cs.LG（2024-07-11）

📊 共 14 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (8) 支柱一：机器人控制 (Robot Control) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3)

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

#题目一句话要点标签🔗⭐
1 RoboMorph: Evolving Robot Morphology using Large Language Models RoboMorph：利用大语言模型进化机器人形态 reinforcement learning large language model
2 Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computing 提出基于分布式深度强化学习的梯度量化方案以优化联邦学习中的训练时间 reinforcement learning deep reinforcement learning DRL
3 Joint Optimization of Age of Information and Energy Consumption in NR-V2X System based on Deep Reinforcement Learning 提出基于深度强化学习的NR-V2X系统AoI与能耗联合优化方法 reinforcement learning deep reinforcement learning DRL
4 Parallelizing Autoregressive Generation with Variational State Space Models 提出基于变分状态空间模型的并行自回归生成方法，加速序列生成任务。 Mamba SSM state space model
5 SLRL: Structured Latent Representation Learning for Multi-view Clustering 提出SLRL框架以解决多视角聚类中的结构信息缺失问题 representation learning
6 Gradient Boosting Reinforcement Learning 提出梯度提升强化学习（GBRL）框架，提升结构化特征场景下的强化学习性能。 reinforcement learning
7 Enhancing Performance and User Engagement in Everyday Stress Monitoring: A Context-Aware Active Reinforcement Learning Approach 提出上下文感知主动强化学习，提升日常压力监测性能与用户体验 reinforcement learning
8 Dynamic Co-Optimization Compiler: Leveraging Multi-Agent Reinforcement Learning for Enhanced DNN Accelerator Performance 提出DCOC：利用多智能体强化学习优化DNN加速器性能 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
9 TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations 提出基于时序距离感知的无监督目标条件强化学习方法TLDR locomotion reinforcement learning
10 Improve Load Forecasting in Energy Communities through Transfer Learning using Open-Access Synthetic Profiles 利用开放合成数据和迁移学习提升能源社区负荷预测精度 model predictive control
11 An Unsupervised Domain Adaptation Method for Locating Manipulated Region in partially fake Audio 提出SDE方法，利用专家混合模型解决部分伪造音频跨域篡改定位问题。 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
12 Mitigating Catastrophic Forgetting in Language Transfer via Model Merging 提出Branch-and-Merge方法，缓解LLM语言迁移中的灾难性遗忘 large language model
13 FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision FlashAttention-3：通过异步和低精度加速Transformer Attention计算。 large language model
14 Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients 提出Q-GaLore，结合量化与低秩投影，显著降低LLM训练的内存占用。 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页