cs.LG(2024-03-14)

📊 共 15 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (11 🔗4) 支柱九:具身大模型 (Embodied Foundation Models) (4 🔗1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗
1 MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning 提出MAMBA以解决元强化学习中的样本效率问题 reinforcement learning world model world models
2 Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning 提出最小最大最优算法以解决分布鲁棒离线强化学习问题 reinforcement learning offline RL offline reinforcement learning
3 SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning 提出SINDy-RL以解决深度强化学习的高数据需求问题 reinforcement learning deep reinforcement learning DRL
4 uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures 提出uaMix-MAE以高效调优预训练音频变换器 masked autoencoder MAE
5 EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning 提出EquiAV框架以解决音视频对比学习中的不对称性问题 representation learning contrastive learning
6 TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting 提出TimeMachine以解决长时间序列预测中的依赖捕获问题 Mamba
7 A Reinforcement Learning Approach to Dairy Farm Battery Management using Q Learning 提出基于Q学习的电池管理方法以优化奶牛场能源使用 reinforcement learning
8 A collection of the accepted papers for the Human-Centric Representation Learning workshop at AAAI 2024 汇总AAAI 2024人本中心表示学习研讨会接受论文 representation learning
9 Towards a theory of model distillation 提出模型蒸馏理论以优化复杂模型简化问题 distillation
10 Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality 提出STRIPE以解决动态图异常检测问题 contrastive learning mutual attention
11 Self-Supervised Learning for Time Series: Contrastive or Generative? 对比与生成方法的自监督学习在时间序列分析中的比较研究 representation learning MAE

🔬 支柱九:具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗
12 MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion 提出MoPE以解决多模态融合中的适应性与表达性不足问题 multimodal
13 Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity 提出检索增强的上下文学习以解决多模态学习中的缺失模态问题 multimodal
14 BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences 提出BurstAttention以解决长序列处理中的效率问题 large language model
15 Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference 提出Keyformer以解决KV缓存大小和内存带宽问题 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页