Chanayut Theslongthong

Symmetry-Transport Hypernetworks: Efficient On-Demand Weights by Separating Task Geometry from Conditional Parameter Generation

A hypernetwork can generate task-specific model weights from a compact representation of the task, rather than learning a separate set of weights for every transformed version. In this work, invariant task coordinates are used to generate canonical weights, which are then transformed according to the known task symmetr...