cs.LG（2024-11-06）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Gradient Boosting Trees and Large Language Models for Tabular Data Few-Shot Learning 改进梯度提升树，提升表格数据小样本学习性能，与大语言模型竞争 large language model
2 Multi-Scale and Multimodal Species Distribution Modeling 提出多尺度多模态物种分布模型，提升物种分布预测精度 multimodal
3 Interactions Across Blocks in Post-Training Quantization of Large Language Models 提出多块联合微调策略，提升大语言模型后训练量化性能（部分模型有效） large language model
4 Towards Optimizing SQL Generation via LLM Routing 提出基于LLM路由的Text-to-SQL优化方法，降低成本并保持精度。 large language model
5 Enhancing Security Control Production With Generative AI 利用生成式AI加速安全控制生成，提升云服务安全性 large language model
6 LSHBloom: Memory-efficient, Extreme-scale Document Deduplication LSHBloom：一种内存高效的、可扩展的文档去重方法 large language model
7 A Implies B: Circuit Analysis in LLMs for Propositional Logical Reasoning 利用LLM电路分析揭示命题逻辑推理机制，发现模块化子电路。 large language model
8 Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning 提出Multi-Sub，通过多模态子空间代理学习实现用户定制化多重聚类。 large language model ✅
9 EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning 提出EXPLORA算法，高效选择复杂推理任务的静态示例子集，提升大语言模型性能。 large language model ✅
10 Large Generative Model-assisted Talking-face Semantic Communication System 提出基于大生成模型的说话人面部语义通信系统，提升带宽利用率和用户体验。 large language model
11 A Bayesian Approach to Data Point Selection 提出一种基于贝叶斯推断的数据点选择方法，提升深度学习训练效率。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
12 Towards Personalized Federated Learning via Comprehensive Knowledge Distillation 提出基于知识蒸馏的个性化联邦学习方法，缓解灾难性遗忘问题 distillation
13 Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems 提出一种可解释高效的数据驱动方法，用于分布式系统的发现与控制。 reinforcement learning DRL model-based RL
14 Opportunities of Reinforcement Learning in South Africa's Just Transition 探索强化学习在南非公正转型中的应用，助力应对气候危机和社会挑战 reinforcement learning
15 Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data 提出混合迁移强化学习HySRL算法，解决动态转移下的样本效率问题 reinforcement learning

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
16 Multimodal Structure-Aware Quantum Data Processing 提出MultiQ-NLP框架，利用量子计算处理多模态结构化数据，提升NLP模型可解释性。 OMOMO large language model multimodal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页