Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

Top Papers in Autoregressive models

Share

Graph2Graph Learning with Conditional Autoregressive Models

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

More...

Share

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

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

More...

Share

Glancing Transformer for Non-Autoregressive Neural Machine Translation

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

More...

Share

LMConv: An Ensemble of Distribution Estimators for High-Dimensional generative Models

Locally Masked Convolution for Autoregressive Models

Read More...

Share

Predictive Sampling of Autoregressive Models

Predictive Sampling with Forecasting Autoregressive Models

Read More...

Share

Causal Forecasting:Generalization Bounds for Autoregressive Models

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

More...

Share

Adaptive Tree Search for Non-Destructive Translation Models

Enabling arbitrary translation objectives with Adaptive Tree Search

Read More...

Share

Blockwise Parallel Decoding for Deep Autoregressive Models

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

More...

Share

Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation

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

More...

Share

Improved Autoregressive Modeling with Distribution Smoothing

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

More...

Share

Integrating Vector Quantised Variational Autor with Denoising Diffusion Probabilistic Models for Image Generation

Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation

Read More...

Share

Limitations of Autoregressive Models and Their Alternatives

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

More...

Share

Anytime Sampling of Autoregressive Models

Anytime Sampling for Autoregressive Models via Ordered Autoencoding

Read More...

Share

Estimating effects within nonlinear autoregressive models: a case study on the impact of child access prevention laws on firearm mortality

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

More...

Share

Pixel-Stega: Generative Image Steganography Based on Autoregressive Models

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

More...

Share

Masked Autoregressive Flow for Density Estimation

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

More...

Share

Adaptive Categorical Discretization

AdaCat: Adaptive Categorical Discretization for Autoregressive Models

Read More...

Share

Cascaded Text Generation with Markov Transformers

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

More...

Share

ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis

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

More...

Share

Improving Non-autoregressive Generation with Mixup Training

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

More...

Share

More