Our impact

The Erlangen AI Hub is one of nine AI research hubs across the UK funded by EPSRC. It sits at the centre of a collaborative network of stakeholders, fusing academic and industry knowledge with real world action, bringing world-leading research to applied settings. We aim to achieve rapid and enduring impact in science, industry, government and beyond.  

The hub forms the basis for exciting, new cross-disciplinary partnerships, within and across research communities, establishing long-term capability that is critical in underpinning the future of AI and the UK ecosystem. It also educates and nurtures young talent through its PhD programme, supporting the development of a diverse and dynamic AI talent and skills pipeline, as its graduates go on to develop the next generation of AI systems in the UK and beyond.  

The hub’s world-class research in AI is facilitating a new generation of AI methods and technology that can be exploited by industry, and our close involvement with industrial partners provides a valuable route to early impact. Our output also impacts key policy makers across government departments and bodies, NGOs, and the third sector, boosting the UK’s capability and standing in AI research and innovation in a highly competitive international environment.

Alessandro Abate / Thom Badings / Giuseppe De Giacomo / Francesco Fabiano
Best-Effort Policies for Robust Markov Decision Processes.
https://www.arxiv.org/abs/2508.07790

Alessandro Abate / David Parker
Efficient Solution and Learning of Robust Factored MDPs.
Yannik Schnitzer, Alessandro Abate, David Parker
https://arxiv.org/abs/2508.00707

Thom Badings / Alessandro Abate
Probabilistic Alternating Simulations for Policy Synthesis in Uncertain Stochastic Dynamical Systems.
Thom Badings, Alessandro Abate
https://www.arxiv.org/abs/2508.05062

Michael Bronstein 
Fisher Flow Matching for Generative Modelling over Discrete Data.
Book Title: Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS)
Oscar Davis‚ Samuel Kessler‚ Mircea Petrache‚ İsmail İlkan Ceylan‚ Michael Bronstein and Avishek Joey Bose 
https://arxiv.org/abs/2405.14664

Michael Bronstein 
Future Directions in the Theory of Graph Machine Learning.
Christopher Morris, Fabrizio Frasca, Nadav Dym, Haggai Maron, İsmail İlkan Ceylan, Ron Levie, Derek Lim, Michael Bronstein, Martin Grohe, Stefanie Jegelka 
https://arxiv.org/abs/2402.02287

Michael Bronstein 
Homomorphism Counts As Structural Encodings For Graph Learning (ICLR).
Linus Bao, Emily Jin, Michael Bronstein, İsmail İlkan Ceylan, Matthias Lanzinger 
https://arxiv.org/pdf/2410.18676 

Michael Bronstein 
Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction.
Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Zachary Quinn, Chenghao Liu, Sarthak Mittal, Nouha Dziri, Michael Bronstein, Yoshua Bengio, Pranam Chatterjee, Alexander Tong, Avishek Joey Bose
https://arxiv.org/abs/2410.08134 

Michael Bronstein 
FORT: Forward-Only Regression Training of Normalizing Flows.
Danyal Rehman, Oscar Davis, Jiarui Lu, Jian Tang, Michael Bronstein, Yoshua Bengio, Alexander Tong, Avishek Joey Bose
https://arxiv.org/abs/2506.01158

Michael Bronstein 
GradMetaNet: An Equivariant Architecture for Learning on Gradients.
Yoav Gelberg, Yam Eitan, Aviv Navon, Aviv Shamsian, Theo (Moe) Putterman, Michael Bronstein, Haggai Maron
https://arxiv.org/abs/2507.01649

Michael Bronstein 
Of Graphs and Tables: Zero-Shot Node Classification with Tabular Foundation Models.
Adrian Hayler, Xingyue Huang, İsmail İlkan Ceylan, Michael Bronstein, Ben Finkelshtein
https://arxiv.org/abs/2509.07143

Michael Bronstein 
Flow-Based Fragment Identification via Binding Site-Specific Latent Representations.
Rebecca Manuela Neeser, Ilia Igashov, Arne Schneuing, Michael Bronstein, Philippe Schwaller, Bruno Correia
https://www.arxiv.org/abs/2509.13216

