← Search

Zining Qin

2 accepted papers

2026

Not All Frequencies Are Equal: Energy-Adaptive Diffusion for Time Series Forecasting

ICML 2026poster

Diffusion models have achieved remarkable success in generative modeling, yet their application to time series forecasting remains suboptimal. Existing approaches apply uniform Gaussian noise across all time steps, assuming all frequency components should be corrupted at the same rate. However, ener…

Cited by 0SourceScholar