cs.LG（2024-07-30）

📊 共 12 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	HyperMM : Robust Multimodal Learning with Varying-sized Inputs	HyperMM：一种鲁棒的、处理变长输入的多模态学习框架	multimodal
2	CELLM: An Efficient Communication in Large Language Models Training for Federated Learning	CELLM：联邦学习中高效的大语言模型训练通信方法	large language model
3	A federated large language model for long-term time series forecasting	提出FedTime：一种用于长期时间序列预测的联邦大语言模型	large language model
4	Machine Unlearning in Generative AI: A Survey	针对生成式AI模型，提出机器遗忘技术综述，解决模型记忆敏感信息问题	large language model multimodal	✅
5	MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning	提出MoFO：一种动量过滤优化器，用于缓解LLM微调中的遗忘问题	large language model
6	Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification	提出恶意放大攻击，破坏自主LLM Agent，使其执行重复或无关动作。	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	🔗	⭐
7	Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations	提出CSR方法以解决强化学习中的环境变化问题	reinforcement learning representation learning
8	How to Choose a Reinforcement-Learning Algorithm	提出强化学习算法选择指南，解决序列决策问题中算法选择难题。	reinforcement learning	✅
9	Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning	MF2Vec：利用多粒度路径学习异构图表示，提升节点嵌入质量。	representation learning
10	Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge	提出因果探索方法，提升任务无关强化学习中世界模型学习的效率。	reinforcement learning world model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning	提出Diffusion Augmented Agents (DAAG)框架，提升具身智能体强化学习的样本效率和迁移学习能力	manipulation reinforcement learning large language model

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

#	题目	一句话要点	标签	🔗	⭐
12	What Are Good Positional Encodings for Directed Graphs?	针对有向图，提出Multi-q磁拉普拉斯位置编码以提升图神经网络性能	spatial relationship	✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页