Michael Bronstein 
Learning Inter-Atomic Potentials without Explicit Equivariance.
Ahmed Elhag, Arun Raja, Alex Morehead, Samuel Blau, Garrett Morris, Michael Bronstein
https://www.arxiv.org/abs/2510.00027

Michael Bronstein 
Carré du champ flow matching: better quality-generalisation tradeoff in generative models.
Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, Adam Gosztolai
https://www.arxiv.org/abs/2510.05930

Michael Bronstein 
gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity.
Hugh Blayney, Álvaro Arroyo, Xiaowen Dong, Michael M. Bronstein
https://arxiv.org/abs/2510.08450

Michael Bronstein 
Connected Causal Graphs for Real-World Science.
Amine M’Charrak, Abbavaram Gowtham Reddy, Thomas Lukasiewicz, Michael M. Bronstein, Krikamol Muandet
https://openreview.net/forum?id=i0rFGQBGzs

Alessandro Abate / David Parker
Certifiably Robust Policies for Uncertain Parametric Environments.
Yannik Schnitzer, Alessandro Abate, David Parker
https://arxiv.org/abs/2408.03093

Thom Badings
Policy Verification in Stochastic Dynamical Systems Using Logarithmic Neural Certificates.
Thom Badings, Wietze Koops, Sebastian Junges, Nils Jansen
https://link.springer.com/chapter/10.1007/978-3-031-98679-6_16

Thom Badings / Alessandro Abate
Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics.
Mahdi Nazeri, Thom Badings, Anne-Kathrin Schmuck, Sadegh Soudjani, Alessandro Abate
https://arxiv.org/abs/2508.15543

Michael Bronstein 
Metric Flow Matching for Smooth Interpolations on the Data Manifold.
Kacper Kapusniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alexander Tong, Michael Bronstein, Avishek Joey Bose, Francesco Di Giovanni
https://arxiv.org/abs/2405.14780

Michael Bronstein 
Balancing Efficiency And Expressiveness: Subgraph GNNs With Walk-Based Centrality.
Joshua Southern, Yam Eitan, Guy Bar-Shalom, Michael Bronstein, Haggai Maron and Fabrizio Frasca 
https://arxiv.org/pdf/2501.03113 

Michael Bronstein 
Relaxed Equivariance via Multitask Learning.
Ahmed A. Elhag, T. Konstantin Rusch, Francesco Di Giovanni, Michael Bronstein
https://arxiv.org/abs/2410.17878 

Michael Bronstein
Scalable Equilibrium Sampling with Sequential Boltzmann Generators.
CB Tan, AJ Bose, C Lin, L Klein, MM Bronstein, A Tong
https://arxiv.org/abs/2502.18462

Michael Bronstein
Flow-Based Fragment Identification via Contrastive Learning of Binding Site-Specific Latent Representations.
RM Neeser, I Igashov, A Schneuing, MM Bronstein
https://openreview.net/pdf/0e5806df934264cbb1a7273ee4c3b2eb94545140.pdf

Michael Bronstein
TGM: A Modular Framework for Machine Learning on Temporal Graphs.
Jacob Chmura, Shenyang Huang, Ali Parviz, Farimah Poursafaei, Michael M. Bronstein, Guillaume Rabusseau, Matthias Fey, Reihaneh Rabbany
https://openreview.net/pdf?id=7Bzm7GrP4d

Michael Bronstein
Temporal Graph Learning Workshop.
Shenyang Huang, Daniele Zambon, Andrea Cini, Farimah Poursafaei, Jacob Chmura, Julia Gastinger, Reihaneh Rabbany, Michael Bronstein
https://dl.acm.org/doi/abs/10.1145/3711896.3737855

Michael Bronstein
Planner Aware Path Learning in Diffusion Language Models Training.
Fred Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks, Shuibai Zhang, Anru R. Zhang, Michael Bronstein, Avishek Joey Bose, Alexander Tong
https://www.arxiv.org/abs/2509.23405

