cs.LG（2024-01-08）

📊 共 20 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) (14 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1 🔗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 MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts 提出MoE-Mamba以提升状态空间模型的效率与性能 Mamba SSM state space model
2 Learn Once Plan Arbitrarily (LOPA): Attention-Enhanced Deep Reinforcement Learning Method for Global Path Planning 提出LOPA以解决深度强化学习在全局路径规划中的收敛与泛化问题 reinforcement learning deep reinforcement learning DRL
3 Deep Reinforcement Learning for Multi-Truck Vehicle Routing Problems with Multi-Leg Demand Routes 提出深度强化学习方法以解决多卡车车辆路径问题 reinforcement learning deep reinforcement learning
4 Inverse Reinforcement Learning with Sub-optimal Experts 提出逆强化学习方法以处理次优专家行为分析问题 reinforcement learning inverse reinforcement learning
5 Long-term Safe Reinforcement Learning with Binary Feedback 提出LoBiSaRL以解决安全强化学习中的反馈问题 reinforcement learning
6 Unifying Graph Contrastive Learning via Graph Message Augmentation 提出图消息增强方法以统一图对比学习 contrastive learning
7 Attention versus Contrastive Learning of Tabular Data -- A Data-centric Benchmarking 提出数据中心基准以评估表格数据的注意力与对比学习 contrastive learning
8 Dense Hopfield Networks in the Teacher-Student Setting 提出密集霍普菲尔德网络以解决无监督学习中的模式检索问题 teacher-student
9 A Minimaximalist Approach to Reinforcement Learning from Human Feedback 提出自我博弈偏好优化算法以提升人类反馈强化学习效率 reinforcement learning
10 A Tensor Network Implementation of Multi Agent Reinforcement Learning 提出张量网络方法以解决多智能体强化学习中的维度诅咒问题 reinforcement learning
11 Adaptive Experimental Design for Policy Learning 提出自适应实验设计以解决上下文最佳臂识别问题 policy learning
12 Universal Time-Series Representation Learning: A Survey 提出通用时间序列表示学习的分类方法以提升分析效果 representation learning ✅
13 Logits Poisoning Attack in Federated Distillation 提出FDLA以解决联邦蒸馏中的中毒攻击问题 distillation
14 Behavioural Cloning in VizDoom 提出模仿学习方法以提升Doom 2游戏中的AI人类行为表现 reinforcement learning imitation learning

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

#题目一句话要点标签🔗⭐
15 Deep Learning in Physical Layer: Review on Data Driven End-to-End Communication Systems and their Enabling Semantic Applications 综述数据驱动的物理层以优化端到端通信系统 multimodal
16 Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series 提出Tiny Time Mixers以解决多变量时间序列预测中的性能瓶颈问题 large language model ✅
17 Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning 提出Chain of LoRA以解决低秩适应方法的泛化不足问题 large language model
18 Evaluating Brain-Inspired Modular Training in Automated Circuit Discovery for Mechanistic Interpretability 提出脑启发模块化训练以提升神经网络的可解释性 large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
19 Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training 提出低秩训练框架以解决联邦推荐系统的通信与安全问题 OMOMO ✅

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

#题目一句话要点标签🔗⭐
20 A non-asymptotic distributional theory of approximate message passing for sparse and robust regression 提出非渐近分布理论以改进稀疏与稳健回归的近似消息传递算法 AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页