cs.LG（2024-12-01）
📊 共 3 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation | DFRot：通过精炼旋转实现旋转LLM的无异常值和无大规模激活 | large language model | ||
| 2 | ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning | 提出ROSE，一种面向奖励的LLM指令调优数据选择框架，提升任务特定性能。 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 3 | Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning | 提出SUBSAMPLE-MFQ以解决多智能体强化学习中的决策效率问题 | reinforcement learning |