The Genodesic
Trajectory Reconstruction using Geodesics with respect to a Distance Based Metric learned via Score Matching applied to sequencing count data.
2025
When Massive Parallelism Is Not Enough: Optimizing the Hamming Matrix
Computing the Hamming Matrix suits GPU parallelism, but its low arithmetic intensity demands careful memory optimization to beat CPUs.
2024
Fixing Lightroom’s Automatic Photo Adjustment using Machine Learning
Adapting a Vision Transformer to find image rendering settings suitable for HDR image editing from small training datasets.
Exploring Skip Connections in MLPs
Investigating the Behaviour of an MLP under a novel Skip Configuration.