Authors

Simon Lucey

Publications 2

Preprint Open access

Should We Skip Diffusion?

Yiping Ji, James Martens, Simon Lucey · 2026

Diffusion models learn semantic representations while generating images. In the Decoupled Diffusion Transformer (DDT), a condition encoder provides features that guide a velocity decoder in denoising. To enable effective denoising at all noise levels, these features must capture both high-level abstract structures and …

Preprint Open access

Optimizer Geometry Sets the Pace: Spectral Learning Dynamics in Matrix Factorization

Mahalakshmi Sabanayagam, Simon Lucey · 2026

Recent successes of matrix- and curvature-based optimizers have renewed interest in how update geometry shapes learning. These methods normalize or precondition updates, changing how different components progress during training. In deep matrix factorization, the geometry that slows gradient descent (GD) favors low-ran …

Co-authors

Yiping Ji James Martens Mahalakshmi Sabanayagam