ArXiv TLDR

Xianpeng Wang

2 papers · Latest:

Machine Learning

Drift-Aware Online Dynamic Learning for Nonstationary Multivariate Time Series: Application to Sintering Quality Prediction

DA-MSDL is a new online dynamic learning framework that uses drift-aware mechanisms to accurately predict nonstationary multivariate time series, outperforming baselines.

2604.09358
Machine Learning

Auto-Configured Networks for Multi-Scale Multi-Output Time-Series Forecasting

This paper introduces an auto-configuration framework for multi-scale, multi-output time-series forecasting, balancing prediction error and model complexity.

2604.07610

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.