Path-Integral Theory Unifies Generative Models and Cuts Sampler Error to 1.6%
Researchers frame generative modeling as a single path integral, showing flow, diffusion, VAE, and GAN as evaluations of one master action. Using the MSRJD formalism they derive a one-loop correction that drops deterministic sampler error from 53% to 1.6% at no extra cost, and introduce a response-weighted score‑matching objective.