cs.LG（2025-07-19）

📊 共 14 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) (9 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Kernel Based Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games 提出基于核函数的最大熵逆强化学习方法，用于求解平均场博弈中的奖励函数。 reinforcement learning inverse reinforcement learning
2 Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning 通过策略多样性学习技能，实现强化学习中可辨识的表征 reinforcement learning representation learning
3 Generative Distribution Distillation 提出生成式分布蒸馏框架GenDD，实现高效的知识蒸馏与图像分类。 distillation
4 Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning 提出约束理性激活函数，平衡强化学习中的表达性和鲁棒性。 reinforcement learning ✅
5 GCC-Spam: Spam Detection via GAN, Contrastive Learning, and Character Similarity Networks 提出GCC-Spam框架，通过GAN、对比学习和字符相似网络增强垃圾文本检测。 contrastive learning
6 Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective 提出AD-GCL以解决图对比学习在异常检测中的结构不平衡问题 contrastive learning
7 Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence 提出基于通信的多智能体强化学习网络防御方法，提升协同防御能力 reinforcement learning
8 SDSC:A Structure-Aware Metric for Semantic Signal Representation Learning 提出SDSC：一种结构感知的时序信号自监督表征学习度量 representation learning
9 Federated Reinforcement Learning in Heterogeneous Environments 提出FedRQ算法，解决环境异构下的联邦强化学习鲁棒性问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
10 GRID: Scalable Task-Agnostic Prompt-Based Continual Learning for Language Models GRID：面向语言模型的可扩展、任务无关的Prompt持续学习框架 large language model
11 LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4 LeanTree：利用因子化状态加速Lean 4中的白盒证明搜索 large language model
12 Exploring the Dynamic Scheduling Space of Real-Time Generative AI Applications on Emerging Heterogeneous Systems 针对异构系统上实时生成式AI应用，探索动态调度策略以优化性能。 large language model
13 Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches 综述性论文：利用生成式AI赋能卫星增强的低空经济与地面网络中的智能体 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Applications and Manipulations of Physics-Informed Neural Networks in Solving Differential Equations 利用物理信息神经网络求解微分方程及其参数优化问题 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页