Pith. sign in

REVIEW 1 cited by

Fast Generation for Convolutional Autoregressive Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1704.06001 v1 pith:4OCCQTFI submitted 2017-04-20 cs.LG cs.CVstat.ML

classification cs.LGcs.CVstat.ML
keywords generationmodelsautoregressiveconvolutionalfastmethodredundanttimes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

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\"{i}ve 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 $21\times$ and $183\times$ speedups respectively.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Discrete Diffusion Models for Language Generation

    cs.CL 2025-07 reject novelty 3.0 of 10

    This thesis reports an empirical D3PM versus autoregressive comparison on WikiText-103, but the claimed speed advantage is unsupported because the speed numbers duplicate NLL values.

Pith tools