cs.LG（2024-04-03）

📊 共 26 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (14 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (12 🔗3)

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗⭐
1 Foundation Models for Structural Health Monitoring 提出Transformer神经网络作为结构健康监测的基础模型 MAE distillation foundation model
2 Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience 通过合作机制重新思考教师-学生课程学习 reinforcement learning curriculum learning teacher-student
3 Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning 提出网格映射伪计数约束以解决离线强化学习中的OOD问题 reinforcement learning SAC offline reinforcement learning
4 AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Dataset 提出AD4RL以解决离线强化学习在自动驾驶中的数据不足问题 reinforcement learning offline reinforcement learning
5 Solving a Real-World Optimization Problem Using Proximal Policy Optimization with Curriculum Learning and Reward Engineering 提出基于PPO的课程学习与奖励工程以优化废物分类问题 reinforcement learning PPO curriculum learning
6 Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation 提出可解释的强化学习方法以优化机械通气控制 reinforcement learning behavior cloning
7 MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search 提出MARL-LNS以解决多智能体强化学习训练效率低下问题 reinforcement learning
8 Model-based Reinforcement Learning for Parameterized Action Spaces 提出DLPA算法以解决参数化动作空间中的强化学习问题 reinforcement learning
9 Linear Attention Sequence Parallelism 提出线性注意力序列并行方法以提升长序列处理效率 linear attention ✅
10 Reinforcement Learning in Categorical Cybernetics 将强化学习算法纳入范畴控制论框架以提升学习效率 reinforcement learning
11 Convergence Analysis of Flow Matching in Latent Space with Transformers 提出流匹配方法以确保ODE生成模型的收敛性 flow matching
12 Masked Completion via Structured Diffusion with White-Box Transformers 提出CRATE-MAE以解决无监督表示学习中的结构化问题 representation learning masked autoencoder MAE ✅
13 Improve Knowledge Distillation via Label Revision and Data Selection 通过标签修正与数据选择提升知识蒸馏效果 distillation
14 Generative-Contrastive Heterogeneous Graph Neural Network 提出生成对比异构图神经网络以解决数据增强不足问题 masked autoencoder contrastive learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
15 Toward Inference-optimal Mixture-of-Expert Large Language Models 提出混合专家模型以优化大语言模型的推理效率 large language model
16 BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models 提出BAdam以解决大语言模型全参数优化的内存效率问题 large language model ✅
17 PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models 提出PiSSA以加速大语言模型的参数高效微调 large language model ✅
18 Towards detecting unanticipated bias in Large Language Models 提出新方法以检测大型语言模型中的隐性偏见 large language model
19 On the Importance of Uncertainty in Decision-Making with Large Language Models 提出不确定性估计以提升大语言模型决策效果 large language model
20 Towards Explainable Traffic Flow Prediction with Large Language Models 提出基于大语言模型的交通流预测模型以解决可解释性问题 large language model
21 On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study 提出基于振动的基础模型以提升物联网应用的鲁棒性 foundation model
22 The Artificial Intelligence Ontology: LLM-assisted construction of AI concept hierarchies 构建人工智能本体以应对AI概念的快速演变 large language model ✅
23 MODNO: Multi Operator Learning With Distributed Neural Operators 提出MODNO以解决多算子学习问题 foundation model
24 How Sparse Attention Approximates Exact Attention? Your Attention is Naturally $n^C$-Sparse 提出稀疏注意力理论框架以优化传统注意力计算 large language model
25 Concept-Guided LLM Agents for Human-AI Safety Codesign 提出概念引导的LLM代理以解决人机安全共设计问题 large language model
26 Task Agnostic Architecture for Algorithm Induction via Implicit Composition 提出通用架构以实现算法归纳，解决多任务学习问题 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页