cs.LG（2023-12-26）

📊 共 10 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning	提出PDiT：一种交错感知与决策Transformer网络，提升深度强化学习性能	reinforcement learning deep reinforcement learning offline RL	✅
2	Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations	针对数据受限的离线元强化学习，提出可泛化的任务表征学习方法GENTLE	reinforcement learning representation learning contrastive learning
3	A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration	提出基于贝叶斯深度强化学习的O-RAN/MEC联合编排框架，优化网络运营成本和MEC性能。	reinforcement learning deep reinforcement learning
4	Efficient Reinforcement Learning via Decoupling Exploration and Utilization	提出OPARL算法，通过解耦探索与利用，提升强化学习效率与泛化性	reinforcement learning	✅
5	AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation	提出AdapterDistillation，通过知识蒸馏实现任务组合，提升FAQ检索效率。	distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
6	MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks	MoTCoder：利用模块化思维提升大语言模型在复杂编程任务中的性能	large language model	✅
7	FedMS: Federated Learning with Mixture of Sparsely Activated Foundations Models	提出FedMS，一种基于混合稀疏激活基础模型的联邦学习方法，提升个性化与效率。	foundation model multimodal
8	Observable Propagation: Uncovering Feature Vectors in Transformers	提出Observable Propagation方法，在低数据量下发现Transformer中的线性特征向量。	large language model
9	A bi-objective $ε$-constrained framework for quality-cost optimization in language model ensembles	提出基于双目标ε约束的框架，优化语言模型集成中的质量-成本权衡。	large language model

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

#	题目	一句话要点	标签	🔗	⭐
10	Smuche: Scalar-Multiplicative Caching in Homomorphic Encryption	提出Smuche以解决同态加密中的缓存效率问题	OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页