XLNet
XLNet is a generalized autoregressive pretraining method for natural language processing that integrates the advantages of Transformer-XL and permutation language modeling, improving performance on various NLP tasks.
autoregressive models
Masked autoregressive flow (MAF)
Masked autoregressive flow (MAF) is a type of normalizing flow used in machine learning for density estimation and generative modeling. It employs autoregressive models combined with masking techniques to create flexible, invertible transformations that allow efficient sampling and likelihood evaluation.