cs.LG（2024-05-13）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱八：物理动画 (Physics-based Animation) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 RLHF Workflow: From Reward Modeling to Online RLHF 提出在线迭代RLHF流程，提升大型语言模型在聊天机器人基准测试中的性能。 reinforcement learning RLHF large language model ✅
2 Decision Mamba Architectures 提出Decision Mamba和Hierarchical Decision Mamba，提升模仿学习中Transformer模型的性能。 imitation learning decision transformer Mamba ✅
3 Predictive Modeling of Flexible EHD Pumps using Kolmogorov-Arnold Networks 提出基于Kolmogorov-Arnold网络的柔性EHD泵预测模型，提升精度与可解释性。 predictive model
4 Radio Resource Management and Path Planning in Intelligent Transportation Systems via Reinforcement Learning for Environmental Sustainability 提出基于强化学习的无线资源管理与路径规划方法，提升智能交通系统环境可持续性 reinforcement learning
5 Hamiltonian-based Quantum Reinforcement Learning for Neural Combinatorial Optimization 提出基于哈密顿量的量子强化学习方法，用于神经组合优化 reinforcement learning
6 Hype or Heuristic? Quantum Reinforcement Learning for Join Order Optimisation 提出基于混合变分量子 ansatz 的量子强化学习方法，用于优化数据库连接顺序。 reinforcement learning
7 Neural Network Compression for Reinforcement Learning Tasks 针对强化学习任务，探索神经网络压缩以提升推理效率 reinforcement learning
8 GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation 提出GLiRA：一种基于知识蒸馏的黑盒成员推理攻击方法 distillation
9 POWQMIX: Weighted Value Factorization with Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning POWQMIX：通过潜在最优联合动作识别加权分解值函数，提升合作多智能体强化学习性能 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
10 HoneyBee: A Scalable Modular Framework for Creating Multimodal Oncology Datasets with Foundational Embedding Models HONeYBEE：一个可扩展的模块化框架，利用基础嵌入模型创建多模态肿瘤学数据集 large language model foundation model multimodal
11 Self-Normalizing Foundation Model for Enhanced Multi-Omics Data Analysis in Oncology 提出SeNMo自归一化基础模型，增强肿瘤多组学数据分析能力 foundation model
12 LLM4ED: Large Language Models for Automatic Equation Discovery 提出LLM4ED框架，利用大语言模型自动发现数据中的控制方程 large language model
13 AnomalyLLM: Few-shot Anomaly Edge Detection for Dynamic Graphs using Large Language Models AnomalyLLM：利用大语言模型进行动态图的少样本异常边检测 large language model
14 Coding historical causes of death data with Large Language Models 利用大型语言模型自动标注历史死因数据ICD-10编码 large language model
15 CataLM: Empowering Catalyst Design Through Large Language Models CataLM：通过大型语言模型赋能催化剂设计 large language model
16 Can Language Models Explain Their Own Classification Behavior? 提出ArticulateRules数据集，评估LLM能否解释自身分类行为，揭示模型自解释能力差异。 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
17 Estimating Direct and Indirect Causal Effects of Spatiotemporal Interventions in Presence of Spatial Interference 提出基于深度学习的时空因果推断模型，用于估计存在空间干涉情况下的干预效果 spatiotemporal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
18 Boosting House Price Estimations with Multi-Head Gated Attention 提出多头门控注意力模型，提升房价空间插值预测精度 spatial relationship

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
19 Accelerating the Evolution of Personalized Automated Lane Change through Lesson Learning 提出基于Lesson Learning的个性化自动变道进化方法，解决在线学习计算量大问题。 model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页