cs.AI（2024-08-11）
📊 共 10 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memes | HateSieve：用于检测和分割多模态Meme中仇恨内容的对比学习框架 | contrastive learning multimodal | ||
| 2 | DeepAir: A Multi-Agent Deep Reinforcement Learning Based Scheme for an Unknown User Location Problem | 提出DeepAir以解决无人机环境下用户位置未知问题 | reinforcement learning deep reinforcement learning DRL | ||
| 3 | VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing | 提出VQ-CTAP，用于语音处理中跨模态细粒度序列表示学习 | representation learning multimodal | ✅ | |
| 4 | Root Cause Attribution of Delivery Risks via Causal Discovery with Reinforcement Learning | 提出一种基于因果发现与强化学习的供应链交付风险根因分析方法 | reinforcement learning | ||
| 5 | Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation | 提出FedKD，通过知识蒸馏实现低维联邦知识图谱嵌入，提升通信效率。 | distillation |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms | 借鉴认知科学，提出语义和算法解释框架，提升深度学习模型可解释性 | large language model foundation model | ||
| 7 | Kov: Transferable and Naturalistic Black-Box LLM Attacks using Markov Decision Processes and Tree Search | Kov：利用马尔可夫决策过程和树搜索实现可迁移的自然黑盒LLM攻击 | large language model | ✅ | |
| 8 | Neurosymbolic Methods for Rule Mining | 综述神经符号方法在规则挖掘中的应用，涵盖深度学习、嵌入和大型语言模型。 | large language model | ||
| 9 | Top Pass: Improve Code Generation by Pass@k-Maximized Code Ranking | Top Pass：通过优化Pass@k最大化代码排序，提升代码生成质量 | large language model | ||
| 10 | GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective | GPT-4能从第三人称视角模拟平均人类的情感认知 | large language model |