cs.AI（2024-09-19）

📊 共 13 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

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

#题目一句话要点标签🔗⭐
1 Multimodal Learning for Scalable Representation of High-Dimensional Medical Data 提出MarbliX框架，用于高维医学多模态数据可扩展表征学习，提升病例检索和临床洞察。 multimodal
2 HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling 提出HLLM：通过分层大语言模型增强序列推荐中的物品和用户建模 large language model ✅
3 Performance and Power: Systematic Evaluation of AI Workloads on Accelerators with CARAML CARAML：用于系统评估AI加速器上ML工作负载性能与功耗的基准测试套件 large language model
4 AutoVerus: Automated Proof Generation for Rust Code AutoVerus：利用LLM自动生成Rust代码正确性证明 large language model
5 Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions 研究表明LLM智能体可在多商品竞争中进行策略性共谋，实现市场分割 large language model
6 System 2 thinking in OpenAI's o1-preview model: Near-perfect performance on a mathematics exam OpenAI o1-preview模型在数学考试中展现近乎完美的System 2思维能力 large language model
7 Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts 揭示Prompt编程特性：通过开发者访谈理解Prompt驱动软件的构建过程 foundation model
8 Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues 提出基于Transformer的多通道目标声源提取框架，利用时空线索提升分离性能。 TAMP
9 On the Effectiveness of LLMs for Manual Test Verifications 利用大型语言模型生成人工测试验证，提升测试效率与覆盖率 large language model
10 Bundle Fragments into a Whole: Mining More Complete Clusters via Submodular Selection of Interesting webpages for Web Topic Detection 提出一种基于子模选择的网页聚类方法，用于从碎片化主题中挖掘更完整的热点话题。 multimodal

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

#题目一句话要点标签🔗⭐
11 Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case 提出VARP框架，探索VLM在《黑神话：悟空》等ARPG游戏中视觉驱动的智能体控制能力 reinforcement learning large language model multimodal ✅
12 DenoMamba: A fused state-space model for low-dose CT denoising DenoMamba：一种用于低剂量CT降噪的融合状态空间模型 Mamba SSM
13 A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification 探索提示模板与类别描述，提升零样本音频分类性能。 contrastive learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页