cs.LG（2024-01-31）

📊 共 16 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6)

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

#题目一句话要点标签🔗⭐
1 Simplifying Latent Dynamics with Softly State-Invariant World Models 提出PLSM以解决世界模型中动作影响不确定性问题 reinforcement learning world model world models
2 Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning 提出DE-TSMCL框架以解决时间序列预测中的数据噪声问题 representation learning contrastive learning distillation
3 Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning 提出SC-DDQ框架以提高对话策略学习的探索效率 reinforcement learning policy learning curriculum learning
4 EPSD: Early Pruning with Self-Distillation for Efficient Model Compression 提出EPSD以实现高效模型压缩 teacher-student distillation
5 Graph Contrastive Learning with Cohesive Subgraph Awareness 提出CTAug以解决图对比学习中的内在属性损失问题 representation learning contrastive learning ✅
6 Decentralized Covert Routing in Heterogeneous Networks Using Reinforcement Learning 提出基于强化学习的去中心化隐蔽路由算法以解决异构网络中的通信问题 reinforcement learning
7 Learning Label Hierarchy with Supervised Contrastive Learning 提出标签感知对比学习方法以解决标签层次问题 contrastive learning
8 Rank Supervised Contrastive Learning for Time Series Classification 提出RankSCL以解决时间序列分类中的相似性信息忽视问题 contrastive learning
9 Causal Coordinated Concurrent Reinforcement Learning 提出因果协调并发强化学习算法以提升数据效率 reinforcement learning
10 MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts 提出MoDE以解决MoE模型专家间信息孤立问题 distillation

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

#题目一句话要点标签🔗⭐
11 Multimodal Neurodegenerative Disease Subtyping Explained by ChatGPT 提出多模态框架以早期分类阿尔茨海默病亚型 large language model multimodal
12 A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models 提出数据有效学习基准以优化医学领域基础模型预训练 foundation model
13 On Prompt-Driven Safeguarding for Large Language Models 提出DRO方法以优化大型语言模型的安全提示 large language model
14 EEG-GPT: Exploring Capabilities of Large Language Models for EEG Classification and Interpretation 提出EEG-GPT以解决EEG分类与解释的局限性 large language model
15 Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM 提出SymPrompt以解决LLM生成测试用例覆盖率低的问题 large language model
16 Efficient Subseasonal Weather Forecast using Teleconnection-informed Transformers 提出基于遥相关的变换器以提升亚季节天气预报精度 foundation model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页