AI RESEARCH
DiScoFormer: Plug-In Density and Score Estimation with Transformers
arXiv CS.LG
•
ArXi:2511.05924v3 Announce Type: replace Estimating probability density and its score from samples remains a core problem in generative modeling, Bayesian inference, and kinetic theory. Existing methods are bifurcated: classical kernel density estimators (KDE) generalize across distributions but suffer from the curse of dimensionality, while modern neural score models achieve high precision but require re