cs.LG(2024-02-26)

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (10 🔗2) 支柱九:具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱八:物理动画 (Physics-based Animation) (2) 支柱三:空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗
1 Model-based deep reinforcement learning for accelerated learning from flow simulations 提出基于模型的深度强化学习以加速流动仿真学习 reinforcement learning deep reinforcement learning
2 Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning 提出Craftax以解决开放式强化学习基准测试效率低下问题 reinforcement learning PPO
3 C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory 提出C-GAIL以解决GAIL训练不稳定问题 reinforcement learning imitation learning
4 Graph Diffusion Policy Optimization 提出图扩散策略优化以解决图生成中的优化问题 reinforcement learning diffusion policy
5 m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers 提出模块间知识蒸馏方法以提升模块化变换器性能 distillation
6 Hyperdimensional Representation Learning for Node Classification and Link Prediction 提出超高维图学习方法HDGL以解决节点分类和链接预测问题 representation learning
7 Program-Based Strategy Induction for Reinforcement Learning 提出基于程序的策略诱导以解决强化学习中的策略发现问题 reinforcement learning
8 QF-tuner: Breaking Tradition in Reinforcement Learning 提出QF-tuner以解决强化学习中的超参数调优问题 reinforcement learning
9 Minimize Control Inputs for Strong Structural Controllability Using Reinforcement Learning with Graph Neural Network 提出基于图神经网络的强化学习方法以最小化控制输入 reinforcement learning
10 Multiple Access in the Era of Distributed Computing and Edge Intelligence 提出下一代多接入技术以应对6G网络挑战 reinforcement learning distillation

🔬 支柱九:具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗
11 Asymmetry in Low-Rank Adapters of Foundation Models 提出低秩适配器的不对称性以提升模型微调效率 foundation model
12 An Integrated Data Processing Framework for Pretraining Foundation Models 提出集成数据处理框架以提升基础模型预训练数据质量 foundation model
13 Foundation Model Transparency Reports 提出基础模型透明报告以解决透明性不足问题 foundation model
14 Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding 提出混合模型以提高自回归解码效率 large language model instruction following
15 TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis 提出TOTEM以解决通用时间序列分析问题 large language model
16 Language-guided Skill Learning with Temporal Variational Inference 提出基于语言指导的技能学习方法以解决技能发现问题 large language model

🔬 支柱八:物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗
17 Parallelized Spatiotemporal Binding 提出并行时空绑定模型以解决长序列训练效率低下问题 spatiotemporal
18 REPLAY: Modeling Time-Varying Temporal Regularities of Human Mobility for Location Prediction over Sparse Trajectories 提出REPLAY以解决人类移动性时间变化规律建模问题 spatiotemporal TAMP

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
19 CARTE: Pretraining and Transfer for Tabular Learning 提出CARTE以解决表格数据预训练与迁移学习问题 open-vocabulary open vocabulary

⬅️ 返回 cs.LG 首页 · 🏠 返回主页