cs.LG（2025-05-22）
📊 共 4 篇论文
🎯 兴趣领域导航
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Interactive Post-Training for Vision-Language-Action Models | 提出RIPT-VLA，通过交互式后训练提升视觉-语言-动作模型的性能。 | reinforcement learning vision-language-action VLA | ||
| 2 | Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies | 提出OGSRL以解决医疗强化学习中的安全性与有效性问题 | reinforcement learning offline RL offline reinforcement learning | ||
| 3 | Efficient Online RL Fine Tuning with Offline Pre-trained Policy Only | 提出PORL，仅用离线预训练策略高效微调在线强化学习，无需Q函数。 | reinforcement learning offline RL imitation learning |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach | 提出FedSA：一种基于滑模控制的联邦学习可控投毒攻击方法 | manipulation |