cs.LG（2024-01-30）

📊 共 18 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱八：物理动画 (Physics-based Animation) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Arrows of Time for Large Language Models 提出时间方向性分析以揭示大语言模型的学习不对称性 large language model
2 Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models 提出Diff-eRank以评估大型语言模型的有效性 large language model ✅
3 Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection 提出MFedMC以解决多模态联邦学习中的通信效率问题 multimodal
4 Reproducibility, energy efficiency and performance of pseudorandom number generators in machine learning: a comparative study of python, numpy, tensorflow, and pytorch implementations 比较Python、NumPy、TensorFlow和PyTorch中的伪随机数生成器性能与能效 large language model
5 Adapting Amidst Degradation: Cross Domain Li-ion Battery Health Estimation via Physics-Guided Test-Time Training 提出BatteryTTT框架以解决锂离子电池健康估计中的数据稀缺问题 large language model
6 PBSCR: The Piano Bootleg Score Composer Recognition Dataset 提出PBSCR数据集以促进古典钢琴作曲家识别研究 multimodal
7 Leveraging Nested MLMC for Sequential Neural Posterior Estimation with Intractable Likelihoods 提出基于嵌套多级Monte Carlo的序列神经后验估计方法 multimodal
8 SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget 提出SwapNet以解决边缘AI设备内存预算不足问题 large language model
9 T3: Transparent Tracking & Triggering for Fine-grained Overlap of Compute & Collectives 提出T3以解决大语言模型通信效率低下问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
10 Augmenting Replay in World Models for Continual Reinforcement Learning 提出WMAR以解决持续强化学习中的遗忘问题 reinforcement learning world model world models
11 Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble 提出奖励模型集成方法以提升人类反馈强化学习的准确性 reinforcement learning RLHF large language model
12 Zero-Shot Reinforcement Learning via Function Encoders 提出函数编码器以解决零-shot强化学习转移问题 reinforcement learning representation learning zero-shot transfer
13 Extrinsicaly Rewarded Soft Q Imitation Learning with Discriminator 提出DSQIL以解决模仿学习中的分布偏移问题 reinforcement learning imitation learning inverse reinforcement learning
14 CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning 提出CORE以实现可扩展高效的因果发现 reinforcement learning deep reinforcement learning ✅
15 Multi-modal Representation Learning for Cross-modal Prediction of Continuous Weather Patterns from Discrete Low-Dimensional Data 提出深度学习方法以解决风能数据预测中的多模态问题 representation learning
16 Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning 提出基于对比学习的框架以应对深度神经网络故障注入攻击 contrastive learning

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

#题目一句话要点标签🔗⭐
17 Traffic estimation in unobserved network locations using data-driven macroscopic models 提出MaTE模型以解决交通流量估计问题 spatiotemporal
18 Online Algorithm for Node Feature Forecasting in Temporal Graphs 提出在线算法mspace以解决时序图节点特征预测问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页