cs.LG(2024-09-28)

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (5 🔗2) 支柱九:具身大模型 (Embodied Foundation Models) (4) 支柱五:交互与反应 (Interaction & Reaction) (1) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗
1 Energy-Efficient Computation with DVFS using Deep Reinforcement Learning for Multi-Task Systems in Edge Computing 提出基于深度强化学习的DVFS方法,解决边缘计算多任务系统能耗优化问题 reinforcement learning deep reinforcement learning
2 HybridFlow: A Flexible and Efficient RLHF Framework HybridFlow:一种灵活高效的RLHF框架,提升分布式训练效率。 reinforcement learning RLHF large language model
3 Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization 提出CP3ER,通过优先近端经验正则化泛化一致性策略到视觉强化学习 reinforcement learning consistency policy
4 Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training 提出MAST框架,通过动态稀疏训练提升多智能体强化学习效率并压缩模型。 reinforcement learning
5 Double Actor-Critic with TD Error-Driven Regularization in Reinforcement Learning 提出基于TD误差驱动正则化的双重Actor-Critic算法,提升强化学习值估计。 reinforcement learning

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

#题目一句话要点标签🔗
6 Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures 提出基于分布差异最小化的非配对多模态混合数据共享成分分析方法 multimodal
7 DelayPTC-LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Models 提出DelayPTC-LLM,利用大语言模型预测地铁延误下的乘客出行选择 large language model
8 On the universality of neural encodings in CNNs 研究CNN中神经编码的通用性,揭示自然图像的通用神经编码 foundation model
9 DOTA: Distributional Test-Time Adaptation of Vision-Language Models 提出DOTA:一种视觉-语言模型的分布测试时自适应方法,缓解灾难性遗忘。 foundation model

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

#题目一句话要点标签🔗
10 Quantum delegated and federated learning via quantum homomorphic encryption 提出基于量子同态加密的量子委托和联邦学习框架,保障数据隐私。 OMOMO

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
11 Machine Learning Operations: A Mapping Study 针对MLOps挑战,本文通过系统性映射研究提供实用工具与解决方案建议 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页