Jasser KraiemWriting and research on probabilistic generative models and learned image compression.https://jasserkraiem.com/Probabilistic Generative Models Overviewhttps://jasserkraiem.com/writing/probabilistic-generative-models-overview/https://jasserkraiem.com/writing/probabilistic-generative-models-overview/An introduction to probabilistic generative modeling: how generative models differ from discriminative ones, and the concepts behind five key model families.Sat, 07 Mar 2026 18:42:07 GMTGaussian Mixture Models Explainedhttps://jasserkraiem.com/writing/gaussian-mixture-models-explained/https://jasserkraiem.com/writing/gaussian-mixture-models-explained/Gaussian Mixture Models express a probability distribution as a weighted combination of Gaussians, capturing multi-modal data through interpretable components.Sun, 08 Mar 2026 07:16:10 GMTVariational Autoencoders Explainedhttps://jasserkraiem.com/writing/variational-autoencoders-explained/https://jasserkraiem.com/writing/variational-autoencoders-explained/A Variational Autoencoder (VAE) is a generative model that learns a compressed, continuous representation (a latent space) of data. It consists of an encoder network that maps data to a distribution in the latent space and a decoder network that reconstructs data from samples drawn from that latent distribution.Thu, 12 Mar 2026 20:23:12 GMTNormalizing Flows Explainedhttps://jasserkraiem.com/writing/normalizing-flows-explained/https://jasserkraiem.com/writing/normalizing-flows-explained/Normalizing Flows turn a simple Gaussian into a complex distribution through invertible transformations, enabling exact and tractable likelihood computation.Sun, 15 Mar 2026 14:35:32 GMTGenerative Adversarial Networks Explainedhttps://jasserkraiem.com/writing/generative-adversarial-networks-explained/https://jasserkraiem.com/writing/generative-adversarial-networks-explained/How GANs learn by pitting a generator against a discriminator: the minimax game, and why adversarial training replaced explicit density estimation.Thu, 19 Mar 2026 11:28:27 GMTDiffusion Models Explainedhttps://jasserkraiem.com/writing/diffusion-models-explained/https://jasserkraiem.com/writing/diffusion-models-explained/How diffusion models generate images by reversing a gradual noise process: forward and reverse Markov chains, DDPM, and why they rival GANs on sample quality.Sat, 21 Mar 2026 19:55:32 GMT