强多智能体模拟的力学和动态特性 large language model
10 The Quantum LLM: Modeling Semantic Spaces with Quantum Principles 提出量子LLM框架，利用量子力学原理建模语义空间 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
11 Distilling Transitional Pattern to Large Language Models for Multimodal Session-based Recommendation 提出TPAD框架，利用LLM蒸馏过渡模式，提升多模态会话推荐性能 distillation large language model multimodal
12 Multi-Modal Hypergraph Enhanced LLM Learning for Recommendation 提出HeLLM框架，融合超图结构与序列行为增强LLM推荐能力 contrastive learning large language model multimodal
13 Optimizing Multi-Gateway LoRaWAN via Cloud-Edge Collaboration and Knowledge Distillation 提出基于云边协同和知识蒸馏的HEAT-LDL算法，优化多网关LoRaWAN网络资源分配。 distillation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Enhancing Mathematical Reasoning in Large Language Models with Self-Consistency-Based Hallucination Detection 提出基于自洽性的幻觉检测方法，提升大语言模型数学推理能力 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页