cs.LG（2025-01-03）
📊 共 9 篇论文
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (4)
支柱九：具身大模型 (Embodied Foundation Models) (3)
支柱八：物理动画 (Physics-based Animation) (2)
🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures | 研究离线与低自适应强化学习的统计复杂性，为实际应用提供理论基础。 | reinforcement learning policy learning offline RL | ||
| 2 | Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning | 提出基于静态谱风险度量的DRL算法，提升风险敏感决策能力 | reinforcement learning DRL | ||
| 3 | Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning | pFedSeq：利用历史序列更新，实现个性化联邦Adapter调优 | SSM state space model foundation model | ||
| 4 | Inversely Learning Transferable Rewards via Abstracted States | 提出一种方法以通过抽象状态反向学习可转移奖励 | reinforcement learning inverse reinforcement learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Creating Artificial Students that Never Existed: Leveraging Large Language Models and CTGANs for Synthetic Data Generation | 利用LLM和CTGAN生成合成学生数据，解决学习分析中的数据隐私问题 | large language model | ||
| 6 | Social Processes: Probabilistic Meta-learning for Adaptive Multiparty Interaction Forecasting | 提出基于概率元学习的Social Process模型，用于自适应多人交互预测。 | multimodal | ||
| 7 | SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation | SaLoRA：提出安全对齐保持的低秩适应方法，提升LLM微调安全性。 | large language model |
🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Architecture for Trajectory-Based Fishing Ship Classification with AIS Data | 提出基于AIS轨迹数据的渔船分类架构，解决现实世界数据噪声和不平衡问题 | spatiotemporal | ||
| 9 | Custom Loss Functions in Fuel Moisture Modeling | 针对野火蔓延预测，提出基于定制损失函数的燃料湿度机器学习模型 | spatiotemporal |