@article{singh2025diffusion,
author = {Singh, Mukul and Verbruggen, Gust and Le, Vu and Gulwani, Sumit},
title = {Diffusion is a code repair operator and generator},
year = {2025},
month = {August},
abstract = {Code diffusion models generate code by iteratively removing noise from the latent representation of a code snippet. During later steps of the diffusion process, when the code snippet has almost converged, differences between discrete representations of these snippets look like last-mile repairs applied to broken or incomplete code. We evaluate the extent to which this resemblance can be exploited to leverage pre-trained code diffusion models for the problem of last-mile repair by considering two applications with significant potential. First, we can leverage the diffusion model for last-mile repair by adding noise to a broken code snippet and resuming the diffusion process. Second, we can leverage the diffusion model to generate arbitrary amount of training data for last-mile repair tasks (that are computationally more efficient) by sampling an intermediate program (input) and the final program (output) from the diffusion process. We perform experiments on 3 domains (Python, Excel and PowerShell) to evaluate applications, as well as analyze properties.},
url = {http://approjects.co.za/?big=en-us/research/publication/diffusion-is-a-code-repair-operator-and-generator/},
journal = {ArXiv},
volume = {abs/2508.11110},
}