cs.LG（2024-02-12）

📊 共 25 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) (11 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (11) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
1 Measurement Scheduling for ICU Patients with Offline Reinforcement Learning 提出离线强化学习方法优化ICU患者实验室测试调度 reinforcement learning offline RL offline reinforcement learning
2 Active Preference Learning for Large Language Models 提出主动偏好学习策略以优化大语言模型的微调过程 reinforcement learning preference learning RLHF
3 A Competition Winning Deep Reinforcement Learning Agent in microRTS 提出RAISocketAI以解决微型RTS竞赛中的深度强化学习挑战 reinforcement learning deep reinforcement learning DRL
4 Policy Improvement using Language Feedback Models 提出语言反馈模型以提升模仿学习任务完成率 imitation learning large language model instruction following
5 UGMAE: A Unified Framework for Graph Masked Autoencoders 提出UGMAE框架以解决图掩码自编码器的多重问题 masked autoencoder
6 Generative Modeling of Discrete Joint Distributions by E-Geodesic Flow Matching on Assignment Manifolds 提出基于E-测地流匹配的生成模型以解决离散联合分布问题 flow matching
7 Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanism 提出双线性注意机制以解决图结构推断问题 linear attention
8 Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model 提出一种近最小极大最优的分布式强化学习算法以解决生成模型问题 reinforcement learning
9 One Train for Two Tasks: An Encrypted Traffic Classification Framework Using Supervised Contrastive Learning 提出CLE-TFE框架以解决加密流量分类问题 contrastive learning ✅
10 Potential-Based Reward Shaping For Intrinsic Motivation 提出潜在基础奖励塑形方法以解决内在动机问题 reward shaping
11 Data Distribution-based Curriculum Learning 提出基于数据分布的课程学习方法以提升分类器性能 curriculum learning

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

#题目一句话要点标签🔗⭐
12 Text-centric Alignment for Multi-Modality Learning 提出文本中心对齐方法以解决多模态学习中的模态不匹配问题 large language model foundation model multimodal
13 PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models 提出PoisonedRAG以解决RAG系统的知识腐蚀攻击问题 large language model
14 Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning 提出差分隐私零阶方法以提升大语言模型微调效率 large language model
15 Towards a Foundation Model for Brain Age Prediction using coVariance Neural Networks 提出NeuroVNN模型以解决脑龄预测问题 foundation model
16 Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction 提出GTT模型以解决零-shot多变量时间序列预测问题 foundation model
17 On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era 提出结合递归模型与变换器的新方法以处理长序列数据 large language model
18 Grounding Data Science Code Generation with Input-Output Specifications 提出GIFT4Code以解决数据科学代码生成中的模糊性问题 large language model
19 Scaling Laws for Fine-Grained Mixture of Experts 提出细粒度专家混合模型的扩展规模法则以优化计算效率 large language model
20 Empowering Federated Learning for Massive Models with NVIDIA FLARE 提出NVIDIA FLARE以解决大规模模型的联邦学习挑战 large language model
21 Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model 提出合成图导航模型以理解变换器中的逐步推理 chain-of-thought
22 Assessing Generalization for Subpopulation Representative Modeling via In-Context Learning 评估基于LLM的子群体代表模型的泛化能力 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
23 Auxiliary Reward Generation with Transition Distance Representation Learning 提出过渡距离表示学习以实现自动辅助奖励生成 manipulation reinforcement learning representation learning

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

#题目一句话要点标签🔗⭐
24 Accelerating Distributed Deep Learning using Lossless Homomorphic Compression 提出无损同态压缩算法以加速分布式深度学习 OMOMO

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

#题目一句话要点标签🔗⭐
25 Zero-shot Imputation with Foundation Inference Models for Dynamical Systems 提出零-shot插补框架以解决动态系统时间序列缺失数据问题 human motion

⬅️ 返回 cs.LG 首页 · 🏠 返回主页