cs.AI（2025-03-28）

📊 共 16 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) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗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 Teaching LLMs Music Theory with In-Context Learning and Chain-of-Thought Prompting: Pedagogical Strategies for Machines 利用上下文学习和思维链提示，探索LLM在音乐理论教学中的应用 large language model chain-of-thought
2 A Self-Supervised Learning of a Foundation Model for Analog Layout Design Automation 提出基于自监督学习的UNet基础模型，用于模拟版图设计自动化。 foundation model
3 Diagnosis of Pulmonary Hypertension by Integrating Multimodal Data with a Hybrid Graph Convolutional and Transformer Network 提出结合图卷积、CNN和Transformer的混合网络，用于肺动脉高压的多模态数据诊断。 multimodal
4 RobuNFR: Evaluating the Robustness of Large Language Models on Non-Functional Requirements Aware Code Generation 提出RobuNFR以评估大型语言模型在非功能性需求代码生成中的鲁棒性问题 large language model
5 Training Large Language Models for Advanced Typosquatting Detection 利用大型语言模型提升高级域名仿冒检测能力 large language model
6 PharmAgents: Building a Virtual Pharma with Large Language Model Agents 提出PharmAgents以解决药物发现过程中的复杂性问题 large language model
7 Unicorn: Text-Only Data Synthesis for Vision Language Model Training Unicorn：提出一种纯文本数据合成方法，用于视觉语言模型训练。 large language model multimodal ✅
8 QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks? QuestBench：评估LLM在不完备信息下提问以完成推理任务的能力 large language model
9 Generating Structured Plan Representation of Procedures with LLMs 提出SOPStruct，利用LLM将标准操作程序转换为结构化决策树表示，提升流程效率。 large language model
10 Post-Incorporating Code Structural Knowledge into Pretrained Models via ICL for Code Translation 提出基于信息覆盖的ICL方法，提升预训练模型在代码翻译中对代码结构的处理能力 large language model
11 Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMs 提出基于多模态LLM的Agent中心个性化多重聚类框架，提升用户兴趣聚类效果。 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 Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF 提出基于夏普比率指导的主动学习方法，高效优化RLHF中的偏好学习。 reinforcement learning preference learning RLHF
13 On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations 揭示深度强化学习实现互换性假设的误区，强调代码一致性的重要性 reinforcement learning deep reinforcement learning DRL
14 Make Some Noise: Towards LLM audio reasoning and generation using sound tokens 提出基于声音令牌的LLM音频推理与生成方法 flow matching VQ-VAE large language model
15 Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankers 研究多阶段微调对Cross-encoder重排序器效果的影响，对比单阶段对比学习微调。 contrastive learning distillation 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🔗⭐
16 Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users 评估多模态语言模型作为视障用户视觉辅助工具的有效性 scene understanding large language model multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页