cs.LG（2024-05-10）

📊 共 16 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) (5 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#题目一句话要点标签🔗⭐
1 Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare 综述联邦学习与预训练模型在生物医学健康领域的应用、挑战与机遇。 reinforcement learning foundation model multimodal
2 Learning Latent Dynamic Robust Representations for World Models 提出HRSSM，通过动态鲁棒表征学习提升世界模型在视觉噪声环境下的性能 reinforcement learning policy learning world model ✅
3 Hedging American Put Options with Deep Reinforcement Learning 利用深度强化学习对冲美式看跌期权，优于传统Black-Scholes Delta策略。 reinforcement learning deep reinforcement learning DRL
4 Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning 提出基于对比表示的数据过滤方法，解决跨域离线强化学习中的数据异构问题。 reinforcement learning offline reinforcement learning
5 Value Augmented Sampling for Language Model Alignment and Personalization 提出价值增强采样(VAS)，用于高效语言模型对齐与个性化，无需模型权重更新。 reinforcement learning PPO DPO
6 XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare 提出XAI4LLM框架，利用领域知识增强LLM在医疗场景下的上下文学习能力 distillation large language model multimodal
7 Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning 通过强化学习微调语言模型，提升靶向分子生成效果 reinforcement learning PPO
8 Heterogeneous Graph Neural Networks with Loss-decrease-aware Curriculum Learning 提出基于损失下降感知的异构图神经网络课程学习方法，提升HINs下游任务性能。 curriculum learning ✅
9 PAC-Bayesian Generalization Bounds for Knowledge Graph Representation Learning 提出ReED框架，为知识图谱表示学习提供PAC-Bayes泛化界限理论分析 representation learning
10 Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs 提出基于卷积投影的强化学习方法，实现连续状态空间MDPs中的最优样本复杂度 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
11 A Survey of Large Language Models for Graphs 综述大型语言模型在图学习中的应用与挑战 large language model ✅
12 SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models SKVQ：滑动窗口键值缓存量化，用于压缩大语言模型KV缓存 large language model
13 Automating Code Adaptation for MLOps -- A Benchmarking Study on LLMs 评估LLM在MLOps代码自动化适配能力：一项基准研究 large language model
14 Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus 提出基于归纳逻辑编程的程序合成方法，解决ARC难题。 large language model
15 Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models 针对LLM，论文提出低秩分解方法，在精度损失可控下实现模型压缩。 large language model

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

#题目一句话要点标签🔗⭐
16 Scalable Property Valuation Models via Graph-based Deep Learning 提出基于图神经网络的可扩展房产估值模型，有效捕捉空间关系 spatial relationship

⬅️ 返回 cs.LG 首页 · 🏠 返回主页