Search
MPI MiS Seminar room: Several people are standing in front of a blackboard
Research Group

Mathematical Structures in AI - Publications

Explore the scholarly works of the Mathematical Structures in AI group. Browse journal articles, contributions in books and conference proceedings, academic theses, or discover our latest research through preprints. The names of the authors who worked on the publication during their time at the institute are shown in bold.


inBook
2026 Journal Open Access
Deniz Kucukahmetler, Maximilian Jean Hemmann, Julian Mosig von Aehrenfeld, Maximilian Amthor, Christian Deubel, Nico Scherf and Diaaeldin Taha

A comparative empirical study of relative embedding alignment in neural dynamical system forecasters

In: Proceedings of the geometry, topology, and machine learning workshop : 10-14 November 2025, Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany / Michael Bleher... (eds.)
[s. l.] : PMLR, 2026. - pp. 201-214
(Proceedings of machine learning research ; 325)
Preprint
2026 Repository Open Access
J. Maxwell Riestenberg, Diaaeldin Taha, Steve Trettel and Anna Wienhard

Certifying arithmeticity for two degree-six symplectic hypergeometric monodromy groups

inBook
2026 Journal Open Access
Michael Bleher, Freya Jensen, Levin Maier, Diaaeldin Taha and Anna Wienhard

Preface of geometry, topology, and machine learning 2025

In: Proceedings of the geometry, topology, and machine learning workshop : 10-14 November 2025, Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany / Michael Bleher... (eds.)
[s. l.] : PMLR, 2026. - i-vii
(Proceedings of machine learning research ; 325)
Book
2026 Journal Open Access
Michael Bleher, Freya Jensen, Levin Maier, Diaaeldin Taha and Anna Wienhard (Eds.)

Proceedings of the geometry, topology, and machine learning workshop : 10-14 November 2025, Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany

[s. l.] : PMLR, 2026.
(Proceedings of machine learning research ; 325)
inJournal
2026 Journal Open Access
Deniz Kucukahmetler, Maximilian Jean Hemmann, Julian Mosig von Aehrenfeld, Maximilian Amthor, Christian Deubel, Nico Scherf and Diaaeldin Taha

Relative geometry of neural forecasters : linking accuracy and alignment in learned latent geometry

In: Transactions on machine learning research, 2026 (2026) 2, pp. 1-29
Preprint
2026 Repository Open Access
Yuhan Peng, Junwen Dong, Yuzhi Zeng, Hao Li, Ce Ju, Huitao Feng, Diaaeldin Taha, Anna Wienhard and Kelin Xia

Sheaf neural networks on SPD manifolds : second-order geometric representation learning