cs.LG(2023-10-16)

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (11 🔗2) 支柱九:具身大模型 (Embodied Foundation Models) (7 🔗2) 支柱三:空间感知与语义 (Perception & Semantics) (1) 支柱一:机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗
1 ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models 提出ReMax以解决PPO在大语言模型对齐中的不足 reinforcement learning PPO RLHF
2 Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments 结合知识蒸馏提升深度强化学习在资源受限环境中的效率 reinforcement learning deep reinforcement learning DRL
3 DavIR: Data Selection via Implicit Reward for Large Language Models 提出DavIR以解决大语言模型的数据选择问题 DPO direct preference optimization large language model
4 Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation 利用拓扑地图提升深度强化学习在多目标导航中的表现 reinforcement learning deep reinforcement learning
5 Proper Laplacian Representation Learning 提出拉普拉斯表示学习以解决强化学习中的状态表示问题 reinforcement learning representation learning reward shaping
6 Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning 提出混合模型基础的后继特征强化学习以解决不确定性知识转移问题 reinforcement learning
7 Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms 提出ERNIE框架以解决多智能体强化学习的鲁棒性问题 reinforcement learning
8 A Comprehensive Study of Privacy Risks in Curriculum Learning 提出隐私风险评估方法以解决课程学习中的数据泄露问题 curriculum learning
9 Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks 提出一种样本复杂度理论以解决基于偏好的非参数离线策略评估问题 reinforcement learning RLHF
10 Self-Pro: A Self-Prompt and Tuning Framework for Graph Neural Networks 提出Self-Prompt框架以解决图神经网络的负迁移问题 representation learning contrastive learning
11 Mimicking the Maestro: Exploring the Efficacy of a Virtual AI Teacher in Fine Motor Skill Acquisition 提出虚拟AI教师以提升精细运动技能的学习效果 reinforcement learning imitation learning

🔬 支柱九:具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗
12 FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models 提出FATE-LLM以解决大语言模型训练资源不足问题 large language model
13 Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible Commonsense Norms 提出NORMLENS以解决视觉基础的常识推理问题 large language model multimodal
14 Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook 综述大模型在时间序列与时空数据分析中的应用与前景 large language model foundation model
15 Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data 提出SWSA框架以解决无标签验证数据下的异常检测模型选择问题 foundation model
16 Approximating Two-Layer Feedforward Networks for Efficient Transformers 提出统一框架以高效近似两层前馈网络 large language model
17 How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations 提出基于表示学习的复杂场景下变换器的上下文学习机制 large language model
18 AdaLomo: Low-memory Optimization with Adaptive Learning Rate 提出AdaLomo以解决大语言模型训练中的低内存优化问题 large language model

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

#题目一句话要点标签🔗
19 Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World 提出Bongard-OpenWorld以解决真实场景中的少样本推理问题 open-vocabulary open vocabulary large language model

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
20 A representation learning approach to probe for dynamical dark energy in matter power spectra 提出DE-VAE以探测动态暗能量在物质功率谱中的表现 MPC representation learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页