cs.LG（2024-11-11）

📊 共 23 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) (12 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
1 Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching 提出基于后继特征匹配的非对抗逆强化学习方法，提升控制任务性能。 reinforcement learning behavior cloning inverse reinforcement learning
2 Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC 提出Streetwise方法，增强离线RL策略在实时通信中应对随机扰动的鲁棒性 reinforcement learning offline RL offline reinforcement learning
3 Variational Graph Contrastive Learning 提出SGEC方法，通过子图高斯嵌入对比学习提升图表示。 representation learning contrastive learning
4 Probabilistic Forecasting of Radiation Exposure for Spaceflight 提出一种基于多模态时间序列数据的机器学习方法，用于空间辐射暴露的概率预测。 predictive model multimodal
5 Fast and Robust Contextual Node Representation Learning over Dynamic Graphs 提出基于稀疏节点注意力的动态图节点表示学习方法 representation learning
6 HeteroSample: Meta-path Guided Sampling for Heterogeneous Graph Representation Learning HeteroSample：面向异构图表示学习的元路径引导采样方法，提升物联网场景图分析效率。 representation learning
7 Leveraging LSTM for Predictive Modeling of Satellite Clock Bias 利用LSTM预测卫星钟差，显著提升卫星导航系统精度和低功耗设备性能。 predictive model
8 Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration 提出Wasserstein质量多样性模仿学习，解决从有限演示中学习多样化行为的问题 imitation learning
9 SPARTAN: A Sparse Transformer World Model Attending to What Matters SPARTAN：一种稀疏Transformer世界模型，关注关键交互 world model
10 Finding "Good Views" of Electrocardiogram Signals for Inferring Abnormalities in Cardiac Condition 探索心电图信号的“良好视角”，用于推断心脏状况异常 contrastive learning spatiotemporal ✅
11 Joint Age-State Belief is All You Need: Minimizing AoII via Pull-Based Remote Estimation 提出基于联合年龄-状态置信度的拉取式远程估计方法，最小化AoII reinforcement learning deep reinforcement learning
12 An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning 提出Mecoin，一种高效的图少样本类增量学习内存模块，解决灾难性遗忘问题。 representation learning distillation ✅

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

#题目一句话要点标签🔗⭐
13 Balancing Multimodal Training Through Game-Theoretic Regularization 提出多模态竞争正则化器(MCR)，解决多模态学习中的模态竞争问题。 multimodal ✅
14 Large Language Models for Constructing and Optimizing Machine Learning Workflows: A Survey 综述：利用大型语言模型构建和优化机器学习工作流 large language model
15 General Geospatial Inference with a Population Dynamics Foundation Model 提出人口动态基础模型(PDFM)，用于通用地理空间推理，实现多领域任务的卓越性能。 foundation model
16 Large Language Model in Medical Informatics: Direct Classification and Enhanced Text Representations for Automatic ICD Coding 利用大型语言模型进行ICD编码，提升医疗文本分类精度 large language model
17 Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models 提出SPA框架，利用合成数据提升大模型生成结果的多样性 foundation model
18 WDMoE: Wireless Distributed Mixture of Experts for Large Language Models 提出无线分布式MoE架构WDMoE，优化无线网络中LLM的协同部署。 large language model
19 Warmstarting for Scaling Language Models 提出基于μTransfer的Warmstarting方法，加速大规模语言模型训练并保持其稳定性。 large language model zero-shot transfer
20 Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks 对比自底向上和自顶向下引导方法在上下文学习任务中的有效性 large language model
21 Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data 基于低维数据，用统计与逼近理论理解Transformer的Scaling Laws large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
22 GSL-PCD: Improving Generalist-Specialist Learning with Point Cloud Feature-based Task Partitioning GSL-PCD：基于点云特征的任务划分提升通用-专家强化学习 manipulation reinforcement learning deep reinforcement learning
23 Computable Model-Independent Bounds for Adversarial Quantum Machine Learning 针对量子对抗机器学习，提出可计算的模型无关对抗误差下界 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页