cs.LG（2024-01-17）
📊 共 9 篇论文
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (5)
支柱九：具身大模型 (Embodied Foundation Models) (3)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Bridging State and History Representations: Understanding Self-Predictive RL | 提出自预测抽象方法以提升强化学习表现 | reinforcement learning deep reinforcement learning representation learning | ||
| 2 | On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations | 提出数据增强策略以优化音乐音频表示的对比学习 | contrastive learning | ||
| 3 | Sharing Knowledge in Multi-Task Deep Reinforcement Learning | 提出多任务深度强化学习中的知识共享方法以提升性能 | reinforcement learning deep reinforcement learning | ||
| 4 | Functional Autoencoder for Smoothing and Representation Learning | 提出功能自编码器以解决功能数据平滑与表示学习问题 | representation learning | ||
| 5 | Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback | 提出离线策略价值排名算法以优化人类反馈的推荐系统 | 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 | Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer | 提出Fwd-Prompt以解决多模态持续指令调优中的负向迁移问题 | large language model multimodal | ||
| 7 | Code Simulation Challenges for Large Language Models | 提出链式模拟方法以提升大语言模型的代码模拟能力 | large language model | ||
| 8 | Herding LLaMaS: Using LLMs as an OS Module | 提出LLaMaS以简化新设备的操作系统集成 | large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search | 提出节奏翻译函数以提升音乐音频嵌入的检索效率 | manipulation |