Speaker
Anna Lena Schaible
Description
Modern integral field spectroscopic (IFS) observations provide unprecedented detail of galaxy dynamics, but directly comparing these integrated light observations to discrete particle outputs from cosmological simulations remains challenging. Traditional forward-modeling tools are often CPU-bound and lack derivative information, hindering their application in modern gradient-assisted machine learning pipelines. To bridge this gap, we present RUBIX, an end-to-end differentiable pipeline built in JAX that directly forward-models particle-level inputs into mock IFS datacubes.