publications

2026

1. ICML

   

   Riemannian Metric Matching for Scalable Geometric Modeling of Distributions

   Jacob Bamberger, Adam Gosztolai, Pierre Vandergheynst, Michael M. Bronstein, and Iolo Jones

   In Forty-third International Conference on Machine Learning, 2026

2025

1. ICLR

   

   Carré du champ flow matching: better quality-generalisation tradeoff in generative models

   Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, and Adam Gosztolai

   2025

   arXiv
2. NeurIPS

   

   Over-squashing in Spatiotemporal Graph Neural Networks

   Ivan Marisca, Jacob Bamberger, Cesare Alippi, and Michael M Bronstein

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

   arXiv
3. ICML

   

   On Measuring Long-Range Interactions in Graph Neural Networks

   Jacob Bamberger, Benjamin Gutteridge, Scott Roux, Michael M. Bronstein, and Xiaowen Dong

   In Forty-second International Conference on Machine Learning, 2025

   arXiv
4. ICLR

   

   Bundle Neural Network for message diffusion on graphs

   Jacob Bamberger, Federico Barbero, Xiaowen Dong, and Michael M. Bronstein

   In The Thirteenth International Conference on Learning Representations, 2025

   arXiv

2024

1. Good stackings, bislim structures, and invariant staggerings

   Jacob Bamberger, David Carrier, Jonah Gaster, and Daniel T Wise

   Michigan Mathematical Journal, 2024

   arXiv

2022

1. TAG in ML @ ICML

   

   A Topological Characterisation of Weisfeiler-Leman Equivalence Classes 

   Jacob Bamberger

   In Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, 2022

   arXiv
2. Failure of the finitely generated intersection property for ascending HNN extensions of free groups

   Jacob Bamberger and Daniel T Wise

   International Journal of Algebra and Computation, 2022

   arXiv