cs.AI（2025-01-02）

📊 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) 支柱六：视频提取与匹配 (Video Extraction) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

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

#题目一句话要点标签🔗⭐
1 ScarNet: A Novel Foundation Model for Automated Myocardial Scar Quantification from LGE in Cardiac MRI ScarNet：一种用于心脏MRI中LGE图像心肌瘢痕自动量化的新型基础模型 foundation model
2 CySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models 提出CySecBench，一个基于生成式AI的、面向网络安全的提示数据集，用于评估大型语言模型。 large language model
3 A Metasemantic-Metapragmatic Framework for Taxonomizing Multimodal Communicative Alignment 提出元语义-元语用框架，用于多模态交流对齐的分类与理解。 multimodal
4 A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation A3：用于移动GUI代理的Android代理竞技场，采用基于必要状态的过程化评估 large language model multimodal
5 CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countries CultureVLM：构建文化理解基准并微调视觉-语言模型，提升其在100多国家文化概念上的理解能力 multimodal
6 The Prompt Alchemist: Automated LLM-Tailored Prompt Optimization for Test Case Generation Prompt Alchemist：自动化定制LLM的提示优化，用于测试用例生成 large language model
7 Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search 提出基于蒙特卡洛树搜索的过程监督方法，提升LLM的推理能力 large language model
8 Harnessing Multi-Agent LLMs for Complex Engineering Problem-Solving: A Framework for Senior Design Projects 提出基于多智能体LLM的框架，用于解决复杂工程问题，辅助毕业设计项目。 large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
9 MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions 提出基于Valence和Arousal的多模态匹配框架MMVA，用于图像、音乐和音乐描述的情感内容理解。 motion matching multimodal
10 MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification MalCL：利用GAN生成回放对抗恶意软件分类中的灾难性遗忘 feature matching ✅

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

#题目一句话要点标签🔗⭐
11 MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization MuQ：基于Mel残差向量量化的自监督音乐表征学习模型，提升音乐理解任务性能。 representation learning contrastive learning foundation model ✅
12 Stealthy Backdoor Attack to Real-world Models in Android Apps 提出基于隐写术的隐蔽后门攻击，提升安卓应用中真实模型攻击的有效性和隐蔽性。 world model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页