An in-depth technical explanation of diffusion models, a class of generative AI models that create data by reversing a noise-adding process.
A technical exploration of the β-VAE objective from an information maximization perspective, discussing its role in learning disentangled representations.
Explores an unsupervised approach combining Mixture of Experts (MoE) with Variational Autoencoders (VAE) for conditional data generation without labels.
An introduction to flow-based deep generative models, explaining how they explicitly learn data distributions using normalizing flows, compared to GANs and VAEs.
A technical explanation of Variational Autoencoders (VAEs), covering their theory, latent space, and how they generate new data.
Explores the evolution from basic Autoencoders to Beta-VAE, covering their architecture, mathematical notation, and applications in dimensionality reduction.
Explores a neural network model, sketch-rnn, that generates vector drawings by learning from human sketch sequences, mimicking abstract visual concepts.
