Jun 2026	I started my internship at Google DeepMind 🚀
May 2026	[🥳 Paper accepted] Mosaic was accepted to ICML 2026! See the twitter thread for details and a demo.
May 2026	[📰 New blog post] I shared my introduction to Triton which I gave to students at the University of Amsterdam, covering GPU basics, kernel fusion, and Flash Attention.
Feb 2026	I started my internship at CuspAI working with Govert Verkes and Pim de Haan on agentic material discovery.
Jan 2026	[🥳 Paper accepted] MSPT was accepted to CVPR 2026!
Jan 2026	[🥳 Paper accepted] AdS-GNN was accepted to ICLR 2026! See you all in Rio 🇧🇷!
Dec 2025	[🚨 New paper] We depeloped MSPT - parallelized multi-scale attention method based on hierarchical partitioning of data. It is incredibly fast and achieves SOTA performance on multiple PDE tasks.
Dec 2025	[🥳 Paper accepted] Our submission Adaptive Mesh Quantization for Neural PDE Solvers was accepted to TMLR! We suggest a data-driven way of quantizing message-passing neural networks inspired by speculative decoding.
Oct 2025	[🚨 Workshop paper] We introduce Conditional Clifford-Steerable convolution, where we condition the convolutional operator with auxiliary information, achieving highly expressive, equivariant, and efficient framework which we apply to PDE modelling. Accepted to AI4Science Workshop at NeurIPS 2025.
Oct 2025	I implemented Clifford neural networks in Triton, see flash-clifford. It is now the fastest implementation of equivariant neural networks, so do check it out if you are into it!
Jun 2025	[🤹 New blog post] I wrote a blog about Erwin where I describe the motivation behind it as well as where it lands in the current landscape of sub-quadratic architectures for irregular data.
Jun 2025	[🚨 Workshop paper] We introduce Ball Sparse Attention: a novel sub-quadratic attention mechanism for irregular data that merges Erwin and Native Sparse Attention. Fantastic effort from my students.
May 2025	Erwin was accepted to ICML 2025! See you all in Vancouver! Blog post soon 👀
Mar 2025	[🚨 Workshop paper] We introduce AdS-GNN: a conformal group invariant analogue of EGNN. On top of rotations and reflections it is also scale invariant. Accepted to ICLR 2025 Workshop on Machine Learning Multiscale Processes.
Feb 2025	[🚨 New paper] We developed a novel local attention mechanism for point clouds which is based on ball tree partitioning. Blazing fast and expressive, Erwin achieves SOTA on multiple physical benchmarks.
May 2024	Clifford-Steerable CNNs was accepted to ICML 2024! See you all in Vienna!
Feb 2024	Together with David Ruhe, Maurice Weiler and others, we have developed Clifford-Steerable CNNs - a new class of isometry-equivariant CNNs that are able to operate on pseudo-Euclidean spaces, such as Euclidean space and Minkowski spacetime. Really strong results on PDEs, new relativistic benchmark and lots of very cool math. The paper is available here.
Sep 2023	Our paper Implicit Convolutional Kernels for Steerable CNNs has been accepted to NeurIPS 2023! We developed a simple and efficient way to parameterize group equivariant convolutional kernels using implicit neural representation, which greatly simplifies the design of steerable CNNs. Check out the blog post for details.
Apr 2023	Absolutely thrilled to announce that I will join the University of Amsterdam and start my PhD this spring, working with Max Welling, Jan-Willem van de Meent and Alfons Hoekstra!
Nov 2022	Extremely proud to present the result of the LOGML research project I have been involved in for the last 3 months under the supervision of Gabriele Cesa. Equivariance for the win!
Aug 2022	Recently, I participated at ICPR 2022, where I presented the paper “Investigating Brain Connectivity with Graph Neural Networks and GNNExplainer”. The GitHub repo is available, and the recording will be released soon too.
Jul 2022	Our paper “Learning Generative Factors of EEG Data with Variational auto-encoders” was accepted to DGM4MICCAI 🎉 Happy to present the results in Singapur in September.
Jul 2022	In July, I participated in EEML summer school, Swiss Equivariant Workshop and LOGML summer school. Over there, I gave poster presentations and participated in a project led by Gabriele Cesa on implicit kernels for steerable CNNs. Stay tuned for the results!
Jun 2022	Last week I attended ML summer school in Krakow, where I presented our new paper on generative modelling in neuroscience.
Jun 2022	I participated in the Helmholtz AI conference and gave two poster presentations. One is about generative modelling in neuroscience, and the second is about ML for GISAXS reconstruction.
May 2022	I will be presenting the paper “Investigating Brain Connectivity with Graph Neural Networks and GNNExplainer” at ICPR 2022.
Mar 2022	I graduated from the Faculty of Computer Science of TU Dresden. See my thesis here.