prof_pic.jpeg

Maksim Zhdanov

PhD student at AMLab

Hi!

>>> print(self.status)

2nd year PhD student at AMLab

>>> print(self.supervisors)

Max Welling, Jan-Willem van de Meent, and Alfons Hoekstra

>>> print(self.research_interests)

scalable architectures for large-scale simulations, hierarchical representations, geometric deep learning

latest posts

selected publications

  1. erwin.png
    Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
    Maksim Zhdanov, Max Welling, and Jan-Willem van de Meent
    preprint
  2. adsgnn.png
    AdS-GNN - a Conformally Equivariant Graph Neural Network
    Maksim Zhdanov, Nabil Iqbal, Erik J Bekkers, and 1 more author
    ICLR 2025 Workshop MLMP
  3. clifford_steerable.png
    Clifford-Steerable Convolutional Neural Networks
    Maksim Zhdanov, David Ruhe, Maurice Weiler, and 3 more authors
    ICML 2024

news

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!