Michael Bronstein
Flock: A Knowledge Graph Foundation Model via Learning on Random Walks.
Jinwoo Kim, Xingyue Huang, Krzysztof Olejniczak, Kyungbin Min, Michael Bronstein, Seunghoon Hong, İsmail İlkan Ceylan
https://arxiv.org/abs/2510.01510

Michael Bronstein
TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs.
Jacob Chmura, Shenyang Huang, Tran Gia Bao Ngo, Ali Parviz, Farimah Poursafaei, Jure Leskovec, Michael Bronstein, Guillaume Rabusseau, Matthias Fey, Reihaneh Rabbany
https://arxiv.org/abs/2510.07586

Michael Bronstein
LLMs can hide text in other text of the same length.
Antonio Norelli, Michael Bronstein
https://arxiv.org/abs/2510.20075v1

Michael Bronstein
Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds.
Oscar Davis, Michael S. Albergo, Nicholas M. Boffi, Michael M. Bronstein, Avishek Joey Bose
https://arxiv.org/html/2510.21608v1

Coralia Cartis
Global Optimality Characterizations and Algorithms for Minimizing Quartically-Regularized Third-Order Taylor Polynomials.
Wenqi Zhu, Coralia Cartis
https://arxiv.org/abs/2504.20259

Coralia Cartis
On the Neural Feature Ansatz for Deep Neural Networks.
Edward Tansley, Estelle Massart, Coralia Cartis
https://arxiv.org/abs/2510.15563v1

Giuseppe De Giacomo
Solving MDPs with LTLf+ and PPLTL+ Temporal Objectives.
Giuseppe De Giacomo, Yong Li, Sven Schewe, Christoph Weinhuber, Pian Yu
https://arxiv.org/abs/2505.17264

Giuseppe De Giacomo
Emerson-Lei and Manna-Pnueli Games for LTLf+ and PPLTL+ Synthesis.
Daniel Hausmann, Shufang Zhu, Gianmarco Parretti, Christoph Weinhuber, Giuseppe De Giacomo, Nir Piterman
https://arxiv.org/abs/2508.14725

Giuseppe De Giacomo
Do Your Best, but Don’t Take Too Many Chances: LTLf Synthesis of Minimal Best-Effort Strategies in FOND Domains.
Giuseppe De Giacomo, Gianmarco Parretti
https://www.researchgate.net/publication/396788782

Francesco Fabiano
Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics.
Giovanni Briglia, Francesco Fabiano, Stefano Mariani
https://arxiv.org/abs/2508.12840

Francesco Fabiano
Advancing Sustainable Development through AIxSDGs.
DS Steingard, F Fabiano
Link

Jeffrey Giansiracusa 
Emergent photons and mechanisms of confinement.
Jeffrey Giansiracusa, David Lanners, Tin Sulejmanpasic
https://arxiv.org/abs/2505.00079

Peter Grindrod 
Modularity, Hierarchical Flows and Symmetry of the Drosophila Connectome.
Grindrod P, Lambiotte R, Sahasrabuddhe R 
https://arxiv.org/abs/2412.13202

Peter Grindrod 
Word Meanings in Transformer Language Models.
Jumbly Grindrod, Peter Grindrod 
https://arxiv.org/abs/2508.12863

Heather Harrington
Cover Learning for Large-Scale Topology Representation.
Luis Scoccola, Uzu Lim, Heather Harrington
https://arxiv.org/abs/2503.09767

Heather Harrington
Discrete signature tensors for persistence landscapes.
Vincenzo Galgano, Heather A. Harrington, Daniel Tolosa
https://arxiv.org/abs/2505.02800

Heather Harrington
A topological approach to the Cahn-Hilliard equation and hyperuniform fields.
Abel H. G. Milor, Otto Sumray, Heather A. Harrington, Axel Voigt, Marco Salvalaglio
https://arxiv.org/abs/2509.05339

Jeroen Lamb 
Learning Iterated Function Systems from Time Series of Partial Observations.
Emilia Gibson, Jeroen S.W. Lamb
https://arxiv.org/abs/2508.13794

