Emadeldeen Eldele

Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Semantic Alignment

EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting

Learning Soft Sparse Shapes for Efficient Time-Series Classification

Counterfactual Contrastive Learning with Normalizing Flows for Robust Treatment Effect Estimation

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift

Towards Adaptive Time Series Foundation Models Against Distribution Shift