collaborators

1 paper

cs.LG2026

SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients

Anselm Paulus, A. René Geist, Vít Musil +3

Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in the…