Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees
Vojtěch Kůr, Adam Kukučka, Tomáš Brázdil +1
Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasses approaches that differ in ho…
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…