cs.LG（2024-01-16）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱八：物理动画 (Physics-based Animation) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Solving Continual Offline Reinforcement Learning with Decision Transformer 提出多头决策变换器以解决持续离线强化学习中的遗忘问题 reinforcement learning offline RL offline reinforcement learning
2 CNN-DRL with Shuffled Features in Finance 提出CNN-DRL与特征重排结合以提升金融数据奖励 reinforcement learning deep reinforcement learning DRL
3 QoS Improvement in Multi User Cellular-Symbiotic Radio Network Assisted by Active-STAR-RIS 提出主动STAR-RIS以提升多用户蜂窝网络的服务质量 reinforcement learning deep reinforcement learning DRL
4 MambaTab: A Plug-and-Play Model for Learning Tabular Data 提出MambaTab以解决表格数据学习的高效性问题 Mamba SSM
5 Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information 提出最大条件互信息法以改进知识蒸馏中的贝叶斯条件分布估计 distillation ✅
6 Generative AI for O-RAN Slicing: A Semi-Supervised Approach with VAE and Contrastive Learning 提出生成式AI驱动的半监督学习架构以优化O-RAN切片资源分配 contrastive learning
7 Learning from Sparse Offline Datasets via Conservative Density Estimation 提出保守密度估计以解决离线强化学习中的外推误差问题 reinforcement learning offline RL offline reinforcement learning
8 Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning 提出多背景表示学习以增强粒子物理异常检测 representation learning
9 DiConStruct: Causal Concept-based Explanations through Black-Box Distillation 提出DiConStruct以解决模型可解释性与预测性能的矛盾问题 distillation

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

#题目一句话要点标签🔗⭐
10 A Survey of Resource-efficient LLM and Multimodal Foundation Models 综述资源高效的LLM与多模态基础模型以应对硬件资源挑战 large language model foundation model multimodal
11 AiGen-FoodReview: A Multimodal Dataset of Machine-Generated Restaurant Reviews and Images on Social Media 提出AiGen-FoodReview数据集以解决餐厅评论的真实性问题 large language model multimodal
12 Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference 提出ExFlow以加速混合专家模型推理 large language model
13 LoMA: Lossless Compressed Memory Attention 提出LoMA以解决长上下文处理中的内存与计算资源问题 large language model

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

#题目一句话要点标签🔗⭐
14 Robust Localization of Key Fob Using Channel Impulse Response of Ultra Wide Band Sensors for Keyless Entry Systems 提出基于UWB传感器的多头自监督神经网络以增强钥匙扣定位鲁棒性 PULSE
15 Binaural Angular Separation Network 提出双耳角度分离网络以解决语音源分离问题 PULSE

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes 提出REValueD以解决高维离散动作空间中的目标方差问题 humanoid reinforcement learning

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

#题目一句话要点标签🔗⭐
17 Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness 提出同态表达能力框架以提升GNN的表达性评估 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页