Institut
Allgemeine Informationen über das Institut wie z.B. Leitbild, Organisationsstruktur, Mitarbeiterverzeichnis, Geschichte, Anfahrtsbeschreibung usw.

Mehr anzeigen
Forschung
Wissenschaftliches Profil mit allen Forschungsgruppen, Themen, Projekten sowie weiteren Forschungsrubriken des Instituts.

Mehr anzeigen
News
Nachrichten und Pressemitteilungen des Instituts, sowie ein Pressearchiv.

Mehr anzeigen
Veranstaltungen
Übersicht über alle Veranstaltungen rund um das Institut, wie Vorträge, Seminare, Vorlesungen, Workshops, Konferenzen und öffentliche Veranstaltungen.

Mehr anzeigen
Publikationen
Übersicht über alle wissenschaftlichen Veröffentlichungen des Instituts sowie über unsere Preprint- und Software-Archive.

Mehr anzeigen
Karriere
Informationen zu Stellenangeboten am Institut, Karriere Benefits, dem Graduiertenkolleg und der Betreuung von Postdocs.

Mehr anzeigen

Veranstaltungen
MiS/ScaDS/CBS Math and AI Meeting

Universität Leipzig

ScaDS.AI D05.17

seminar

21.11.25 05.12.25

MiS/ScaDS/CBS Math and AI Meeting

seminar

21.11.25 05.12.25

MiS/ScaDS/CBS Math and AI Meeting

- Upcoming Events
- Previous Events

Upcoming Events of this Seminar

talk

21.11.25, 14:00

Learning Geometrically and Topologically Aligned Representations with Topologically Regularized Autoencoders Learning Geometrically and Topologically Aligned Representations with Topologically…

Samuel Graepler (Leipzig University)

Details anzeigen

talk

05.12.25, 14:00

to be announced to be announced

Details anzeigen

Previous Events


07.11.25	Nahid Tobati (MPI for Human Cognitive and Brain Sciences) : Geometry matters: insights from Ollivier–Ricci curvature and Ricci Flow into representational alignment Representational similarity analysis (RSA) is widely used to analyze the alignment between humans and neural networks; however, conclusions based on this approach can be misleading without considering the underlying representational geometry. Our work introduces a framework using Ollivier Ricci Curvature and Ricci Flow to analyze the fine-grained local structure of representations. This approach is agnostic to the source of the representational space, enabling a direct geometric comparison between human behavioral judgments and a model's vector embeddings. We apply it to compare human similarity judgments for 2D and 3D face stimuli with a baseline 2D-native network (VGG-Face) and a variant of it aligned to human behavior. Our results suggest that geometry-aware analysis provides a more sensitive characterization of discrepancies and geometric dissimilarities in the underlying representations that remain only partially captured by RSA. Notably, we reveal geometric inconsistencies in the alignment when moving from 2D to 3D viewing conditions. This highlights how incorporating geometric information can expose alignment differences missed by traditional metrics, offering deeper insight into representational organization.
24.10.25	Nikola Milosevic (Max Planck Institute for Cognitive and Brain Sciences) : On the Generality of Relative Entropy Policy Iteration. Relative Entropy Policy Iteration is a reinforcement learning framework that alternates between policy evaluation and relative-entropy–regularized improvement. A prominent example is Maximum a Posteriori Policy Optimization (MPO), widely used in robotics and control. In this talk, I revisit the underlying principle of MPO from a theoretical perspective and suggest that its core idea may extend to much more general settings, including nonlinear utilities and continuous state-action spaces. The theory is still incomplete, but I will outline a possible mathematical framework and hope to gather feedback and ideas from the audience on how to formalize and analyze this perspective.
10.10.25	Yu Tian (MPI PKS & MPI CBG) : Matrix-weighted networks for modeling multidimensional dynamics Networks are powerful tools for modeling interactions in complex systems. While traditional networks use scalar edge weights, many real-world systems involve multidimensional interactions. For example, in social networks, individuals often have multiple interconnected opinions that can affect different opinions of other individuals, which can be better characterized by matrices. We propose a general framework for modeling such multidimensional interacting dynamics: matrix-weighted networks (MWNs). We present the mathematical foundations of MWNs and examine consensus dynamics and random walks within this context. Our results reveal that the coherence of MWNs gives rise to non-trivial steady states that generalize the notions of communities and structural balance in traditional networks.