cs.LG（2024-08-07）

📊 共 13 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) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 PowerPM: Foundation Model for Power Systems 提出PowerPM电力系统基础模型，解决电力时间序列数据通用表示学习难题。 contrastive learning foundation model
2 RL-ADN: A High-Performance Deep Reinforcement Learning Environment for Optimal Energy Storage Systems Dispatch in Active Distribution Networks RL-ADN：用于主动配电网中储能系统优化调度的强化学习环境 reinforcement learning deep reinforcement learning DRL ✅
3 PackMamba: Efficient Processing of Variable-Length Sequences in Mamba training PackMamba：高效处理Mamba训练中变长序列，显著提升吞吐量。 Mamba SSM large language model
4 Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives 提出一种免学习率强化学习框架，通过模型选择应对非平稳目标问题。 reinforcement learning
5 Knowledge Probing for Graph Representation Learning 提出GraphProbe图探针框架，用于评估图表示学习方法对图知识的编码能力 representation learning
6 UpLIF: An Updatable Self-Tuning Learned Index Framework 提出UpLIF：一种可更新的自适应学习索引框架，提升更新效率和降低内存占用。 reinforcement learning predictive model
7 Reliable Node Similarity Matrix Guided Contrastive Graph Clustering 提出NS4GC框架，通过可靠节点相似度矩阵指导对比图聚类 representation learning contrastive learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
8 Multimodal Gender Fairness in Depression Prediction: Insights on Data from the USA & China 针对抑郁症预测中多模态性别公平性问题，提出美国和中国数据集的对比分析。 multimodal
9 A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models 提出FISTAPruner以解决大语言模型剪枝效率低下问题 large language model
10 In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models In2Core：利用影响函数进行大语言模型指令微调中的核心集选择 large language model
11 VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs VulScribeR：探索基于RAG的LLM漏洞增强方法，提升漏洞检测器性能 large language model
12 Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learning 提出基于变异理论的反事实数据增强主动学习方法，提升数据效率 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Scaling Law of Sim2Real Transfer Learning in Expanding Computational Materials Databases for Real-World Predictions 揭示Sim2Real迁移学习在计算材料数据库中的扩展规律，提升真实世界预测性能。 sim2real

⬅️ 返回 cs.LG 首页 · 🏠 返回主页