Coralia Cartis
On Global Rates for Regularization Methods based on Secant Derivative Approximations.
Coralia Cartis, Sadok Jerad
https://arxiv.org/abs/2509.07580

Giuseppe De Giacomo
LTLf+ and PPLTL+: Extending LTLf and PPLTL to Infinite Traces.
Benjamin Aminof, Giuseppe De Giacomo, Sasha Rubin, Moshe Y. Vardi
https://arxiv.org/abs/2411.09366

Giuseppe De Giacomo
Computational Grounding of Responsibility Attribution and Anticipation in LTLf.
Giuseppe De Giacomo, Emiliano Lorini, Timothy Parker, Gianmarco Parretti
https://arxiv.org/abs/2410.14544

Giuseppe De Giacomo
LTLf Adaptive Synthesis for Multi-Tier Goals in Nondeterministic Domains.
Giuseppe De Giacomo, Gianmarco Parretti, Shufang Zhu
https://arxiv.org/abs/2504.20983

Giuseppe De Giacomo
LTL Synthesis under Multi-Agent Environment Assumptions.
Benjamin Aminof, Giuseppe De Giacomo, Giuseppe Perelli, Sasha Rubin
https://kth.diva-portal.org/smash/record.jsf?pid=diva2%3A1614597&dswid=-6099

Jeffrey Giansiracusa 
Projective hypersurfaces in tropical scheme theory I: the Macaulay ideal.
Alex Fink, Jeffrey Giansiracusa, Noah Giansiracusa, Joshua Mundinger
https://arxiv.org/abs/2405.16338

Aideen Fay
Holes in Latent Space: Topological Signatures Under Adversarial Influence.
Aideen Fay, Inés García-Redondo, Qiquan Wang, Haim Dubossarsky, Anthea Monod
https://arxiv.org/abs/2505.20435

Jeffrey Giansiracusa 
Topological Data Analysis of Abelian Magnetic Monopoles in Gauge Theories, to appear in Proceedings of the 41st International Symposium on Lattice Field Theory (LATTICE2024). 
X. Crean, J. Giansiracusa and B. Lucini
https://arXiv.org/2501.19320

Peter Grindrod 
Dynamical Systems on Generalised Klein. Bottles. Entropy 2025, 27, 119.
Grindrod, P.; Yim, K.M.
https://doi.org/10.3390/e27020119

Peter Grindrod 
On The Next Generation For
Neuromorphic Computing and
Neuromorphic AI.
https://www.researchgate.net/publication/393280208

Heather Harrington 
Fibers of point cloud persistence 
David Beers, Heather A Harrington, Jacob Leygonie, Uzu Lim, Louis Theran
https://arxiv.org/abs/2411.08201 

Heather Harrington
Topological model selection: a case-study in tumour-induced angiogenesis.
Robert A McDonald, Helen M Byrne, Heather A Harrington, Thomas Thorne, Bernadette J Stolz
https://arxiv.org/abs/2504.15442

Iolo Jones 
Manifold Diffusion Geometry: Curvature, Tangent Spaces, and Dimension 
https://arxiv.org/abs/2411.04100 

Renaud Lambiotte 
Mean-field approximation for networks with synchrony-driven adaptive coupling. Chaos: An Interdisciplinary Journal of Nonlinear Science, 35(1). 
Fennelly, N., Neff, A., Lambiotte, R., Keane, A., & Byrne, Á.
https://pubs.aip.org/aip/cha/article/35/1/013152/3332426 

Renaud Lambiotte 
Detection of anomalous spatio-temporal patterns of app traffic in response to catastrophic events.  
Medina, S., Babul, S. A., Sahasrabuddhe, R., LaRock, T., Lambiotte, R., & Pedreschi, N.
https://arxiv.org/abs/2409.01355 

Renaud Lambiotte 
Concise network models of memory dynamics reveal explainable patterns in path data.
Sahasrabuddhe R, Lambiotte R, Rosvall M 
https://www.science.org/doi/full/10.1126/sciadv.adw4544

