Yang Weng

LASS-ODE: When Large Foundation Models Meet Small Unified ODE Representations

Boundary-Aware Tokenization for Event-Driven Time-Series Forecasting

Controllable Representation Learning for Time-series Analysis

Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning

G-AlignNet: Geometry-Driven Quality Alignment for Robust Dynamical Systems Modeling

Orthogonal Deep Neural Networks (ODNN): Uncovering Hidden Physics in Partially Observable Systems

MetaInv: Overcoming Iterative and Direct Method Limitations for Inverse Learning