cs.LG（2024-05-14）

📊 共 14 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
1 Deep Reinforcement Learning for Real-Time Ground Delay Program Revision and Corresponding Flight Delay Assignments 利用深度强化学习优化地面延误程序，提升航班延误分配效率 reinforcement learning deep reinforcement learning CQL
2 Optimizing Deep Reinforcement Learning for American Put Option Hedging 优化深度强化学习在美式看跌期权对冲中的应用，提出基于市场校准的再训练策略。 reinforcement learning deep reinforcement learning DRL
3 CIER: A Novel Experience Replay Approach with Causal Inference in Deep Reinforcement Learning 提出CIER：一种基于因果推理的深度强化学习经验回放新方法，提升数据利用率和可解释性。 reinforcement learning deep reinforcement learning DRL
4 Reinformer: Max-Return Sequence Modeling for Offline RL Reinformer：面向离线强化学习的最大回报序列建模方法 reinforcement learning offline RL offline reinforcement learning ✅
5 Self-Distillation Improves DNA Sequence Inference 提出基于自蒸馏的DNA序列推断模型，提升下游任务预测精度 contrastive learning distillation ✅
6 Understanding the performance gap between online and offline alignment algorithms 揭示在线与离线对齐算法在强化学习人类反馈中的性能差距 reinforcement learning RLHF large language model
7 Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning 基于神经崩塌理论分析差分隐私下表征学习的泛化能力与鲁棒性 representation learning
8 Hierarchical Resource Partitioning on Modern GPUs: A Reinforcement Learning Approach 提出基于强化学习的GPU分层资源划分方法，提升多程序并发执行吞吐量。 reinforcement learning
9 Python-Based Reinforcement Learning on Simulink Models 提出基于Python和Simulink的强化学习框架，用于训练并部署控制任务智能体。 reinforcement learning
10 Safety Constrained Multi-Agent Reinforcement Learning for Active Voltage Control 提出安全约束多智能体强化学习算法，用于主动电压控制 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
11 Towards Enhanced RAC Accessibility: Leveraging Datasets and LLMs 利用数据集和LLM增强哥伦比亚航空法规（RAC）的可访问性 large language model ✅
12 Falcon 7b for Software Mention Detection in Scholarly Documents 利用Falcon-7b解决学术文献中软件提及检测与分类问题 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
13 Computation-Aware Kalman Filtering and Smoothing 提出计算感知卡尔曼滤波与平滑算法，解决高维Gauss-Markov模型中的计算瓶颈。 spatiotemporal
14 Improving the Real-Data Driven Network Evaluation Model for Digital Twin Networks 提出基于自编码器和跳跃连接消息传递神经网络的DTN评估模型，提升真实数据驱动下的网络性能评估。 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页