About

I am a lecturer in Applied Mathematics at Stellenbosch University, South Africa. I recently completed my PhD in Applied Mathematics (dissertation), where I focused on computational efficiency and likelihood reliability in continuous-time normalising flows. My research interests lie in deep generative models, with particular focus on flow matching. I also have an interest in computer vision.

Before transitioning to academia, I worked as a software engineer in telecommunications, where I developed complex event processing applications and enhanced the frameworks supporting them. Additionally, I contributed to database integration, focusing on optimising data workflows.

Teaching

Below is a list of courses I am currently teaching and have taught in the past.

Publication and preprints

1. Multimodal base distributions in conditional flow matching generative models
   Shane Josias, Willie Brink
   British Machine Vision conference (BMVC), paper 492, 2024
   html | video | poster | supplementary
   

2. Multimodal base distributions for continuous-time normalising flows
   Shane Josias, Willie Brink
   The Symbiosis of Deep Learning and Differential Equations Workshop at NeurIPS, 2023
   html | poster
   

3. Deep learning approaches to landmark detection in tsetse wing images
   Dylan Geldenhuys, Shane Josias, Willie Brink, and Mulanga Makhubele, Cang Hui, Pietro Landi, Jeremy Bingham, John Hargrove, Marijn Hazelbag
   PLOS Computational Biology, 2023
   html | data
   

4. Jacobian norm regularisation and conditioning in neural ODEs
   Shane Josias, Willie Brink
   Communications in Computer and Information Science, 2022
   html | slides | poster
   

5. Class-selective mini-batching and multitask learning for visual relationship recognition
   Shane Josias, Willie Brink
   SAIEE Africa Research Journal, 2021
   html
   

6. Batch construction and multitask learning in visual relationship recognition
   Shane Josias, Willie Brink
   International SAUPEC/RobMech/PRASA Conference, 2020
   html | slides