DDPM needs 1000 steps to generate a sample. DDIM reframes the reverse process as an ODE and gets the same quality in 50. The model weights are identical — only the sampling procedure changes.
Language models are probabilistic systems. Understanding the statistical machinery behind maximum likelihood estimation, Bayesian inference, and sampling algorithms clarifies why training and decoding work the way they do.
DDPM needs 1000 steps to generate a sample. DDIM reframes the reverse process as an ODE and gets the same quality in 50. The model weights are identical — only the sampling procedure changes.
Language models are probabilistic systems. Understanding the statistical machinery behind maximum likelihood estimation, Bayesian inference, and sampling algorithms clarifies why training and decoding work the way they do.