cs.LG（2023-12-01）

📊 共 23 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) (14 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗⭐
1 Mamba: Linear-Time Sequence Modeling with Selective State Spaces 提出Mamba以解决Transformer在长序列建模中的效率问题 Mamba SSM state space model
2 Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting 提出空间-时间解耦的掩蔽预训练方法以解决时空预测问题 masked autoencoder MAE spatiotemporal ✅
3 Age-Based Scheduling for Mobile Edge Computing: A Deep Reinforcement Learning Approach 提出基于年龄调度的深度强化学习方法以优化移动边缘计算 reinforcement learning deep reinforcement learning
4 Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning 探索音频增强策略以提升自监督心音图分类模型的鲁棒性 representation learning contrastive learning
5 Tracking Object Positions in Reinforcement Learning: A Metric for Keypoint Detection (extended version) 提出一种轻量级指标以评估关键点检测在强化学习中的表现 reinforcement learning
6 Domain Adaptive Imitation Learning with Visual Observation 提出一种新框架以解决视觉观察下的领域自适应模仿学习问题 imitation learning
7 Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition 提出虚拟融合方法以解决单传感器活动识别问题 contrastive learning
8 Spectral Temporal Contrastive Learning 提出谱时序对比学习以提升无监督表示学习效果 contrastive learning
9 Extreme Event Prediction with Multi-agent Reinforcement Learning-based Parametrization of Atmospheric and Oceanic Turbulence 基于多智能体强化学习的气候极端事件预测方法 reinforcement learning
10 Safe Reinforcement Learning in Tensor Reproducing Kernel Hilbert Space 提出基于RKHS的安全强化学习方法以解决部分可观测环境中的安全问题 reinforcement learning
11 Optimal Sample Complexity of Contrastive Learning 提出对比学习的最优样本复杂度界限以提升泛化能力 contrastive learning
12 Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk 提出基于信任区域条件风险的高效离线安全强化学习方法 reinforcement learning
13 Hypergraph Node Representation Learning with One-Stage Message Passing 提出一种单阶段消息传递方法以提升超图节点表示学习 representation learning
14 GFN-SR: Symbolic Regression with Generative Flow Networks 提出GFN-SR以解决符号回归中的复杂组合搜索问题 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
15 Exploring the Robustness of Decentralized Training for Large Language Models 探讨去中心化训练在大语言模型中的鲁棒性问题 large language model foundation model
16 Understanding Unimodal Bias in Multimodal Deep Linear Networks 提出多模态深度线性网络中的单模态偏差理论以优化联合训练 multimodal ✅
17 Latent Space Explorer: Visual Analytics for Multimodal Latent Space Exploration 提出Latent Space Explorer以解决多模态表示模型探索难题 multimodal
18 LinguaLinked: A Distributed Large Language Model Inference System for Mobile Devices 提出LinguaLinked以解决移动设备上大语言模型推理的挑战 large language model
19 Nonparametric Variational Regularisation of Pretrained Transformers 提出非参数变分正则化以解决预训练变换器的过拟合问题 large language model
20 Pathway to a fully data-driven geotechnics: lessons from materials informatics 提出数据驱动的土木工程方法以应对土壤复杂性挑战 large language model
21 A Bayesian approach for prompt optimization in pre-trained language models 提出贝叶斯优化方法以解决预训练语言模型的提示优化问题 large language model
22 PEFTDebias : Capturing debiasing information using PEFTs 提出PEFTDebias以解决基础模型中的隐性偏见问题 foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
23 Spatiotemporal Transformer for Imputing Sparse Data: A Deep Learning Approach 提出时空变换器以解决稀疏数据插补问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页