cs.LG（2024-09-14）

📊 共 8 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) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens	提出Planning Transformer，利用规划令牌解决离线强化学习中的长时程任务难题。	reinforcement learning offline reinforcement learning decision transformer
2	ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood	提出ASFT，通过优化绝对似然进行对齐监督微调，提升LLM与人类偏好对齐效果。	RLHF DPO direct preference optimization
3	Turbo your multi-modal classification with contrastive learning	提出Turbo对比学习策略，提升多模态分类任务性能	representation learning contrastive learning
4	Informative Subgraphs Aware Masked Auto-Encoder in Dynamic Graphs	DyGIS：动态图中信息子图感知的掩码自编码器，提升时空信息建模能力	masked autoencoder MAE

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

#	题目	一句话要点	标签	🔗	⭐
5	Leveraging Foundation Models for Efficient Federated Learning in Resource-restricted Edge Networks	提出FedD2P框架，利用联邦学习和知识蒸馏在边缘网络高效部署Foundation Model。	foundation model
6	LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach	利用LLM集成学习解决论文溯源问题，无需GPU训练	large language model	✅
7	Symbolic Regression with a Learned Concept Library	LaSR：利用学习的概念库进行符号回归，显著提升性能	large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	COMFORT: A Continual Fine-Tuning Framework for Foundation Models Targeted at Consumer Healthcare	COMFORT：面向消费医疗的Transformer基础模型持续微调框架	MDM foundation model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页