We present a graph neural network model for solving graph-to-graph learning problems. Most deep learning on graphs considers ``simple'' problems such as graph classification or regressing real-valued

This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the mode

Although non-autoregressive models with one-iteration generation achieve remarkable inference speed-up, they still fall behind their autoregressive counterparts in prediction accuracy. The non-autoreg

Despite the increasing relevance of forecasting methods, the causal implications of these algorithms remain largely unexplored. This is concerning considering that, even under simplifying assumptions

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutio

State-of-the-art neural machine translation models generate outputs autoregressively, where every step conditions on the previously generated tokens. This sequential nature causes inherent decoding la

While autoregressive models excel at image compression, their sample quality is often lacking. Although not realistic, generated images often have high likelihood according to the model, resembling th

Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol. While this is attractive, it means they cannot model distributions whose

Autoregressive models are widely used for the analysis of time-series data, but they remain underutilized when estimating effects of interventions. This is in part due to endogeneity of the lagged out

In this letter, we explored generative image steganography based on autoregressive models. We proposed Pixel-Stega, which implements pixel-level information hiding with autoregressive models and arith

Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers

The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependen

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, they incorporate image

While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a chall