cs.LG（2025-01-26）

📊 共 9 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	RLER-TTE: An Efficient and Effective Framework for En Route Travel Time Estimation with Reinforcement Learning	提出RLER-TTE框架，利用强化学习高效准确地进行在途旅行时间估计。	reinforcement learning curriculum learning
2	Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space	提出MbaGCN，利用选择性状态空间解决图神经网络的过平滑问题	Mamba representation learning
3	Random Walk Guided Hyperbolic Graph Distillation	提出基于双曲空间随机游走的图蒸馏方法HyDRO，提升图学习任务性能。	distillation
4	A Comprehensive Survey on Self-Interpretable Neural Networks	全面综述自解释性神经网络，涵盖方法、应用与挑战	reinforcement learning deep reinforcement learning	✅
5	Episodic Novelty Through Temporal Distance	提出基于时间距离的情节新颖性探索方法ETD，解决稀疏奖励CMDP中的探索难题。	reinforcement learning contrastive learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Improving Network Threat Detection by Knowledge Graph, Large Language Model, and Imbalanced Learning	提出基于知识图谱、大语言模型和不平衡学习的网络威胁检测框架，提升威胁捕获率。	large language model
7	Advancing Generative Artificial Intelligence and Large Language Models for Demand Side Management with Internet of Electric Vehicles	提出基于检索增强生成的大语言模型，用于物联网电动汽车需求侧管理的优化。	large language model
8	Decentralized Low-Rank Fine-Tuning of Large Language Models	提出Dec-LoRA，实现大型语言模型在去中心化环境下的低秩微调	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning	提出UNIDOOR框架，解决深度强化学习中动作级后门攻击的通用性问题。	manipulation reinforcement learning deep reinforcement learning	✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页