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!