Variational Autoencoder
A generative model that learns to encode input data into a latent space and then decode from that space to reconstruct the original data, often used for generating new data samples.
Category: Generative AI
Disentangled Object Sampling
A technique designed to mitigate insufficient object generation and concept confusion in complex multi-object scenes.
Video Diffusion Model
A generative model that creates videos by diffusing information over time, often conditioned on textual or visual inputs.
Retrieval-Augmented Generation
RAG is a method that combines retrieval of relevant information with generative models to enhance the quality of predictions.