Compara mètodes

	Variational Autoencoder	Model generatiu basat en la puntuació
Camp	Aprenentatge profund	Aprenentatge profund
Família	Machine learning	Machine learning
Any d'origen	2014	2019
Autor original	Kingma, D. P. & Welling, M.	Song, Y. & Ermon, S.
Tipus	Deep generative latent-variable model (encoder–decoder)	Score-based generative model (SDE framework)
Font seminal	Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR).	Song, Y. & Ermon, S. (2019). Generative Modeling by Estimating Gradients of the Data Distribution. NeurIPS 32, 11895–11907.
Àlies	Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model	Skor Tabanlı Üretici Model (Score-Based / SDE), score-based diffusion, SDE-based generative model, score SDE
Relacionats	5	5
Resum	The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.	A score-based generative model, introduced by Yang Song and Stefano Ermon in 2019 and generalized to the stochastic differential equation (SDE) framework in 2021, learns the gradient of the data density — the score — rather than predicting noise directly, and uses it to generate new samples. It is the mathematical generalization that unifies diffusion models under a continuous-time formulation.