Yang Weng

Heterogeneous load forecasting scales efficiently by learning a small bank of low-rank adaptations for a shared probabilistic model, outperforming independent models and monolithic Transformers.

Generating synthetic power-grid scenarios that are both operationally feasible and statistically accurate could revolutionize planning and resilience assessments in power systems.

Foundation models can now predict power grid dynamics with zero-shot generalization, opening the door to faster, more reliable grid management.