cs.LG（2025-01-12）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Deep Learning and Foundation Models for Weather Prediction: A Survey	综述深度学习与预训练模型在天气预测中的应用，并提出未来研究方向。	foundation model
2	Transfer Learning of Tabular Data by Finetuning Large Language Models	通过微调大型语言模型实现表格数据的迁移学习	large language model
3	MTPareto: A MultiModal Targeted Pareto Framework for Fake News Detection	提出MTPareto框架，通过多模态目标帕累托优化解决假新闻检测中的模态融合难题。	multimodal
4	Comparison of Autoencoders for tokenization of ASL datasets	对比自编码器在美式手语数据集tokenization中的应用，扩散自编码器表现最优	large language model multimodal
5	Compact Bayesian Neural Networks via pruned MCMC sampling	提出基于剪枝MCMC采样的紧凑贝叶斯神经网络，提升模型泛化能力与可移植性。	multimodal
6	ZOQO: Zero-Order Quantized Optimization	提出ZOQO：一种零阶量化优化方法，用于资源受限环境下的模型训练。	large language model
7	Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights	提出Grad-Mimic框架，通过模仿模型权重高效评估样本效用，实现数据选择。	multimodal

#	题目	一句话要点	标签	🔗
8	A novel multi-agent dynamic portfolio optimization learning system based on hierarchical deep reinforcement learning	提出一种基于分层深度强化学习的多智能体动态投资组合优化系统，提升风险调整收益。	reinforcement learning deep reinforcement learning DRL
9	Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference	提出半参数双重强化学习，用于长期因果推断，提升策略价值估计效率。	reinforcement learning DRL
10	DRDT3: Diffusion-Refined Decision Test-Time Training Model	提出DRDT3模型，融合扩散模型与测试时训练，提升离线强化学习决策Transformer性能。	reinforcement learning offline RL offline reinforcement learning
11	Average Reward Reinforcement Learning for Wireless Radio Resource Management	提出平均奖励Off-policy软演员评论家算法，解决无线资源管理中折扣奖励与长期目标不匹配问题	reinforcement learning SAC
12	SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training	提出SPAM优化器，通过动量重置和梯度裁剪解决LLM训练中的梯度爆炸问题，提升训练稳定性和资源效率。	reinforcement learning large language model	✅
13	Pareto Set Learning for Multi-Objective Reinforcement Learning	提出PSL-MORL，利用超网络学习Pareto集，高效解决多目标强化学习问题	reinforcement learning