cs.LG（2024-01-25）

📊 共 12 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning	提出TWOSOME框架以解决LLMs与环境不对齐问题	reinforcement learning PPO open-vocabulary
2	Tacit algorithmic collusion in deep reinforcement learning guided price competition: A study using EV charge pricing game	提出基于深度强化学习的电动车充电定价博弈以解决算法性默契合谋问题	reinforcement learning deep reinforcement learning
3	Multi-granularity Knowledge Transfer for Continual Reinforcement Learning	提出MT-Core框架以解决持续强化学习中的知识转移问题	reinforcement learning policy learning large language model
4	Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research	提出Scilab-RL框架以解决认知建模与强化学习研究中的效率问题	reinforcement learning
5	Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks	提出一种自动构建子任务奖励函数的RL算法以提高样本效率	reinforcement learning
6	Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation	提出FedCompress以解决联邦学习中的通信成本问题	distillation

#	题目	一句话要点	标签	🔗
7	A Survey of Deep Learning and Foundation Models for Time Series Forecasting	综述深度学习与基础模型在时间序列预测中的应用与挑战	large language model foundation model
8	ServerlessLLM: Low-Latency Serverless Inference for Large Language Models	提出ServerlessLLM以解决大语言模型低延迟推理问题	large language model
9	How Can Large Language Models Understand Spatial-Temporal Data?	提出STG-LLM以解决大语言模型在时空预测中的挑战	large language model
10	FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design	提出FP6-LLM以解决大语言模型推理效率问题	large language model	✅
11	LocMoE: A Low-Overhead MoE for Large Language Model Training	提出LocMoE以解决大语言模型训练中的负载不均和延迟问题	large language model
12	Cross-Modal Prototype based Multimodal Federated Learning under Severely Missing Modality	提出多模态联邦交叉原型学习以解决严重缺失模态问题	multimodal