You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is code for Multi-period Learning for Financial Time Series Forecasting (MLF, published in KDD 2025), which incorporates multiple inputs with varying lengths (periods) to achieve better accura…
This is code for Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification (APTF, WWW 2026), enables the model to focus on high-predictability samples while s…
This is code for SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting (WWW 2026). SEMixer can handle longer input sequences and achieve better performan…
This repository contains the official code of Smoothed Full Fine-tuning (SFF) from Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model? (ICLR 2026). SFF enables larg…
This is code for the paper Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations, which is accpted by ICML 2026.