iiinova — where your digital self keeps evolving

Martin Uray

@martinuray.bsky.social

Doing something with research and lecturing | Opinions are my own | born 357 ppm

Martin Uray @martinuray.bsky.social · 29/09/2025

Our paper “The Flood Complex – Large-Scale Persistent Homology on Millions of Points” is accepted at #NeurIPS25 🎉 📄 Preprint: arxiv.org/pdf/2509.22432 💻 Code: open + ready to use

arxiv.org

110

Martin Uray @martinuray.bsky.social · 05/08/2025

🚀 Just released: flooder – a fast, GPU-powered Python package for computing persistent homology on millions of points in Euclidean space. Topology at scale is here! 📦 pip install flooder 🔬 Preprint coming soon – stay tuned! #PersistentHomology #TDA #Python #MachineLearning

101

Martin Uray @martinuray.bsky.social · 14/05/2025

For all that are struggling with the #Overleaf #outage before the #NeurIPS2025 deadline: The git interface is still working, so you can pull your project from there, in case you can reconstruct the path. #servicepost

000

Martin Uray @martinuray.bsky.social · 14/05/2025

Overleaf goes down hours before NeurIPS deadline 🚨 Authors: screaming 🫠 Me: refreshing Overleaf like it’s a life support machine This isn’t a paper submission — it’s a psychological experiment. #NeurIPS2025 #Overleaf #AcademicChaos

110

Martin Uray @martinuray.bsky.social · 24/04/2025

Excited to share our latest paper: "Persistence-based Line Detection in Hough Space" w/ students Johannes Ferner & Angel Pop, and colleagues Saverio Messineo & @shuber3.bsky.social. arxiv.org/abs/2504.16114

arxiv.org

Persistence-based Hough Transform for Line Detection

The Hough transform is a popular and classical technique in computer vision for the detection of lines (or more general objects). It maps a pixel into a dual space -- the Hough space: each pixel is ma...

111