cs.LG（2024-07-18）

📊 共 22 篇论文 | 🔗 4 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) (6 🔗2) 支柱八：物理动画 (Physics-based Animation) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 Random Latent Exploration for Deep Reinforcement Learning 提出随机潜在空间探索(RLE)算法，提升深度强化学习的探索效率。 reinforcement learning deep reinforcement learning ✅
2 Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning 提出两种目标对齐方法，解决深度强化学习中总回报与折扣回报差异问题 reinforcement learning deep reinforcement learning
3 Event-Triggered Reinforcement Learning Based Joint Resource Allocation for Ultra-Reliable Low-Latency V2X Communications 提出基于事件触发强化学习的联合资源分配方案，用于超可靠低延迟V2X通信。 reinforcement learning deep reinforcement learning DRL
4 Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review 综述：基于强化学习的扩散模型微调方法，优化生物序列生成任务 reinforcement learning PPO ✅
5 Model-based Policy Optimization using Symbolic World Model 提出基于符号世界模型的策略优化方法，提升机器人学习的样本效率 reinforcement learning world model
6 Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization 提出基于强化学习动态算法配置的实例选择方法，提升泛化性能 reinforcement learning deep reinforcement learning
7 Reconfigurable Intelligent Surface Aided Vehicular Edge Computing: Joint Phase-shift Optimization and Multi-User Power Allocation 提出基于RIS辅助的VEC系统，利用DRL优化相移和功率分配，提升车辆边缘计算性能。 reinforcement learning deep reinforcement learning DRL
8 A reinforcement learning strategy to automate and accelerate h/p-multigrid solvers 提出基于强化学习的h/p-多重网格求解器自动优化策略，提升求解效率与稳定性 reinforcement learning
9 Optimistic Q-learning for average reward and episodic reinforcement learning 提出乐观Q学习算法以解决平均奖励强化学习中的后悔最小化问题 reinforcement learning
10 Data-Driven Estimation of Conditional Expectations, Application to Optimal Stopping and Reinforcement Learning 提出一种纯数据驱动的条件期望估计方法，并应用于最优停止和强化学习。 reinforcement learning
11 HHGT: Hierarchical Heterogeneous Graph Transformer for Heterogeneous Graph Representation Learning 提出HHGT：一种用于异构图表示学习的分层异构图Transformer模型 representation learning
12 PG-Rainbow: Using Distributional Reinforcement Learning in Policy Gradient Methods PG-Rainbow：将分布强化学习融入策略梯度方法，提升Atari游戏性能 reinforcement learning

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

#题目一句话要点标签🔗⭐
13 NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals NNsight与NDIF： democratize 开放权重基础模型内部机制的研究 large language model foundation model
14 CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech CogniVoice：多模态多语种融合网络用于从语音中评估轻度认知障碍 multimodal
15 A Foundation Model for Soccer 提出足球领域的基础模型，用于预测足球比赛中的后续动作。 foundation model ✅
16 TrialEnroll: Predicting Clinical Trial Enrollment Success with Deep & Cross Network and Large Language Models TrialEnroll：利用深度交叉网络和LLM增强文本特征预测临床试验招募成功率 large language model
17 Reconstruct the Pruned Model without Any Retraining 提出LIAR框架以无须重训练重构剪枝模型 large language model
18 Integrated Hardware Architecture and Device Placement Search PHAZE：通过联合搜索硬件架构与设备放置策略优化分布式深度学习训练。 large language model ✅

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
19 A Survey on Differential Privacy for SpatioTemporal Data in Transportation Research 综述时空数据差分隐私在交通研究中的应用与挑战 spatiotemporal
20 Automated and Holistic Co-design of Neural Networks and ASICs for Enabling In-Pixel Intelligence 提出基于贝叶斯优化的神经网络与ASIC协同设计方法，实现像素内智能 PULSE

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 Deterministic Trajectory Optimization through Probabilistic Optimal Control 提出基于概率最优控制的确定性轨迹优化算法，提升数值稳定性和收敛速度 trajectory optimization

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

#题目一句话要点标签🔗⭐
22 Privacy-preserving gradient-based fair federated learning 提出一种基于同态加密的、保护隐私的梯度公平联邦学习方案 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页