Free Information Center
The denoising diffusion implicit model (DDIM) is a generative modeling technique that improves the efficiency and sampling speed of diffusion-based models by introducing a non-Markovian diffusion process. It enables faster image synthesis while maintaining high-quality results.
An energy-based model is a type of probabilistic model in machine learning that associates a scalar energy value to each configuration of variables. These models learn to represent data by minimizing the energy of observed data points and assigning higher energy to other configurations.
Masked autoregressive flow (MAF) is a type of normalizing flow used in machine learning for density estimation and generative modeling. It employs autoregressive models combined with masking techniques to create flexible, invertible transformations that allow efficient sampling and likelihood evaluation.