# Fast Generation for Convolutional Autoregressive Models

arXiv: https://arxiv.org/abs/1704.06001 · HTML: https://mlsanity.com/paper/1704.06001/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2017.

## Built on by (most cited first, 14 of 14)

- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers](https://mlsanity.com/paper/2204.14217/) (2022)
- [Accelerating Transformer Inference for Translation via Parallel Decoding](https://mlsanity.com/paper/2305.10427/) (2023)
- [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021)
- [Progressive Distillation for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2202.00512/) (2022)
- [Autoregressive Conditional Neural Processes](https://mlsanity.com/paper/2303.14468/) (2023)
- [NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering](https://mlsanity.com/paper/2503.07076/) (2025)
- [Anytime Sampling for Autoregressive Models via Ordered Autoencoding](https://mlsanity.com/paper/2102.11495/) (2021)
- [Diffusion Models with Deterministic Normalizing Flow Priors](https://mlsanity.com/paper/2309.01274/) (2023)
- [Few-shot Image Generation Using Discrete Content Representation](https://mlsanity.com/paper/2207.10833/) (2022)
- [Lossless Image Compression Using a Multi-Scale Progressive Statistical Model](https://mlsanity.com/paper/2108.10551/) (2021)
- [A Tutorial on Adversarial Learning Attacks and Countermeasures](https://mlsanity.com/paper/2202.10377/) (2022)
- [Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency](https://mlsanity.com/paper/2109.12459/) (2021)
- [Discrete Diffusion Models for Language Generation](https://mlsanity.com/paper/2507.07050/) (2025)

## Abstract (arXiv)

Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a na"ive fashion where redundant computations are unnecessarily repeated. This results in slow generation, making such models infeasible for production environments. In this work, we describe a method to speed up generation in convolutional autoregressive models. The key idea is to cache hidden states to avoid redundant computation. We apply our fast generation method to the Wavenet and PixelCNN++ models and achieve up to 21× and 183× speedups respectively.