cs.LG（2024-07-24）

📊 共 15 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 A Large Encoder-Decoder Family of Foundation Models For Chemical Language 提出基于大规模Encoder-Decoder的化学语言基础模型，提升化学性质预测性能。 foundation model
2 Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? 研究水印技术对大语言模型版权保护和训练数据隐私的影响 large language model
3 Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference 针对后验模型解释，提出基于成员推理的数据隐私风险揭示与缓解方法 foundation model
4 BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning BLAZE：通过动态分块和难例学习实现跨语言和跨项目的缺陷定位 large language model
5 Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans 提出基于注意力机制神经网络的认知模型，用于模拟人类动态决策过程中的异质性。 large language model
6 Scalify: scale propagation for efficient low-precision LLM training Scalify：面向低精度LLM训练的规模传播方法，提升计算效率 large language model ✅
7 COEFF-KANs: A Paradigm to Address the Electrolyte Field with KANs COEFF-KANs：利用KANs预测电解液的库仑效率，加速锂金属电池设计 multimodal
8 Time Series Imputation with Multivariate Radial Basis Function Neural Network 提出基于多元径向基函数神经网络的时间序列缺失值填充方法 TAMP
9 Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks 提出Wonderful Matrices，一种更高效的语言建模架构，提升复杂语言任务处理能力。 foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
10 MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning MoveLight：基于运动中心深度强化学习的交通信号控制系统 reinforcement learning deep reinforcement learning
11 SMA-Hyper: Spatiotemporal Multi-View Fusion Hypergraph Learning for Traffic Accident Prediction 提出SMA-Hyper模型，通过时空多视角融合超图学习预测交通事故。 contrastive learning spatiotemporal
12 Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach 提出基于强化学习的自行车模型路径跟踪与稳定控制方法 reinforcement learning curriculum learning
13 Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning 提出高效的多目标强化学习算法以优化Pareto策略 reinforcement learning
14 Exploring Domain Robust Lightweight Reward Models based on Router Mechanism 提出基于路由机制的领域鲁棒轻量级奖励模型，提升多领域适应性。 reinforcement learning large language model
15 Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems 针对状态依赖型扩散过程，提出次线性遗憾的连续时间LQ强化学习算法 reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页