Renaud Lambiotte 
Garbage in Garbage out: Impacts of data quality on criminal network intervention.
Wang Ngai Yeung, Riccardo Di Clemente, Renaud Lambiotte
https://arxiv.org/abs/2501.01508 

Renaud Lambiotte
From reductionism to realism: Holistic mathematical modelling for complex biological systems.
R Nartallo-Kaluarachchi, R Lambiotte, A Goriely
https://arxiv.org/abs/2503.20511

Renaud Lambiotte
Entropy-based models to randomize real-world hypergraphs.
Fabio Saracco, Giovanni Petri, Renaud Lambiotte, Tiziano Squartini
https://arxiv.org/abs/2207.12123

Renaud Lambiotte
Repairing a failed clustered network by external activation.
Xun Zhou, Gaogao Dong, Fan Wang, Ruijin Du, Renaud Lambiotte
https://www.sciencedirect.com/science/article/abs/pii/S0960077925009099

Renaud Lambiotte
Quantifying digital habits.
Matthew Sharpe, Michael Bowen, Renaud Lambiotte
https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-025-00581-7

Renaud Lambiotte 
Louvain for signed networks.
Pougué-Biyong, J. N., & Lambiotte, R.
https://arxiv.org/abs/2407.19288 

Renaud Lambiotte 
Matrix-weighted networks for modeling multidimensional dynamics.
Tian, Y., Kojaku, S., Sayama, H., & Lambiotte, R.  
https://arxiv.org/abs/2410.05188 

Renaud Lambiotte 
Strong and weak random walks on signed networks. npj Complexity 2, 4 (2025). 
Babul, S.A., Tian, Y. & Lambiotte, R.
https://www.nature.com/articles/s44260-025-00027-1 

Renaud Lambiotte
Hippocampal Ripple Diversity organises Neuronal Reactivation Dynamics in the Offline Brain.
Manfredi Castelli, Vítor Lopes-dos-Santos, Giuseppe P. Gava, Renaud Lambiotte, David Dupret
https://www.biorxiv.org/content/10.1101/2025.03.11.642571v2

Renaud Lambiotte
Coarse-graining Directed Networks with Ergodic Sets Preserving Diffusive Dynamics.
E Hormann, R Lambiotte
https://arxiv.org/abs/2503.18823

Renaud Lambiotte
Nonequilibrium physics of brain dynamics.
Ramón Nartallo-Kaluarachchi, Morten L. Kringelbach, Gustavo Deco, Renaud Lambiotte, Alain Goriely
https://arxiv.org/abs/2504.12188

Renaud Lambiotte
Global Synchronization in Matrix-Weighted Networks.
Anna Gallo, Yu Tian, Renaud Lambiotte, Timoteo Carletti
https://arxiv.org/abs/2507.12322

Renaud Lambiotte
Gremban Expansion for Signed Networks: Algebraic and Combinatorial Foundations for Community-Faction Detection.
Fernando Diaz-Diaz, Karel Devriendt, Renaud Lambiotte
https://www.researchgate.net/publication/395582839

Renaud Lambiotte
Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion.
Cristina López Amado, Tassilo Schwarz, Yu Tian, Renaud Lambiotte
https://openreview.net/forum?id=EgRvGMd2Zp

Ran Levi 
Foundations of Differential Calculus for modules over posets. 
J. Brodzki, R. Levi, H. Rihiimaki
https://arxiv.org/abs/2307.02444v4 

Terry Lyons 
Higher Order Lipschitz Sandwich Theorems. 
McLeod, Andrew; Lyons, Terry
Journal of the London Mathematical Society 
https://arxiv.org/abs/2404.06849  

Anthea Monod 
Tropical Fréchet Means.
Lin B, Ferry K, Améndola C, Monod A, Yoshida R 
https://arxiv.org/abs/2502.05322 

Anthea Monod 
Tropical Gradient Descent.
Talbut R, Monod A 
https://arxiv.org/abs/2405.19551 

Anthea Monod 
A Topological Gaussian Mixture Model for Bone Marrow Morphology in Leukaemia.
Wang Q, Song A, Batsivari A, Bonnet D, Monod A 
https://arxiv.org/abs/2408.13685 

