cs.LG（2025-03-11）
📊 共 6 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Robust Multi-Objective Controlled Decoding of Large Language Models | 提出鲁棒多目标控制解码以解决大语言模型对人类偏好的对齐问题 | large language model instruction following | ||
| 2 | Interpreting the Repeated Token Phenomenon in Large Language Models | 揭示大语言模型重复Token现象：通过干预Attention Sinks提升模型可靠性 | large language model | ||
| 3 | Adapting Large Language Models for Parameter-Efficient Log Anomaly Detection | 利用参数高效微调方法，将大型语言模型应用于日志异常检测 | large language model | ✅ |
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Meta-Reinforcement Learning with Discrete World Models for Adaptive Load Balancing | 提出基于离散世界模型的元强化学习方法，自适应优化操作系统负载均衡。 | reinforcement learning world model dreamer | ||
| 5 | V-Max: A Reinforcement Learning Framework for Autonomous Driving | V-Max：用于自动驾驶的强化学习开源框架，加速策略研究 | reinforcement learning imitation learning | ||
| 6 | Zero-Shot Action Generalization with Limited Observations | 提出AGLO框架，利用有限观测实现零样本动作泛化 | reinforcement learning policy learning representation learning |