cs.LG（2024-04-11）

📊 共 18 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) (8) 支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱八：物理动画 (Physics-based Animation) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 Offline Reinforcement Learning with Domain-Unlabeled Data 提出PUORL以解决离线强化学习中的领域未标记数据问题 reinforcement learning offline RL offline reinforcement learning
2 On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning 提出潜在基于奖励塑形以解决强化学习样本效率问题 reinforcement learning reward shaping
3 Predictive Modelling of Air Quality Index (AQI) Across Diverse Cities and States of India using Machine Learning: Investigating the Influence of Punjab's Stubble Burning on AQI Variability 基于机器学习的空气质量指数预测模型，探讨稻草焚烧对AQI的影响 predictive model MAE
4 Can Contrastive Learning Refine Embeddings 提出SIMSKIP以优化下游任务的嵌入表示 representation learning contrastive learning
5 Quantum Reinforcement Learning in Non-Abelian Environments: Unveiling Novel Formulations and Quantum Advantage Exploration 提出量子强化学习新框架以应对非阿贝尔环境挑战 reinforcement learning
6 Differentially Private Reinforcement Learning with Self-Play 提出差分隐私强化学习算法以解决多智能体隐私保护问题 reinforcement learning
7 Representation Learning of Tangled Key-Value Sequence Data for Early Classification 提出KVEC方法以解决复杂键值序列的早期分类问题 representation learning
8 Diffusion posterior sampling for simulation-based inference in tall data settings 提出新算法以加速长数据设置下的后验采样 world model world models

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
9 CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes 提出CEM方法以解决大语言模型持续学习中的数据效率问题 large language model
10 A Multi-Expert Large Language Model Architecture for Verilog Code Generation 提出多专家大语言模型架构以提升Verilog代码生成质量 large language model
11 The OxMat dataset: a multimodal resource for the development of AI-driven technologies in maternal and newborn child health 提出OxMat数据集以解决母婴健康数据不足问题 multimodal
12 Data-Driven Portfolio Management for Motion Pictures Industry: A New Data-Driven Optimization Methodology Using a Large Language Model as the Expert 提出基于大语言模型的电影行业数据驱动投资组合管理方法 large language model
13 Sketch-Plan-Generalize: Learning and Planning with Neuro-Symbolic Programmatic Representations for Inductive Spatial Concepts 提出神经符号程序表示方法以解决人机协作中的概念学习问题 large language model instruction following
14 Streaming detection of significant delay changes in public transport systems 提出实时检测公共交通系统显著延误变化的方法 multimodal

🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)

#题目一句话要点标签🔗⭐
15 Differentiable All-pole Filters for Time-varying Audio Systems 提出可微分全极点滤波器以解决音频系统训练问题 PULSE ✅
16 A Parsimonious Setup for Streamflow Forecasting using CNN-LSTM 提出CNN-LSTM模型以提升流量预测精度 spatiotemporal
17 Inferring Change Points in High-Dimensional Regression via Approximate Message Passing 提出近似消息传递算法以定位高维回归中的变更点 AMP

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
18 Mitigating Vulnerable Road Users Occlusion Risk Via Collective Perception: An Empirical Analysis 提出一种新算法以降低脆弱道路用户的遮挡风险 penetration

⬅️ 返回 cs.LG 首页 · 🏠 返回主页