cs.LG（2024-04-23）
📊 共 15 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (7 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (7 🔗1)
支柱三：空间感知与语义 (Perception & Semantics) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | NExT: Teaching Large Language Models to Reason about Code Execution | 提出NExT以解决大型语言模型对代码执行理解不足的问题 | large language model chain-of-thought | ||
| 2 | $\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning | 提出MiniMol以解决分子学习中的数据稀缺问题 | foundation model | ||
| 3 | Graph Machine Learning in the Era of Large Language Models (LLMs) | 探讨大语言模型时代图机器学习的进展与应用 | large language model | ||
| 4 | Advances and Open Challenges in Federated Foundation Models | 提出联邦基础模型以解决隐私和计算效率问题 | foundation model | ||
| 5 | FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model | 提出FMint以解决动态系统快速仿真问题 | foundation model | ✅ | |
| 6 | Rethinking LLM Memorization through the Lens of Adversarial Compression | 提出对抗压缩比以评估大语言模型的记忆能力 | large language model | ||
| 7 | Uncertainty Quantification on Graph Learning: A Survey | 系统评估图模型的不确定性量化技术 | foundation model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Compete and Compose: Learning Independent Mechanisms for Modular World Models | 提出COMET以解决模块化世界模型的知识重用问题 | world model world models | ||
| 9 | SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting | 提出SST模型以解决时间序列预测中的信息损失问题 | Mamba SSM state space model | ✅ | |
| 10 | Private Optimal Inventory Policy Learning for Feature-based Newsvendor with Unknown Demand | 提出隐私保护的最优库存策略学习以解决需求未知问题 | policy learning | ||
| 11 | The Power of Resets in Online Reinforcement Learning | 提出局部模拟器访问以解决高维强化学习中的样本效率问题 | reinforcement learning | ||
| 12 | Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems | 提出自适应正则化强化学习以确保关键系统的安全控制 | reinforcement learning | ||
| 13 | Graph Neural Networks and Reinforcement Learning for Proactive Application Image Placement | 提出图神经网络与强化学习结合的主动应用图像放置方法 | reinforcement learning | ||
| 14 | MultiSTOP: Solving Functional Equations with Reinforcement Learning | 提出MultiSTOP框架以解决物理中的函数方程问题 | reinforcement learning |
🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 15 | Deep-learning Optical Flow Outperforms PIV in Obtaining Velocity Fields from Active Nematics | 提出深度学习光流法以解决活性向列体速度场测量问题 | optical flow |