Anthea Monod
Computing the Tropical Abel–Jacobi Transform and Tropical Distances for Metric Graphs.
Yueqi Cao, Anthea Monod
https://arxiv.org/abs/2504.11619

Gesine Reinert 
Learning to Fuse Temporal Proximity Networks: A Case Study in Chimpanzee Social Interactions.
He, Y., Sandel, A., Wipf, D., Cucuringu, M., Mitani, J., & Reinert, G.
https://arxiv.org/abs/2502.00302  

Gesine Reinert 
A Kernelised Stein Discrepancy for Assessing the Fit of Inhomogeneous Random Graph Models.
Anum Fatima, Gesine Reinert
https://arxiv.org/abs/2505.21580 

Gesine Reinert 
Graph models of brain state in deep anaesthesia reveal sink state dynamics of reduced spatiotemporal complexity.
James Wilsenach, Charlotte M. Deane, Gesine Reinert, Katie Warnaby
https://direct.mit.edu/netn/article/doi/10.1162/netn.a.27/131738/

Primoz Skraba 
Persistent (Co)Homology in Matrix Multiplication Time.
Dmitriy Morozov, Primoz Skraba
https://arxiv.org/abs/2412.02591

Ulrike Tillmann / Heather Harrington 
Topology across Scales on Heterogeneous Cell Data.
Maria Torras-Pérez, Iris H.R. Yoon, Praveen Weeratunga, Ling-Pei Ho, Helen M. Byrne, Ulrike Tillmann, Heather A. Harrington
https://arxiv.org/abs/2505.02717

Terry Lyons 
Signature methods in machine learning.  
EMS Surveys in Mathematical Sciences.
Terry Lyons, Andrew D. McLeod
https://arxiv.org/abs/2206.14674  

Anthea Monod 
On the Limitations of Fractal Dimension as a Measure of Generalization.
Tan CB, Garcia-Redondo I, Wang Q, Bronstein MM, Monod A (NeurIPS 2024) 
https://arxiv.org/abs/2406.02234

Anthea Monod 
Stability for Inference with Persistent Homology Rank Functions. Wang Q, García‐Redondo I, Faugère P, Henselman‐Petrusek G, Monod A 
https://arxiv.org/abs/2307.02904   

Anthea Monod 
Tropical Expressivity of Neural Networks.
Lezeau P, Walker T, Cao Y, Bhatia S, Monod A 
https://arxiv.org/abs/2405.20174 

Anthea Monod
Confidence Bands for Multiparameter Persistence Landscapes.
I García-Redondo, A Monod, Q Wang
https://arxiv.org/abs/2504.01113

Edward Pearce-Crump
Permutation Equivariant Neural Networks for Symmetric Tensors.
https://arxiv.org/abs/2503.11276

Gesine Reinert
Triadic structures in multislice networks.
K Ren, T Trauthwein, G Reinert
https://arxiv.org/abs/2504.00508

Gesine Reinert
Individualised Counterfactual Examples Using Conformal Prediction Intervals.
James M. Adams, Gesine Reinert, Lukasz Szpruch, Carsten Maple, Andrew Elliott
https://arxiv.org/abs/2505.22326

Gesine Reinert/Sam Cohen
Generalization and Robustness of the Tilted Empirical Risk.
Gholamali Aminian, Amir R. Asadi, Tian Li, Ahmad Beirami, Gesine Reinert, Samuel N. Cohen
https://arxiv.org/abs/2409.19431

Rubén Sánchez-García
Equitability and explosive synchronisation in multiplex and higher-order networks.
Kirill Kovalenko, Gonzalo Contreras-Aso, Charo I. del Genio, Stefano Boccaletti, Rubén Sánchez-García
https://arxiv.org/abs/2507.09319

Jared Tanner
Mind the Gap: a Spectral Analysis of Rank Collapse and Signal Propagation in Attention Layers.
Alireza Naderi, Thiziri Nait Saada, Jared Tanner
https://arxiv.org/abs/2410.07799