collaborators

10 papers

cs.LG2026

Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

Yisong Fu, Zezhi Shao, Chengqing Yu +4

We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. U…

cs.CV2026

Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model

Yu Wang, Chuanguang Yang, Zhulin An +6

Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due…

cs.LG2025

APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift

Yujie Li, Zezhi Shao, Chengqing Yu +4

Time series forecasting under distribution shift remains challenging, as existing deep learning models often rely on local statistical normalization (e.g., mean and variance) that…

cs.LG2025

STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach

Yujie Li, Zezhi Shao, Chengqing Yu +6

Spatio-temporal tasks often encounter incomplete data arising from missing or inaccessible sensors, making spatio-temporal kriging crucial for inferring the completely missing temp…

cs.LG2025

Selective Learning for Deep Time Series Forecasting

Yisong Fu, Zezhi Shao, Chengqing Yu +5

Benefiting from high capacity for capturing complex temporal patterns, deep learning (DL) has significantly advanced time series forecasting (TSF). However, deep models tend to suf…

cs.LG2025

On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting

Yisong Fu, Fei Wang, Zezhi Shao +6

Transformers have gained attention in atmospheric time series forecasting (ATSF) for their ability to capture global spatial-temporal correlations. However, their complex architect…