cs.LG（2023-12-15）
📊 共 17 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) (8)
支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2)
支柱八：物理动画 (Physics-based Animation) (3)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping | 利用奖励塑造加速逆强化学习的计算效率 | reinforcement learning inverse reinforcement learning reward shaping | ||
| 2 | Small Dataset, Big Gains: Enhancing Reinforcement Learning by Offline Pre-Training with Model Based Augmentation | 提出基于模型增强的离线预训练方法，提升小数据集强化学习性能 | reinforcement learning offline reinforcement learning world model | ||
| 3 | Multi-Objective Reinforcement Learning-based Approach for Pressurized Water Reactor Optimization | 提出PEARL方法以优化压水反应堆的多目标问题 | reinforcement learning curriculum learning | ||
| 4 | GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy | GraphRARE：利用相对熵和强化学习增强图神经网络，提升异质图上的节点分类性能 | reinforcement learning deep reinforcement learning | ||
| 5 | Student as an Inherent Denoiser of Noisy Teacher | 提出Peer-Advised KD，利用学生模型内在去噪能力提升噪声教师模型的知识蒸馏效果 | distillation large language model | ||
| 6 | Assume-Guarantee Reinforcement Learning | 提出一种基于假设-保证的模块化强化学习方法，解决复杂环境下的控制问题。 | reinforcement learning | ||
| 7 | Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classification | 提出听诊器引导的监督对比学习，解决呼吸音分类中的跨域适应问题。 | contrastive learning | ||
| 8 | Urban Region Embedding via Multi-View Contrastive Prediction | 提出ReCP模型，通过多视角对比预测学习城市区域嵌入表示，提升城市功能理解。 | representation learning contrastive learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | Data-Efficient Multimodal Fusion on a Single GPU | 提出FuseMix：一种数据高效的多模态融合方法，显著降低训练成本。 | multimodal | ✅ | |
| 10 | TSRNet: Simple Framework for Real-time ECG Anomaly Detection with Multimodal Time and Spectrogram Restoration Network | TSRNet：一种基于多模态时域与频谱图恢复网络的实时心电图异常检测框架 | multimodal | ✅ | |
| 11 | Beyond Empirical Windowing: An Attention-Based Approach for Trust Prediction in Autonomous Vehicles | 提出基于注意力机制的选择性窗口网络SWAN，用于自动驾驶中的信任预测。 | multimodal | ||
| 12 | 3FM: Multi-modal Meta-learning for Federated Tasks | 提出3FM：一种用于联邦任务的多模态元学习框架，解决模态异构和数据缺失问题。 | multimodal | ||
| 13 | Vectorizing string entries for data processing on tables: when are larger language models better? | 研究表格数据向量化中，大型语言模型在何种情况下更优 | large language model |
🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 14 | Multi-stage Learning for Radar Pulse Activity Segmentation | 提出多阶段学习方法，用于雷达脉冲活动分割与定位，提升电子战系统效能。 | PULSE | ||
| 15 | Challenges with unsupervised LLM knowledge discovery | 揭示无监督LLM知识发现的局限性：现有方法易提取显著特征而非真实知识 | simulated character large language model | ||
| 16 | Accelerating Neural Network Training: A Brief Review | 研究加速深度神经网络训练的方法，关注ResNet50、ViT和EfficientNet模型。 | AMP |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 17 | Adversarial Robustness on Image Classification with $k$-means | 提出基于k-means的对抗训练方法，提升图像分类聚类算法的鲁棒性。 | manipulation |