SUPR
Training new diffusion models for faster generative AI
Dnr:

NAISS 2025/22-730

Type:

NAISS Small Compute

Principal Investigator:

Akash Sharma

Affiliation:

Chalmers tekniska högskola

Start Date:

2025-05-15

End Date:

2026-06-01

Primary Classification:

10210: Artificial Intelligence

Allocation

Abstract

We are working on stochastic differential equations driven diffusion models. We are proposing new diffusion models interlaced with jump process to accelerate their sampling process. Our models have shown improved performance on toy data sets, we aim to deploy them on image data set which requires the use of GPU.