Yingjie Tan

2 accepted papers

2026

DGNet: Learning Spatiotemporal PDEs with Discrete Green Networks

ICLR 2026poster

Spatiotemporal partial differential equations (PDEs) underpin a wide range of scientific and engineering applications, yet classical solvers are computationally costly on large or irregular domains. Neural PDE solvers have emerged as an efficient alternative, but they struggle to generalize to unsee…

Cited by 0 Source ↗Scholar ↗

2026

S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting

Wenshuo Wang, Yaomin Shen, Yingjie Tan, Yihao Chen

AAAI 2026technical

Spatiotemporal forecasting often relies on computationally intensive models to capture complex dynamics. Knowledge distillation (KD) has emerged as a key technique for creating lightweight student models, with recent advances like frequency-aware KD successfully preserving spectral properties (i.e.,

Cited by 0 Source ↗PDF ↗Scholar ↗