cs.LG(2025-10-17)

📊 共 7 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) (4 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (1) 支柱四:生成式动作 (Generative Motion) (1) 支柱八:物理动画 (Physics-based Animation) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗
1 Towards Robust Zero-Shot Reinforcement Learning 提出BREEZE,增强零样本强化学习的鲁棒性和泛化能力 reinforcement learning policy learning representation learning
2 WEBSERV: A Browser-Server Environment for Efficient Training of Reinforcement Learning-based Web Agents at Scale 提出WEBSERV以解决大规模强化学习网页代理训练效率问题 reinforcement learning
3 Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics 提出探索-再承诺算法以解决非平稳线性乐队问题 latent dynamics
4 Alignment is Localized: A Causal Probe into Preference Layers 通过因果探针揭示偏好层局部对齐现象,优化语言模型。 reinforcement learning RLHF

🔬 支柱九:具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗
5 DRO-InstructZero: Distributionally Robust Prompt Optimization for Large Language Models DRO-InstructZero:面向大语言模型的分布鲁棒提示优化方法 large language model

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
6 Learning a Generalized Model for Substation Level Voltage Estimation in Distribution Networks 提出一种分层图神经网络,用于配电网中变电站级电压估计,提升精度和可扩展性。 penetration

🔬 支柱八:物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗
7 Singularity-free dynamical invariants-based quantum control 提出一种基于无奇异动态不变量的量子控制方法,用于提升噪声环境下的量子态制备。 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页