Concepts

TorchEBM treats generative modeling as the composition of a small number of mathematical objects. Each has one subpackage, one base class, and one page here:

Axis	Question it answers	Package	Page
Energy	What is the model?	torchebm.core, torchebm.models	The Energy-Based View
Dynamics	How are samples drawn?	torchebm.samplers, torchebm.integrators	Sampling and Integration
Objective	How is the model fit to data?	torchebm.losses	Learning Objectives
Transport	Which path and pairing connect noise and data?	torchebm.interpolants, torchebm.couplings	Interpolants and Couplings

Design and Scope states the unifying abstraction precisely and places EBMs, score-based and diffusion models, flow matching, stochastic interpolants, and Schrödinger bridges in one taxonomy, with references.

Read in any order; each page links to the runnable examples that exercise it.