Domain: Diffusion & Generative Models

Model that compresses input into latent space and reconstructs it.

Diffusion model trained to remove noise step by step.

Generative model that learns to reverse a gradual noise process.

Exact likelihood generative models using invertible transforms.

Two-network setup where generator fools a discriminator.

Models that learn to generate samples resembling training data.

Diffusion performed in latent space for efficiency.

Generator produces limited variety of outputs.

Controls amount of noise added at each diffusion step.

Learns the score (∇ log p(x)) for generative sampling.

Autoencoder using probabilistic latent variables and KL regularization.