cs.LG（2024-05-01）
📊 共 4 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) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning | 结合监督学习与强化学习，提升WebAI在MiniWoB上的网页导航能力 | reinforcement learning large language model multimodal | ||
| 2 | Self-Play Preference Optimization for Language Model Alignment | 提出基于自博弈偏好优化的语言模型对齐方法SPPO，提升模型性能。 | reinforcement learning RLHF DPO | ✅ | |
| 3 | MetaRM: Shifted Distributions Alignment via Meta-Learning | MetaRM：通过元学习对齐奖励模型与漂移分布，提升RLHF性能 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | RAG-based Explainable Prediction of Road Users Behaviors for Automated Driving using Knowledge Graphs and Large Language Models | 提出基于RAG的知识图谱与大语言模型融合方法，用于自动驾驶中道路使用者行为的可解释预测。 | large language model |