cs.LG（2024-04-30）
📊 共 9 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) (5 🔗1)
支柱九：具身大模型 (Embodied Foundation Models) (3)
支柱七：动作重定向 (Motion Retargeting) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric | 提出加权点集嵌入以优化多模态对比学习相似度度量 | contrastive learning multimodal | ||
| 2 | Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning | 提出基于不确定性的MTDS方法以解决离线强化学习中的数据共享问题 | reinforcement learning offline RL offline reinforcement learning | ✅ | |
| 3 | Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning | 提出子最优数据预训练方法以提升人机协作强化学习效率 | reinforcement learning | ||
| 4 | A Survey of Imitation Learning Methods, Environments and Metrics | 系统性回顾模仿学习方法与标准化问题 | imitation learning | ||
| 5 | Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning | 提出信息导向采样算法以解决多智能体强化学习问题 | reinforcement learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Soft Preference Optimization: Aligning Language Models to Expert Distributions | 提出软偏好优化方法以对齐语言模型与人类偏好 | large language model | ||
| 7 | On Training a Neural Network to Explain Binaries | 提出深度神经网络以解释二进制代码功能 | large language model | ||
| 8 | More Compute Is What You Need | 提出新的缩放法则以优化大语言模型的计算资源分配 | large language model |
🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | MAP-Former: Multi-Agent-Pair Gaussian Joint Prediction | 提出MAP-Former以解决多智能体轨迹风险评估问题 | motion prediction |