work NEEDLE Neural-based diffusion likelihood estimations for scientific computing Neural Likelihood Ratios Quasiprobabilistic likelihood-ratio estimation with negatively weighted Monte Carlo ATLAS Higgs & Modelling Precision Higgs measurements and Monte Carlo modelling with ATLAS carl-torch PyTorch toolbox for multivariate Monte Carlo reweighting fun Terascale ML Tutorials Machine learning tutorials for HEP students at Terascale 2026