2 papers
stat.ML2026
Flow-based Spectral Kernel Learning for Nonstationary Attention
Zi Yang, Ying Li, Alejandro Lancho +3
Kernelized attention provides a useful perspective for understanding self-attention as a similarity-based aggregation mechanism, but existing approaches often rely on fixed or stat…
cs.LG2025
Transformer Vibration Forecasting for Advancing Rail Safety and Maintenance 4.0
Darío C. Larese, Almudena Bravo Cerrada, Gabriel Dambrosio Tomei +3
Maintaining railway axles is critical to preventing severe accidents and financial losses. The railway industry is increasingly interested in advanced condition monitoring techniqu…